From eae95d5671234e38316d565aa6e0bd7fd1116cb6 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Thu, 23 Mar 2023 23:28:57 +0100
Subject: [PATCH 01/60] add script insert wip

---
 insert_wordpress.py | 50 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)
 create mode 100644 insert_wordpress.py

diff --git a/insert_wordpress.py b/insert_wordpress.py
new file mode 100644
index 0000000..3576885
--- /dev/null
+++ b/insert_wordpress.py
@@ -0,0 +1,50 @@
+#!/usr/bin/python3
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse
+from requests.auth import HTTPBasicAuth
+from getpass import getpass
+import requests, os, argparse, logging
+
+
+if __name__ == '__main__':
+
+    month = {"janvier":"01", "février": "02", "mars": "03", "avril":"04", "mai": "05", "juin": "06", "juillet": "07", "août": "08", "septembre": "09", "octobre": "10", "novembre": "11", "décembre": "12"}
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--user", help="wordpress user", required=True)
+    parser.add_argument("--file", help="HTML file", required=True)
+    args = parser.parse_args()
+    password = getpass()
+    if len(password) == 0:
+        print("No password error !!! ")
+        exit(1)
+    basic = HTTPBasicAuth(args.user, password)
+
+    with open(args.file, 'r') as f:
+        contents = f.read()
+
+        soup = BeautifulSoup(contents, 'html.parser')
+        articletitle = soup.find_all("h2", class_="articletitle")
+        articlebody = soup.find_all("div", class_="articlebody")
+        articledate = soup.find_all("span", class_="articledate")
+        dateheader = soup.find_all("div", class_="dateheader")
+        itemfooter = soup.find_all("div", class_="itemfooter")
+        a = itemfooter[0].find_all("a", {"rel": True})
+        tag = []
+        for i in a:
+            rel = i.get("rel")
+            if rel[0] == 'tag':
+                tag.append(i.text)
+        print(tag)
+        title = articletitle[0].text
+        body = articlebody[0]
+        hour = articledate[0].text
+        time = dateheader[0].text.split(" ")
+        data = {"title":title, "content":body, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": [5]}
+        #print(data)
+        exit(0)
+
+    page = requests.post("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, data=data)
+    print(page.status_code)
+    if page.status_code == 201:
+        print(page.content)
\ No newline at end of file

From 3622e379428d5843cdfe767754ad5ba975cd278c Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Thu, 23 Mar 2023 23:49:42 +0100
Subject: [PATCH 02/60] add tags

---
 insert_wordpress.py | 31 ++++++++++++++++++++++++++-----
 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 3576885..cd9b3ed 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -7,9 +7,8 @@ import requests, os, argparse, logging
 
 
 if __name__ == '__main__':
-
+    tags = []
     month = {"janvier":"01", "février": "02", "mars": "03", "avril":"04", "mai": "05", "juin": "06", "juillet": "07", "août": "08", "septembre": "09", "octobre": "10", "novembre": "11", "décembre": "12"}
-
     parser = argparse.ArgumentParser()
     parser.add_argument("--user", help="wordpress user", required=True)
     parser.add_argument("--file", help="HTML file", required=True)
@@ -20,6 +19,13 @@ if __name__ == '__main__':
         exit(1)
     basic = HTTPBasicAuth(args.user, password)
 
+    page = requests.get("http://localhost:8080/wp-json/wp/v2/tags")
+
+    if page.status_code == 200:
+        tags = page.json()
+    print(tags)
+
+
     with open(args.file, 'r') as f:
         contents = f.read()
 
@@ -35,13 +41,28 @@ if __name__ == '__main__':
             rel = i.get("rel")
             if rel[0] == 'tag':
                 tag.append(i.text)
-        print(tag)
+        listtag = []
+        for i in tag:
+            tag_exist = False
+            for j in tags:
+                if j["name"] == i:
+                    tag_exist = True
+                    listtag.append(j["id"])
+            if tag_exist is False:
+                data = {"name": i}
+                page = requests.post("http://localhost:8080/wp-json/wp/v2/tags", auth=basic, data=data)
+                if page.status_code == 201:
+                    result = page.json()
+                    listtag.append(result["id"])
+
+
+        
         title = articletitle[0].text
         body = articlebody[0]
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
-        data = {"title":title, "content":body, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": [5]}
-        #print(data)
+        data = {"title":title, "content":body, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listtag}
+        print(data)
         exit(0)
 
     page = requests.post("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, data=data)

From 0c41dc3e651bb91c6b229ce83194a6421e79f703 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 27 Mar 2023 23:51:51 +0200
Subject: [PATCH 03/60] distinct tags and categories

---
 insert_wordpress.py | 58 ++++++++++++++++++++++++++-------------------
 1 file changed, 33 insertions(+), 25 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index cd9b3ed..86fab01 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -3,7 +3,7 @@ from bs4 import BeautifulSoup
 from urllib.parse import urlparse
 from requests.auth import HTTPBasicAuth
 from getpass import getpass
-import requests, os, argparse, logging
+import requests, os, argparse, logging, re
 
 
 if __name__ == '__main__':
@@ -19,13 +19,19 @@ if __name__ == '__main__':
         exit(1)
     basic = HTTPBasicAuth(args.user, password)
 
-    page = requests.get("http://localhost:8080/wp-json/wp/v2/tags")
-
-    if page.status_code == 200:
-        tags = page.json()
-    print(tags)
+    liste = ["categories", "tags"]
+    elements = {}
+    element = {}
+    listelement = {}
 
+    for i in liste:
+        page = requests.get("http://localhost:8080/wp-json/wp/v2/{0}".format(i))
+        if page.status_code == 200:
+            elements[i] = page.json()
+            element[i] = []
+            listelement[i] = []
 
+    
     with open(args.file, 'r') as f:
         contents = f.read()
 
@@ -36,34 +42,36 @@ if __name__ == '__main__':
         dateheader = soup.find_all("div", class_="dateheader")
         itemfooter = soup.find_all("div", class_="itemfooter")
         a = itemfooter[0].find_all("a", {"rel": True})
-        tag = []
         for i in a:
             rel = i.get("rel")
             if rel[0] == 'tag':
-                tag.append(i.text)
-        listtag = []
-        for i in tag:
-            tag_exist = False
-            for j in tags:
-                if j["name"] == i:
-                    tag_exist = True
-                    listtag.append(j["id"])
-            if tag_exist is False:
-                data = {"name": i}
-                page = requests.post("http://localhost:8080/wp-json/wp/v2/tags", auth=basic, data=data)
-                if page.status_code == 201:
-                    result = page.json()
-                    listtag.append(result["id"])
+                href = i.get("href")
+                if re.search(r'/tag/', href):
+                    element["tags"].append(i.text)
+                if re.search(r'/archives/', href):
+                    element["categories"].append(i.text)
+        for i in liste:
+            for j in element[i]:
+                element_exist = False
+                for k in elements[i]:
+                    if k["name"] == j:
+                        element_exist = True
+                        array = listelement[i].append(k["id"])
+                if element_exist is False:
+                    data = {"name": j}
+                    page = requests.post("http://localhost:8080/wp-json/wp/v2/{0}".format(i), auth=basic, data=data)
+                    if page.status_code == 201:
+                        result = page.json()
+                        listelement[i].append(result["id"])
 
 
-        
+      
+
         title = articletitle[0].text
         body = articlebody[0]
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
-        data = {"title":title, "content":body, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listtag}
-        print(data)
-        exit(0)
+        data = {"title":title, "content":body, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
 
     page = requests.post("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, data=data)
     print(page.status_code)

From 491f15ae3c0d12df0945a42458fc10a21c0c5bb0 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 28 Mar 2023 11:31:25 +0200
Subject: [PATCH 04/60] premier essai d'insertion d'article reussi

---
 insert_wordpress.py | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 86fab01..595a3d6 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -68,12 +68,27 @@ if __name__ == '__main__':
       
 
         title = articletitle[0].text
-        body = articlebody[0]
+        body = articlebody[0].find_all("p")
+        bodyhtml = "<p>"
+        for i in body:
+            if len(i.text) == 1:
+                bodyhtml = bodyhtml + "<br />"
+            else:
+                bodyhtml = bodyhtml + str(i).replace("<p>", "").replace("</p>", "").replace("<br>", "<br />") + "<br />"
+        bodyhtml = bodyhtml + "</p>"
+        print(bodyhtml)
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
-        data = {"title":title, "content":body, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
+        data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
+    params = {"search":title}
+    page = requests.get("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, params=params)
+    page_exist = True
+    if page.status_code:
+        result= page.json()
+        if len(result) == 0:
+            page_exist = False
 
-    page = requests.post("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, data=data)
-    print(page.status_code)
-    if page.status_code == 201:
-        print(page.content)
\ No newline at end of file
+    if page_exist == False:
+        page = requests.post("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, data=data)
+        if page.status_code == 201:
+            print(page.content)
\ No newline at end of file

From 605bd06e51f2efd33d90fa114310bda2ccbba290 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 28 Mar 2023 12:07:11 +0200
Subject: [PATCH 05/60] fix space

---
 insert_wordpress.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 595a3d6..b2c2787 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -84,7 +84,7 @@ if __name__ == '__main__':
     page = requests.get("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, params=params)
     page_exist = True
     if page.status_code:
-        result= page.json()
+        result = page.json()
         if len(result) == 0:
             page_exist = False
 

From 82ce3d1a2b9b099882ad86e856aaa79141b85e8b Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 28 Mar 2023 15:28:34 +0200
Subject: [PATCH 06/60] add author for article

---
 insert_wordpress.py | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index b2c2787..d59a35a 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -39,6 +39,7 @@ if __name__ == '__main__':
         articletitle = soup.find_all("h2", class_="articletitle")
         articlebody = soup.find_all("div", class_="articlebody")
         articledate = soup.find_all("span", class_="articledate")
+        articleacreator = soup.find_all("span", class_="articlecreator")
         dateheader = soup.find_all("div", class_="dateheader")
         itemfooter = soup.find_all("div", class_="itemfooter")
         a = itemfooter[0].find_all("a", {"rel": True})
@@ -68,6 +69,15 @@ if __name__ == '__main__':
       
 
         title = articletitle[0].text
+        author = articleacreator[0].text.lower()
+        author_exist = False
+        params = {"search":author}
+        page = requests.get("http://localhost:8080/wp-json/wp/v2/users", auth=basic, params=params)
+        if page.status_code == 200:
+            result = page.json()
+            print(result)
+            author_id = result[0]["id"]
+            author_exist = True
         body = articlebody[0].find_all("p")
         bodyhtml = "<p>"
         for i in body:
@@ -76,10 +86,12 @@ if __name__ == '__main__':
             else:
                 bodyhtml = bodyhtml + str(i).replace("<p>", "").replace("</p>", "").replace("<br>", "<br />") + "<br />"
         bodyhtml = bodyhtml + "</p>"
-        print(bodyhtml)
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
         data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
+        if author_exist == True:
+            data["author"] = author_id
+    
     params = {"search":title}
     page = requests.get("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, params=params)
     page_exist = True

From e3b9e92c23d69411b9aa2108761517393cde67e9 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 28 Mar 2023 15:37:48 +0200
Subject: [PATCH 07/60] fix add author

---
 insert_wordpress.py | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index d59a35a..5faee26 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -69,15 +69,7 @@ if __name__ == '__main__':
       
 
         title = articletitle[0].text
-        author = articleacreator[0].text.lower()
-        author_exist = False
-        params = {"search":author}
-        page = requests.get("http://localhost:8080/wp-json/wp/v2/users", auth=basic, params=params)
-        if page.status_code == 200:
-            result = page.json()
-            print(result)
-            author_id = result[0]["id"]
-            author_exist = True
+        author = articleacreator[0].text.lower()        
         body = articlebody[0].find_all("p")
         bodyhtml = "<p>"
         for i in body:
@@ -88,9 +80,14 @@ if __name__ == '__main__':
         bodyhtml = bodyhtml + "</p>"
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
+        
         data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
-        if author_exist == True:
-            data["author"] = author_id
+        params = {"search":author}
+        page = requests.get("http://localhost:8080/wp-json/wp/v2/users", auth=basic, params=params)
+        if page.status_code == 200:
+            result = page.json()
+            data["author"] = result[0]["id"]
+
     
     params = {"search":title}
     page = requests.get("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, params=params)

From dc0fd0c78137d466bbf67eda96ad01c5ca389ac9 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 28 Mar 2023 16:40:15 +0200
Subject: [PATCH 08/60] insert comment 75%

---
 insert_wordpress.py | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 5faee26..044292d 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -42,6 +42,19 @@ if __name__ == '__main__':
         articleacreator = soup.find_all("span", class_="articlecreator")
         dateheader = soup.find_all("div", class_="dateheader")
         itemfooter = soup.find_all("div", class_="itemfooter")
+        comment = soup.find_all("div", class_="comment_item")
+        comment_post = []
+        for i in comment:
+            comment_item = i.text.split("\n")
+            footer = i.find_all("div", class_="itemfooter")
+            comment_author = footer[0].text.split(",")[0].replace("Posté par ", "")
+            comment_date = footer[0].find_all("abbr")[0].get("title")
+            comment_content = "<p>"
+            for j in range(0, len(comment_item)-2):
+                if len(comment_item[j]) > 0:
+                    comment_content = comment_content + comment_item[j] + "<br />"
+            comment_content = comment_content + "</p>"
+            comment_post.append({"author": comment_author, "date": comment_date, "content": comment_content})
         a = itemfooter[0].find_all("a", {"rel": True})
         for i in a:
             rel = i.get("rel")
@@ -80,7 +93,7 @@ if __name__ == '__main__':
         bodyhtml = bodyhtml + "</p>"
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
-        
+
         data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
         params = {"search":author}
         page = requests.get("http://localhost:8080/wp-json/wp/v2/users", auth=basic, params=params)
@@ -100,4 +113,12 @@ if __name__ == '__main__':
     if page_exist == False:
         page = requests.post("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, data=data)
         if page.status_code == 201:
-            print(page.content)
\ No newline at end of file
+            result = page.json()
+            print("Article ajoute : {0}".format(result["title"]["raw"]))
+            print(comment_post)
+            for i in comment_post:
+                data = {"post": result["id"], "content": i["content"], "date": i["date"]}
+                page = requests.post("http://localhost:8080/wp-json/wp/v2/comments", auth=basic, data=data)
+                print(page.status_code)
+                if page.status_code == 201:
+                    print("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
\ No newline at end of file

From d96d38e50879c870ff3246be3c7a60cd0fbcac44 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 28 Mar 2023 16:43:56 +0200
Subject: [PATCH 09/60] add author name

---
 insert_wordpress.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 044292d..be12c65 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -117,7 +117,7 @@ if __name__ == '__main__':
             print("Article ajoute : {0}".format(result["title"]["raw"]))
             print(comment_post)
             for i in comment_post:
-                data = {"post": result["id"], "content": i["content"], "date": i["date"]}
+                data = {"post": result["id"], "content": i["content"], "date": i["date"], "author_name": i["author"]}
                 page = requests.post("http://localhost:8080/wp-json/wp/v2/comments", auth=basic, data=data)
                 print(page.status_code)
                 if page.status_code == 201:

From 19229bc65bd0d332ce447a623c5d35ceb040f7ae Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 28 Mar 2023 22:29:55 +0200
Subject: [PATCH 10/60] add .gitgnore + add function

---
 .gitignore          |  2 ++
 insert_wordpress.py | 33 ++++++++++++++++++++-------------
 2 files changed, 22 insertions(+), 13 deletions(-)
 create mode 100644 .gitignore

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..d9171fe
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+backup/
+web_scrap.log
diff --git a/insert_wordpress.py b/insert_wordpress.py
index be12c65..babec3a 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -5,19 +5,9 @@ from requests.auth import HTTPBasicAuth
 from getpass import getpass
 import requests, os, argparse, logging, re
 
-
-if __name__ == '__main__':
+def insertWordpress(file, basic):
     tags = []
     month = {"janvier":"01", "février": "02", "mars": "03", "avril":"04", "mai": "05", "juin": "06", "juillet": "07", "août": "08", "septembre": "09", "octobre": "10", "novembre": "11", "décembre": "12"}
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--user", help="wordpress user", required=True)
-    parser.add_argument("--file", help="HTML file", required=True)
-    args = parser.parse_args()
-    password = getpass()
-    if len(password) == 0:
-        print("No password error !!! ")
-        exit(1)
-    basic = HTTPBasicAuth(args.user, password)
 
     liste = ["categories", "tags"]
     elements = {}
@@ -32,7 +22,7 @@ if __name__ == '__main__':
             listelement[i] = []
 
     
-    with open(args.file, 'r') as f:
+    with open(file, 'r') as f:
         contents = f.read()
 
         soup = BeautifulSoup(contents, 'html.parser')
@@ -109,6 +99,8 @@ if __name__ == '__main__':
         result = page.json()
         if len(result) == 0:
             page_exist = False
+        else:
+            print("La page {0} existe deja".format(title))
 
     if page_exist == False:
         page = requests.post("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, data=data)
@@ -121,4 +113,19 @@ if __name__ == '__main__':
                 page = requests.post("http://localhost:8080/wp-json/wp/v2/comments", auth=basic, data=data)
                 print(page.status_code)
                 if page.status_code == 201:
-                    print("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
\ No newline at end of file
+                    print("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
+    
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--user", help="wordpress user", required=True)
+    parser.add_argument("--file", help="HTML file", required=True)
+    args = parser.parse_args()
+    password = getpass()
+    if len(password) == 0:
+        print("No password error !!! ")
+        exit(1)
+
+    basic = HTTPBasicAuth(args.user, password)
+    insertWordpress(args.file, basic)
\ No newline at end of file

From f250637912f8432ca9a578d66300efad32a153e3 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Wed, 29 Mar 2023 22:31:35 +0200
Subject: [PATCH 11/60] add class + wordpress

---
 insert_wordpress.py | 101 +++++++++++++++++++++++---------------------
 1 file changed, 54 insertions(+), 47 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index babec3a..c0c4d3d 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -5,27 +5,33 @@ from requests.auth import HTTPBasicAuth
 from getpass import getpass
 import requests, os, argparse, logging, re
 
-def insertWordpress(file, basic):
-    tags = []
-    month = {"janvier":"01", "février": "02", "mars": "03", "avril":"04", "mai": "05", "juin": "06", "juillet": "07", "août": "08", "septembre": "09", "octobre": "10", "novembre": "11", "décembre": "12"}
-
-    liste = ["categories", "tags"]
-    elements = {}
-    element = {}
-    listelement = {}
-
-    for i in liste:
-        page = requests.get("http://localhost:8080/wp-json/wp/v2/{0}".format(i))
-        if page.status_code == 200:
-            elements[i] = page.json()
-            element[i] = []
-            listelement[i] = []
-
+class WPimport:
     
-    with open(file, 'r') as f:
-        contents = f.read()
+    def __init__(self, basic, wordpress):
+        self.basic = basic
+        self.wordpress = wordpress
 
-        soup = BeautifulSoup(contents, 'html.parser')
+    def fromFile(self, file):
+        with open(file, 'r') as f:
+            contents = f.read()
+            self.insertWordpress(contents)
+
+    def insertWordpress(self, content):
+        tags = []
+        month = {"janvier":"01", "février": "02", "mars": "03", "avril":"04", "mai": "05", "juin": "06", "juillet": "07", "août": "08", "septembre": "09", "octobre": "10", "novembre": "11", "décembre": "12"}
+        liste = ["categories", "tags"]
+        elements = {}
+        element = {}
+        listelement = {}
+
+        for i in liste:
+            page = requests.get("http://{0}/wp-json/wp/v2/{1}".format(self.wordpress,i))
+            if page.status_code == 200:
+                elements[i] = page.json()
+                element[i] = []
+                listelement[i] = []
+
+        soup = BeautifulSoup(content, 'html.parser')
         articletitle = soup.find_all("h2", class_="articletitle")
         articlebody = soup.find_all("div", class_="articlebody")
         articledate = soup.find_all("span", class_="articledate")
@@ -63,14 +69,11 @@ def insertWordpress(file, basic):
                         array = listelement[i].append(k["id"])
                 if element_exist is False:
                     data = {"name": j}
-                    page = requests.post("http://localhost:8080/wp-json/wp/v2/{0}".format(i), auth=basic, data=data)
+                    page = requests.post("http://{0}/wp-json/wp/v2/{1}".format(self.wordpress, i), auth=self.basic, data=data)
                     if page.status_code == 201:
                         result = page.json()
                         listelement[i].append(result["id"])
 
-
-      
-
         title = articletitle[0].text
         author = articleacreator[0].text.lower()        
         body = articlebody[0].find_all("p")
@@ -86,34 +89,36 @@ def insertWordpress(file, basic):
 
         data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
         params = {"search":author}
-        page = requests.get("http://localhost:8080/wp-json/wp/v2/users", auth=basic, params=params)
+        page = requests.get("http://{0}/wp-json/wp/v2/users".format(self.wordpress), auth=self.basic, params=params)
         if page.status_code == 200:
             result = page.json()
             data["author"] = result[0]["id"]
 
-    
-    params = {"search":title}
-    page = requests.get("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, params=params)
-    page_exist = True
-    if page.status_code:
-        result = page.json()
-        if len(result) == 0:
-            page_exist = False
-        else:
-            print("La page {0} existe deja".format(title))
-
-    if page_exist == False:
-        page = requests.post("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, data=data)
-        if page.status_code == 201:
+        params = {"search":title}
+        page = requests.get("http://{0}/wp-json/wp/v2/posts".format(self.wordpress), auth=self.basic, params=params)
+        page_exist = True
+        if page.status_code:
             result = page.json()
-            print("Article ajoute : {0}".format(result["title"]["raw"]))
-            print(comment_post)
-            for i in comment_post:
-                data = {"post": result["id"], "content": i["content"], "date": i["date"], "author_name": i["author"]}
-                page = requests.post("http://localhost:8080/wp-json/wp/v2/comments", auth=basic, data=data)
-                print(page.status_code)
-                if page.status_code == 201:
-                    print("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
+            if len(result) == 0:
+                page_exist = False
+            else:
+                print("La page {0} existe deja".format(title))
+
+        if page_exist == False:
+            page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self.wordpress), auth=self.basic, data=data)
+            if page.status_code == 201:
+                result = page.json()
+                print("Article ajoute : {0}".format(result["title"]["raw"]))
+                print(comment_post)
+                for i in comment_post:
+                    data = {"post": result["id"], "content": i["content"], "date": i["date"], "author_name": i["author"]}
+                    page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self.wordpress), auth=self.basic, data=data)
+                    print(page.status_code)
+                    if page.status_code == 201:
+                        print("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
+
+
+
     
 
 
@@ -121,6 +126,7 @@ if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument("--user", help="wordpress user", required=True)
     parser.add_argument("--file", help="HTML file", required=True)
+    parser.add_argument("--wordpress", help="URL Wordpress", required=True)
     args = parser.parse_args()
     password = getpass()
     if len(password) == 0:
@@ -128,4 +134,5 @@ if __name__ == '__main__':
         exit(1)
 
     basic = HTTPBasicAuth(args.user, password)
-    insertWordpress(args.file, basic)
\ No newline at end of file
+    importWp = WPimport(basic)
+    importWp.fromFile(args.file)
\ No newline at end of file

From e1b0c0cba80ff0a2ec2fd1253d07a4ca99ee5c2a Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Wed, 29 Mar 2023 22:59:15 +0200
Subject: [PATCH 12/60] img wip

---
 insert_wordpress.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index c0c4d3d..216b483 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -39,6 +39,9 @@ class WPimport:
         dateheader = soup.find_all("div", class_="dateheader")
         itemfooter = soup.find_all("div", class_="itemfooter")
         comment = soup.find_all("div", class_="comment_item")
+        img = articlebody[0].find_all("img")
+        print(img)
+        exit(0)
         comment_post = []
         for i in comment:
             comment_item = i.text.split("\n")
@@ -134,5 +137,5 @@ if __name__ == '__main__':
         exit(1)
 
     basic = HTTPBasicAuth(args.user, password)
-    importWp = WPimport(basic)
+    importWp = WPimport(basic, args.wordpress)
     importWp.fromFile(args.file)
\ No newline at end of file

From 301f1e2d4b698dfa1e7d2fe492e5cc399c005c5f Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Thu, 30 Mar 2023 23:29:29 +0200
Subject: [PATCH 13/60] add img successful in media

---
 insert_wordpress.py | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 216b483..389cb7f 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -39,8 +39,33 @@ class WPimport:
         dateheader = soup.find_all("div", class_="dateheader")
         itemfooter = soup.find_all("div", class_="itemfooter")
         comment = soup.find_all("div", class_="comment_item")
-        img = articlebody[0].find_all("img")
-        print(img)
+        img_a = articlebody[0].find_all("a", {"target": "_blank"})
+        list_img = []
+        for i in img_a:
+            new_img = {}
+            img = i.find_all("img")
+            if len(img) > 0:
+                href_a = i.get("href")
+                href_img = img[0].get("src")
+                page_img = requests.get(href_img)
+                if page_img.status_code == 404:
+                    href_img = href_a
+                page = requests.get(href_img)
+                if page.status_code == 200:
+                    split_fileimg = href_img.split("/")
+                    img_name = split_fileimg[len(split_fileimg)-1]
+                    data = page.content
+                    img_type = "image/png"
+                    if img_name.split(".")[1]:
+                        img_type = "image/jpg"
+                    headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}                   
+                    r = requests.post("http://{0}/wp-json/wp/v2/media".format(self.wordpress), auth=self.basic, headers=headers, data=data)
+                    if r.status_code == 201:
+                        new_img["old_src"]=href_img
+                        new_img["id"]=r.json()["id"]
+                        new_img["new_src"]=r.json()["guid"]["rendered"]
+                        list_img.append(new_img)
+        print(list_img)     
         exit(0)
         comment_post = []
         for i in comment:

From c92f24e6af681dd3737d4e63c6b8a8754600b356 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Thu, 30 Mar 2023 23:50:25 +0200
Subject: [PATCH 14/60] check image exist in media

---
 insert_wordpress.py | 44 +++++++++++++++++++++++++++++++++-----------
 1 file changed, 33 insertions(+), 11 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 389cb7f..780844d 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -48,25 +48,37 @@ class WPimport:
                 href_a = i.get("href")
                 href_img = img[0].get("src")
                 page_img = requests.get(href_img)
+                img_break = False
                 if page_img.status_code == 404:
                     href_img = href_a
+                    img_break = True
                 page = requests.get(href_img)
                 if page.status_code == 200:
+            
                     split_fileimg = href_img.split("/")
                     img_name = split_fileimg[len(split_fileimg)-1]
-                    data = page.content
-                    img_type = "image/png"
-                    if img_name.split(".")[1]:
-                        img_type = "image/jpg"
-                    headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}                   
-                    r = requests.post("http://{0}/wp-json/wp/v2/media".format(self.wordpress), auth=self.basic, headers=headers, data=data)
-                    if r.status_code == 201:
+                    params = { "search": img_name}
+                    r = requests.get("http://{0}/wp-json/wp/v2/media".format(self.wordpress), auth=self.basic, params=params)
+                    if r.status_code == 200:
+                        res = r.json()
+                        if len(res) == 0:
+                            data = page.content
+                            img_type = "image/png"
+                            if img_name.split(".")[1]:
+                                img_type = "image/jpg"
+                            headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}                   
+                            r = requests.post("http://{0}/wp-json/wp/v2/media".format(self.wordpress), auth=self.basic, headers=headers, data=data)
+                            if r.status_code == 201:
+                                res = r.json()
+
                         new_img["old_src"]=href_img
-                        new_img["id"]=r.json()["id"]
-                        new_img["new_src"]=r.json()["guid"]["rendered"]
+                        new_img["old_href"]=href_a
+                        new_img["id"]=res["id"]
+                        new_img["new_src"]=res["guid"]["rendered"]
+                        new_img["break"]=img_break
                         list_img.append(new_img)
-        print(list_img)     
-        exit(0)
+                
+                            
         comment_post = []
         for i in comment:
             comment_item = i.text.split("\n")
@@ -112,6 +124,16 @@ class WPimport:
             else:
                 bodyhtml = bodyhtml + str(i).replace("<p>", "").replace("</p>", "").replace("<br>", "<br />") + "<br />"
         bodyhtml = bodyhtml + "</p>"
+        for i in list_img:
+            o = urlparse(i["new_src"])
+            if i == True:
+                print(i["old_href"])
+                bodyhtml = bodyhtml.replace(i["old_href"], o.path)
+            else:
+                print(i["old_src"])
+                bodyhtml = bodyhtml.replace(i["old_src"], o.path)
+        print(bodyhtml)
+        exit(0)
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
 

From 90881eb03714db8ab9c6972e0b91087beadc6762 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Fri, 31 Mar 2023 00:05:11 +0200
Subject: [PATCH 15/60] add media in body html

---
 insert_wordpress.py | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 780844d..a5a86eb 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -49,6 +49,8 @@ class WPimport:
                 href_img = img[0].get("src")
                 page_img = requests.get(href_img)
                 img_break = False
+                new_img["old_src"]=href_img
+                new_img["old_href"]=href_a
                 if page_img.status_code == 404:
                     href_img = href_a
                     img_break = True
@@ -70,11 +72,13 @@ class WPimport:
                             r = requests.post("http://{0}/wp-json/wp/v2/media".format(self.wordpress), auth=self.basic, headers=headers, data=data)
                             if r.status_code == 201:
                                 res = r.json()
-
-                        new_img["old_src"]=href_img
-                        new_img["old_href"]=href_a
-                        new_img["id"]=res["id"]
-                        new_img["new_src"]=res["guid"]["rendered"]
+                                id_res = res["id"]
+                                rendered = res["guid"]["rendered"]
+                        else:
+                            id_res = res[0]["id"]
+                            rendered = res[0]["guid"]["rendered"]
+                        new_img["id"]=id_res
+                        new_img["new_src"]=rendered
                         new_img["break"]=img_break
                         list_img.append(new_img)
                 
@@ -126,14 +130,8 @@ class WPimport:
         bodyhtml = bodyhtml + "</p>"
         for i in list_img:
             o = urlparse(i["new_src"])
-            if i == True:
-                print(i["old_href"])
-                bodyhtml = bodyhtml.replace(i["old_href"], o.path)
-            else:
-                print(i["old_src"])
-                bodyhtml = bodyhtml.replace(i["old_src"], o.path)
-        print(bodyhtml)
-        exit(0)
+            bodyhtml = bodyhtml.replace(i["old_href"], o.path)
+            bodyhtml = bodyhtml.replace(i["old_src"], o.path)
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
 

From 066d8cae52c771ceeee9d340b4dfedcde8437238 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Fri, 31 Mar 2023 00:06:47 +0200
Subject: [PATCH 16/60] remove print

---
 insert_wordpress.py | 2 --
 1 file changed, 2 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index a5a86eb..9e40faa 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -157,11 +157,9 @@ class WPimport:
             if page.status_code == 201:
                 result = page.json()
                 print("Article ajoute : {0}".format(result["title"]["raw"]))
-                print(comment_post)
                 for i in comment_post:
                     data = {"post": result["id"], "content": i["content"], "date": i["date"], "author_name": i["author"]}
                     page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self.wordpress), auth=self.basic, data=data)
-                    print(page.status_code)
                     if page.status_code == 201:
                         print("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
 

From e0b4895b62072edd65da8aa560e9d59cca55c342 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Fri, 31 Mar 2023 00:14:38 +0200
Subject: [PATCH 17/60] association image article

---
 insert_wordpress.py | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 9e40faa..0f1b2fa 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -162,6 +162,12 @@ class WPimport:
                     page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self.wordpress), auth=self.basic, data=data)
                     if page.status_code == 201:
                         print("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
+                for i in list_img:
+                    data = {"post": result["id"]}
+                    r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self.wordpress, i["id"]), auth=self.basic, data=data)
+                    if r.status_code == 200:
+                        print("Association d'une image à l'article {0}".format(result["title"]["raw"]))
+
 
 
 

From bcb3abce016e4f038c499ccd3170cc792e0135f1 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 1 Apr 2023 00:11:33 +0200
Subject: [PATCH 18/60] fix variable

---
 insert_wordpress.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 0f1b2fa..854c412 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -110,7 +110,7 @@ class WPimport:
                 for k in elements[i]:
                     if k["name"] == j:
                         element_exist = True
-                        array = listelement[i].append(k["id"])
+                        listelement[i].append(k["id"])
                 if element_exist is False:
                     data = {"name": j}
                     page = requests.post("http://{0}/wp-json/wp/v2/{1}".format(self.wordpress, i), auth=self.basic, data=data)
@@ -145,7 +145,7 @@ class WPimport:
         params = {"search":title}
         page = requests.get("http://{0}/wp-json/wp/v2/posts".format(self.wordpress), auth=self.basic, params=params)
         page_exist = True
-        if page.status_code:
+        if page.status_code == 200:
             result = page.json()
             if len(result) == 0:
                 page_exist = False

From faa22f1438532d65e104cf9c471b924299f2264e Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 1 Apr 2023 00:18:56 +0200
Subject: [PATCH 19/60] update post

---
 insert_wordpress.py | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 854c412..e327729 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -150,7 +150,14 @@ class WPimport:
             if len(result) == 0:
                 page_exist = False
             else:
-                print("La page {0} existe deja".format(title))
+                print("La page {0} existe deja et mis à jour".format(title))
+                post_id = result[0]["id"]
+                page = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self.wordpress, post_id), auth=self.basic, data=data)
+                if page.status_code == 200:
+                    result = page.json()
+                    print("Article mis à jour : {0}".format(result["title"]["raw"]))
+
+
 
         if page_exist == False:
             page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self.wordpress), auth=self.basic, data=data)

From 4054f41e9bf1af96ca6b2a8377ba05d1d0738d8d Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 1 Apr 2023 18:32:17 +0200
Subject: [PATCH 20/60] add json dumps for post

---
 insert_wordpress.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index e327729..662bcda 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -3,7 +3,7 @@ from bs4 import BeautifulSoup
 from urllib.parse import urlparse
 from requests.auth import HTTPBasicAuth
 from getpass import getpass
-import requests, os, argparse, logging, re
+import requests, os, argparse, logging, re, json
 
 class WPimport:
     
@@ -134,7 +134,6 @@ class WPimport:
             bodyhtml = bodyhtml.replace(i["old_src"], o.path)
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
-
         data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
         params = {"search":author}
         page = requests.get("http://{0}/wp-json/wp/v2/users".format(self.wordpress), auth=self.basic, params=params)
@@ -145,6 +144,7 @@ class WPimport:
         params = {"search":title}
         page = requests.get("http://{0}/wp-json/wp/v2/posts".format(self.wordpress), auth=self.basic, params=params)
         page_exist = True
+        headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
         if page.status_code == 200:
             result = page.json()
             if len(result) == 0:
@@ -152,7 +152,7 @@ class WPimport:
             else:
                 print("La page {0} existe deja et mis à jour".format(title))
                 post_id = result[0]["id"]
-                page = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self.wordpress, post_id), auth=self.basic, data=data)
+                page = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self.wordpress, post_id), auth=self.basic, headers=headers, data=json.dumps(data))
                 if page.status_code == 200:
                     result = page.json()
                     print("Article mis à jour : {0}".format(result["title"]["raw"]))
@@ -160,7 +160,7 @@ class WPimport:
 
 
         if page_exist == False:
-            page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self.wordpress), auth=self.basic, data=data)
+            page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self.wordpress), auth=self.basic, headers=headers, data=json.dumps(data))
             if page.status_code == 201:
                 result = page.json()
                 print("Article ajoute : {0}".format(result["title"]["raw"]))

From f07f8c040f0c0d043a03b2bbd127e612787bddd6 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 2 Apr 2023 13:06:10 +0200
Subject: [PATCH 21/60] add private method for association id

---
 insert_wordpress.py | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 662bcda..ad30fd8 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -15,6 +15,13 @@ class WPimport:
         with open(file, 'r') as f:
             contents = f.read()
             self.insertWordpress(contents)
+    
+    def _linkImgPost(self, title, list_img, post_id):
+        for i in list_img:
+            data = {"post": post_id}
+            r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self.wordpress, i["id"]), auth=self.basic, data=data)
+            if r.status_code == 200:
+                print("Association d'une image à l'article {0}".format(title))
 
     def insertWordpress(self, content):
         tags = []
@@ -156,6 +163,7 @@ class WPimport:
                 if page.status_code == 200:
                     result = page.json()
                     print("Article mis à jour : {0}".format(result["title"]["raw"]))
+                    self._linkImgPost(result["title"]["raw"], list_img, result["id"])
 
 
 
@@ -169,12 +177,7 @@ class WPimport:
                     page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self.wordpress), auth=self.basic, data=data)
                     if page.status_code == 201:
                         print("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
-                for i in list_img:
-                    data = {"post": result["id"]}
-                    r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self.wordpress, i["id"]), auth=self.basic, data=data)
-                    if r.status_code == 200:
-                        print("Association d'une image à l'article {0}".format(result["title"]["raw"]))
-
+                self._linkImgPost(result["title"]["raw"], list_img, result["id"])
 
 
 

From cc33ab34df6256a4ca88c45e18351188a5d953ed Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 2 Apr 2023 13:14:52 +0200
Subject: [PATCH 22/60] private variable

---
 insert_wordpress.py | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index ad30fd8..897a1d4 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -8,22 +8,22 @@ import requests, os, argparse, logging, re, json
 class WPimport:
     
     def __init__(self, basic, wordpress):
-        self.basic = basic
-        self.wordpress = wordpress
+        self._basic = basic
+        self._wordpress = wordpress
 
     def fromFile(self, file):
         with open(file, 'r') as f:
             contents = f.read()
-            self.insertWordpress(contents)
+            self._insertWordpress(contents)
     
     def _linkImgPost(self, title, list_img, post_id):
         for i in list_img:
             data = {"post": post_id}
-            r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self.wordpress, i["id"]), auth=self.basic, data=data)
+            r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, i["id"]), auth=self._basic, data=data)
             if r.status_code == 200:
                 print("Association d'une image à l'article {0}".format(title))
 
-    def insertWordpress(self, content):
+    def _insertWordpress(self, content):
         tags = []
         month = {"janvier":"01", "février": "02", "mars": "03", "avril":"04", "mai": "05", "juin": "06", "juillet": "07", "août": "08", "septembre": "09", "octobre": "10", "novembre": "11", "décembre": "12"}
         liste = ["categories", "tags"]
@@ -32,7 +32,7 @@ class WPimport:
         listelement = {}
 
         for i in liste:
-            page = requests.get("http://{0}/wp-json/wp/v2/{1}".format(self.wordpress,i))
+            page = requests.get("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress,i))
             if page.status_code == 200:
                 elements[i] = page.json()
                 element[i] = []
@@ -67,7 +67,7 @@ class WPimport:
                     split_fileimg = href_img.split("/")
                     img_name = split_fileimg[len(split_fileimg)-1]
                     params = { "search": img_name}
-                    r = requests.get("http://{0}/wp-json/wp/v2/media".format(self.wordpress), auth=self.basic, params=params)
+                    r = requests.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
                     if r.status_code == 200:
                         res = r.json()
                         if len(res) == 0:
@@ -76,7 +76,7 @@ class WPimport:
                             if img_name.split(".")[1]:
                                 img_type = "image/jpg"
                             headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}                   
-                            r = requests.post("http://{0}/wp-json/wp/v2/media".format(self.wordpress), auth=self.basic, headers=headers, data=data)
+                            r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
                             if r.status_code == 201:
                                 res = r.json()
                                 id_res = res["id"]
@@ -120,7 +120,7 @@ class WPimport:
                         listelement[i].append(k["id"])
                 if element_exist is False:
                     data = {"name": j}
-                    page = requests.post("http://{0}/wp-json/wp/v2/{1}".format(self.wordpress, i), auth=self.basic, data=data)
+                    page = requests.post("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i), auth=self._basic, data=data)
                     if page.status_code == 201:
                         result = page.json()
                         listelement[i].append(result["id"])
@@ -143,13 +143,13 @@ class WPimport:
         time = dateheader[0].text.split(" ")
         data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
         params = {"search":author}
-        page = requests.get("http://{0}/wp-json/wp/v2/users".format(self.wordpress), auth=self.basic, params=params)
+        page = requests.get("http://{0}/wp-json/wp/v2/users".format(self._wordpress), auth=self._basic, params=params)
         if page.status_code == 200:
             result = page.json()
             data["author"] = result[0]["id"]
 
         params = {"search":title}
-        page = requests.get("http://{0}/wp-json/wp/v2/posts".format(self.wordpress), auth=self.basic, params=params)
+        page = requests.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params)
         page_exist = True
         headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
         if page.status_code == 200:
@@ -159,7 +159,7 @@ class WPimport:
             else:
                 print("La page {0} existe deja et mis à jour".format(title))
                 post_id = result[0]["id"]
-                page = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self.wordpress, post_id), auth=self.basic, headers=headers, data=json.dumps(data))
+                page = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, data=json.dumps(data))
                 if page.status_code == 200:
                     result = page.json()
                     print("Article mis à jour : {0}".format(result["title"]["raw"]))
@@ -168,13 +168,13 @@ class WPimport:
 
 
         if page_exist == False:
-            page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self.wordpress), auth=self.basic, headers=headers, data=json.dumps(data))
+            page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
             if page.status_code == 201:
                 result = page.json()
                 print("Article ajoute : {0}".format(result["title"]["raw"]))
                 for i in comment_post:
                     data = {"post": result["id"], "content": i["content"], "date": i["date"], "author_name": i["author"]}
-                    page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self.wordpress), auth=self.basic, data=data)
+                    page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, data=data)
                     if page.status_code == 201:
                         print("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
                 self._linkImgPost(result["title"]["raw"], list_img, result["id"])

From 42b7e7e408b73d49e8bd6c19bd75eabe2ee498ed Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 2 Apr 2023 16:56:07 +0200
Subject: [PATCH 23/60] get featured image for post wip

---
 insert_wordpress.py | 42 +++++++++++++++++++++++++++++++++++++-----
 1 file changed, 37 insertions(+), 5 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 897a1d4..fb61e6b 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -6,24 +6,57 @@ from getpass import getpass
 import requests, os, argparse, logging, re, json
 
 class WPimport:
-    
+    # Constructor
     def __init__(self, basic, wordpress):
         self._basic = basic
         self._wordpress = wordpress
 
+    # Public method
+
     def fromFile(self, file):
         with open(file, 'r') as f:
-            contents = f.read()
-            self._insertWordpress(contents)
+            content = f.read()
+            soup = BeautifulSoup(content, 'html.parser')
+            articlebody = soup.find_all("div", class_="articlebody")
+            if len(articlebody) > 0:
+                self._addOrUpdatePost(soup)
+            else:
+                self._addOrUpdateFeaturedMedia(soup)
     
+    # Private method
+
+
+    ## Get or update featured image
+
+    def _addOrUpdateFeaturedMedia(self, soup):
+        item_div = soup.find_all("div", {"data-edittype": "post"})
+        for i in item_div:
+            h2 = i.find_all("h2")[0].text
+            params = {"search":h2, "type":"post"}
+            page = requests.get("http://{0}/wp-json/wp/v2/search".format(self._wordpress), auth=self._basic, params=params)
+            if page.status_code == 200:
+                result = page.json()
+                if len(result) > 0:
+                    if h2 == result[0]["title"]:
+                        img = i.find_all("img")
+                        if len(img) > 0:
+                            img_src = img[0].get("src")
+                            print(img_src)
+
+                
+    ## Association image to post
+
     def _linkImgPost(self, title, list_img, post_id):
         for i in list_img:
             data = {"post": post_id}
             r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, i["id"]), auth=self._basic, data=data)
             if r.status_code == 200:
                 print("Association d'une image à l'article {0}".format(title))
+            
+    
+    ## Add or Update post 
 
-    def _insertWordpress(self, content):
+    def _addOrUpdatePost(self, soup):
         tags = []
         month = {"janvier":"01", "février": "02", "mars": "03", "avril":"04", "mai": "05", "juin": "06", "juillet": "07", "août": "08", "septembre": "09", "octobre": "10", "novembre": "11", "décembre": "12"}
         liste = ["categories", "tags"]
@@ -38,7 +71,6 @@ class WPimport:
                 element[i] = []
                 listelement[i] = []
 
-        soup = BeautifulSoup(content, 'html.parser')
         articletitle = soup.find_all("h2", class_="articletitle")
         articlebody = soup.find_all("div", class_="articlebody")
         articledate = soup.find_all("span", class_="articledate")

From cb64dd47ab554ac1fe3aa2596a7f2105c82e9620 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 2 Apr 2023 17:34:55 +0200
Subject: [PATCH 24/60] create private method for add or update media

---
 insert_wordpress.py | 64 ++++++++++++++++++++++++---------------------
 1 file changed, 34 insertions(+), 30 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index fb61e6b..43597dc 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -52,7 +52,32 @@ class WPimport:
             r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, i["id"]), auth=self._basic, data=data)
             if r.status_code == 200:
                 print("Association d'une image à l'article {0}".format(title))
-            
+    
+    ## Add or update img 
+
+    def _addOrUpdateMedia(self, href_img):
+        media = {"id":"", "rendered":""}
+        split_fileimg = href_img.split("/")
+        img_name = split_fileimg[len(split_fileimg)-1]
+        params = { "search": img_name}
+        r = requests.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
+        if r.status_code == 200:
+            res = r.json()
+            if len(res) == 0:
+                data = page.content
+                img_type = "image/png"
+                if img_name.split(".")[1]:
+                    img_type = "image/jpg"
+                headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}                   
+                r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
+                if r.status_code == 201:
+                    res = r.json()
+                    media["id"] = res["id"]
+                    media["rendered"] = res["guid"]["rendered"]
+            else:
+                media["id"] = res[0]["id"]
+                media["rendered"] = res[0]["guid"]["rendered"]
+        return media
     
     ## Add or Update post 
 
@@ -86,42 +111,21 @@ class WPimport:
             if len(img) > 0:
                 href_a = i.get("href")
                 href_img = img[0].get("src")
-                page_img = requests.get(href_img)
-                img_break = False
                 new_img["old_src"]=href_img
                 new_img["old_href"]=href_a
+                page_img = requests.get(href_img)
+                img_break = False
                 if page_img.status_code == 404:
                     href_img = href_a
                     img_break = True
-                page = requests.get(href_img)
+                    page = requests.get(href_a)
                 if page.status_code == 200:
-            
-                    split_fileimg = href_img.split("/")
-                    img_name = split_fileimg[len(split_fileimg)-1]
-                    params = { "search": img_name}
-                    r = requests.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
-                    if r.status_code == 200:
-                        res = r.json()
-                        if len(res) == 0:
-                            data = page.content
-                            img_type = "image/png"
-                            if img_name.split(".")[1]:
-                                img_type = "image/jpg"
-                            headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}                   
-                            r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
-                            if r.status_code == 201:
-                                res = r.json()
-                                id_res = res["id"]
-                                rendered = res["guid"]["rendered"]
-                        else:
-                            id_res = res[0]["id"]
-                            rendered = res[0]["guid"]["rendered"]
-                        new_img["id"]=id_res
-                        new_img["new_src"]=rendered
-                        new_img["break"]=img_break
-                        list_img.append(new_img)
+                    media=self._addOrUpdateMedia(href_img)
+                    new_img["id"]=media["id"]
+                    new_img["new_src"]=media["rendered"]
+                    new_img["break"]=img_break
+                    list_img.append(new_img)
                 
-                            
         comment_post = []
         for i in comment:
             comment_item = i.text.split("\n")

From ec4135c5d024f72fdacee10bcf321b5db13d2fae Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 2 Apr 2023 17:36:17 +0200
Subject: [PATCH 25/60] fix condition type file

---
 insert_wordpress.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 43597dc..32f3439 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -66,7 +66,7 @@ class WPimport:
             if len(res) == 0:
                 data = page.content
                 img_type = "image/png"
-                if img_name.split(".")[1]:
+                if img_name.split(".")[1] == "jpg" or img_name.split(".")[1] == "jpeg":
                     img_type = "image/jpg"
                 headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}                   
                 r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)

From 1e162662e65fb7adf500f6763b451b3869f8e16c Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 2 Apr 2023 17:51:54 +0200
Subject: [PATCH 26/60] add featured media

---
 insert_wordpress.py | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 32f3439..a9e71d9 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -41,7 +41,13 @@ class WPimport:
                         img = i.find_all("img")
                         if len(img) > 0:
                             img_src = img[0].get("src")
-                            print(img_src)
+                            page = requests.get(img_src)
+                            if page.status_code == 200:
+                                media=self._addOrUpdateMedia(img_src, page)
+                                data = {"featured_media": media["id"]}
+                                r = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, result[0]["id"]), auth=self._basic, data=json.dumps(data))
+                                if r.status_code == 200:
+                                    print("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
 
                 
     ## Association image to post
@@ -55,7 +61,7 @@ class WPimport:
     
     ## Add or update img 
 
-    def _addOrUpdateMedia(self, href_img):
+    def _addOrUpdateMedia(self, href_img, page):
         media = {"id":"", "rendered":""}
         split_fileimg = href_img.split("/")
         img_name = split_fileimg[len(split_fileimg)-1]
@@ -120,7 +126,7 @@ class WPimport:
                     img_break = True
                     page = requests.get(href_a)
                 if page.status_code == 200:
-                    media=self._addOrUpdateMedia(href_img)
+                    media=self._addOrUpdateMedia(href_img, page)
                     new_img["id"]=media["id"]
                     new_img["new_src"]=media["rendered"]
                     new_img["break"]=img_break

From f77274f00e51073d5fbba2dd3f096ffcfe58d5ff Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 2 Apr 2023 17:56:22 +0200
Subject: [PATCH 27/60] add headers json

---
 insert_wordpress.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index a9e71d9..7db1fd1 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -44,8 +44,9 @@ class WPimport:
                             page = requests.get(img_src)
                             if page.status_code == 200:
                                 media=self._addOrUpdateMedia(img_src, page)
+                                headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
                                 data = {"featured_media": media["id"]}
-                                r = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, result[0]["id"]), auth=self._basic, data=json.dumps(data))
+                                r = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, result[0]["id"]), auth=self._basic, headers=headers, data=json.dumps(data))
                                 if r.status_code == 200:
                                     print("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
 

From c9b1264153abf4b6ec46c554eae039abec07b452 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 2 Apr 2023 18:01:57 +0200
Subject: [PATCH 28/60] remove private method for featured media

---
 insert_wordpress.py | 30 +-----------------------------
 1 file changed, 1 insertion(+), 29 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 7db1fd1..fff8279 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -20,36 +20,8 @@ class WPimport:
             articlebody = soup.find_all("div", class_="articlebody")
             if len(articlebody) > 0:
                 self._addOrUpdatePost(soup)
-            else:
-                self._addOrUpdateFeaturedMedia(soup)
     
     # Private method
-
-
-    ## Get or update featured image
-
-    def _addOrUpdateFeaturedMedia(self, soup):
-        item_div = soup.find_all("div", {"data-edittype": "post"})
-        for i in item_div:
-            h2 = i.find_all("h2")[0].text
-            params = {"search":h2, "type":"post"}
-            page = requests.get("http://{0}/wp-json/wp/v2/search".format(self._wordpress), auth=self._basic, params=params)
-            if page.status_code == 200:
-                result = page.json()
-                if len(result) > 0:
-                    if h2 == result[0]["title"]:
-                        img = i.find_all("img")
-                        if len(img) > 0:
-                            img_src = img[0].get("src")
-                            page = requests.get(img_src)
-                            if page.status_code == 200:
-                                media=self._addOrUpdateMedia(img_src, page)
-                                headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
-                                data = {"featured_media": media["id"]}
-                                r = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, result[0]["id"]), auth=self._basic, headers=headers, data=json.dumps(data))
-                                if r.status_code == 200:
-                                    print("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
-
                 
     ## Association image to post
 
@@ -184,7 +156,7 @@ class WPimport:
             bodyhtml = bodyhtml.replace(i["old_src"], o.path)
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
-        data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
+        data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"], "featured_media":list_img[0]["id"]}
         params = {"search":author}
         page = requests.get("http://{0}/wp-json/wp/v2/users".format(self._wordpress), auth=self._basic, params=params)
         if page.status_code == 200:

From 501876dac23893a7823b70071e2776d255b9ced8 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 3 Apr 2023 23:45:48 +0200
Subject: [PATCH 29/60] add or update featured media

---
 insert_wordpress.py | 54 +++++++++++++++++++++++++++++++++++++++------
 1 file changed, 47 insertions(+), 7 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index fff8279..06185fe 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -20,8 +20,46 @@ class WPimport:
             articlebody = soup.find_all("div", class_="articlebody")
             if len(articlebody) > 0:
                 self._addOrUpdatePost(soup)
+            else:
+                self._addOrUpdateFeaturedMedia(soup)
     
     # Private method
+
+    ## Add or update featured media
+
+
+       ## Get or update featured image
+
+    def _addOrUpdateFeaturedMedia(self, soup):
+        item_div = soup.find_all("div", {"data-edittype": "post"})
+        for i in item_div:
+            h2 = i.find_all("h2")[0].text
+            params = {"search":h2, "type":"post"}
+            page = requests.get("http://{0}/wp-json/wp/v2/search".format(self._wordpress), auth=self._basic, params=params)
+            if page.status_code == 200:
+                result = page.json()
+                if len(result) > 0:
+                    if h2 == result[0]["title"]:
+                        img = i.find_all("img")
+                        if len(img) > 0:
+                            img_src = img[0].get("src")
+                            page = requests.get(img_src)
+                            if page.status_code == 200:
+                                name_img = img_src.replace("_q", "")
+                                name_img = name_img.split("/")[len(name_img.split("/"))-1]
+                                params = {"search": name_img}
+                                page = requests.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
+                                if page.status_code == 200:
+                                    res = page.json()
+                                    if len(res) > 0:
+                                        id_media = res[0]["id"]
+                                        headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
+                                        data = {"featured_media": id_media}
+                                        r = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, result[0]["id"]), auth=self._basic, headers=headers, data=json.dumps(data))
+                                        if r.status_code == 200:
+                                            print("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
+                                    else:
+                                        print("Aucun media trouvé")
                 
     ## Association image to post
 
@@ -93,17 +131,19 @@ class WPimport:
                 new_img["old_src"]=href_img
                 new_img["old_href"]=href_a
                 page_img = requests.get(href_img)
-                img_break = False
                 if page_img.status_code == 404:
                     href_img = href_a
-                    img_break = True
-                    page = requests.get(href_a)
-                if page.status_code == 200:
-                    media=self._addOrUpdateMedia(href_img, page)
+                    page_img = requests.get(href_a)
+                if page_img.status_code == 200:
+                    media=self._addOrUpdateMedia(href_img, page_img)
                     new_img["id"]=media["id"]
                     new_img["new_src"]=media["rendered"]
-                    new_img["break"]=img_break
                     list_img.append(new_img)
+                    if href_img != href_a:
+                        media=self._addOrUpdateMedia(href_a, page_img)
+                        new_img["id"]=media["id"]
+                        new_img["new_src"]=media["rendered"]
+                        list_img.append(new_img)
                 
         comment_post = []
         for i in comment:
@@ -156,7 +196,7 @@ class WPimport:
             bodyhtml = bodyhtml.replace(i["old_src"], o.path)
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
-        data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"], "featured_media":list_img[0]["id"]}
+        data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
         params = {"search":author}
         page = requests.get("http://{0}/wp-json/wp/v2/users".format(self._wordpress), auth=self._basic, params=params)
         if page.status_code == 200:

From 404ad5dd6cd3ebd5ce5ca7aa27385833b8885f81 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 4 Apr 2023 00:00:28 +0200
Subject: [PATCH 30/60] update image not fix

---
 insert_wordpress.py | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 06185fe..ba799d3 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -80,20 +80,20 @@ class WPimport:
         r = requests.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
         if r.status_code == 200:
             res = r.json()
-            if len(res) == 0:
-                data = page.content
-                img_type = "image/png"
-                if img_name.split(".")[1] == "jpg" or img_name.split(".")[1] == "jpeg":
-                    img_type = "image/jpg"
-                headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}                   
-                r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
-                if r.status_code == 201:
-                    res = r.json()
-                    media["id"] = res["id"]
-                    media["rendered"] = res["guid"]["rendered"]
-            else:
-                media["id"] = res[0]["id"]
-                media["rendered"] = res[0]["guid"]["rendered"]
+            url = "http://{0}/wp-json/wp/v2/media".format(self._wordpress)
+            if len(res) > 0:
+                url = "http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, res[0]["id"])
+            print(url)
+            data = page.content
+            img_type = "image/png"
+            if img_name.split(".")[1] == "jpg" or img_name.split(".")[1] == "jpeg":
+                img_type = "image/jpg"
+            headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
+            r = requests.post(url, auth=self._basic, headers=headers, data=data)
+            if r.status_code == 201 or r.status_code == 200:
+                res = r.json()
+                media["id"] = res["id"]
+                media["rendered"] = res["guid"]["rendered"]
         return media
     
     ## Add or Update post 

From 665f1474f27b15e19d35607f7071f68d45d702e4 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 4 Apr 2023 22:07:36 +0200
Subject: [PATCH 31/60] delete and replace image

---
 insert_wordpress.py | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index ba799d3..fd878cd 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -59,7 +59,7 @@ class WPimport:
                                         if r.status_code == 200:
                                             print("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
                                     else:
-                                        print("Aucun media trouvé")
+                                        print("Aucun media trouvé pour {0}".format(h2))
                 
     ## Association image to post
 
@@ -80,17 +80,18 @@ class WPimport:
         r = requests.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
         if r.status_code == 200:
             res = r.json()
-            url = "http://{0}/wp-json/wp/v2/media".format(self._wordpress)
             if len(res) > 0:
-                url = "http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, res[0]["id"])
-            print(url)
+                params = {"force":1}
+                r = requests.delete("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, res[0]["id"]), auth=self._basic, params=params)
+                if r.status_code == 200:
+                    print("Image supprimé {0}".format(img_name))
             data = page.content
             img_type = "image/png"
             if img_name.split(".")[1] == "jpg" or img_name.split(".")[1] == "jpeg":
                 img_type = "image/jpg"
             headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
-            r = requests.post(url, auth=self._basic, headers=headers, data=data)
-            if r.status_code == 201 or r.status_code == 200:
+            r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
+            if r.status_code == 201:
                 res = r.json()
                 media["id"] = res["id"]
                 media["rendered"] = res["guid"]["rendered"]

From ba511bc6c4251b7987712481a4ad98a2737d31e4 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 4 Apr 2023 22:14:10 +0200
Subject: [PATCH 32/60] Ajout print image ajoute

---
 insert_wordpress.py | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index fd878cd..1f6812c 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -13,23 +13,21 @@ class WPimport:
 
     # Public method
 
-    def fromFile(self, file):
-        with open(file, 'r') as f:
-            content = f.read()
-            soup = BeautifulSoup(content, 'html.parser')
-            articlebody = soup.find_all("div", class_="articlebody")
-            if len(articlebody) > 0:
-                self._addOrUpdatePost(soup)
-            else:
-                self._addOrUpdateFeaturedMedia(soup)
+    def fromFile(self, files):
+        for file in files.split(","):
+            with open(file, 'r') as f:
+                content = f.read()
+                soup = BeautifulSoup(content, 'html.parser')
+                articlebody = soup.find_all("div", class_="articlebody")
+                if len(articlebody) > 0:
+                    self._addOrUpdatePost(soup)
+                else:
+                    self._addOrUpdateFeaturedMedia(soup)
     
     # Private method
 
     ## Add or update featured media
 
-
-       ## Get or update featured image
-
     def _addOrUpdateFeaturedMedia(self, soup):
         item_div = soup.find_all("div", {"data-edittype": "post"})
         for i in item_div:
@@ -92,6 +90,7 @@ class WPimport:
             headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
             r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
             if r.status_code == 201:
+                print("Ajout d'image {0}".format(img_name))
                 res = r.json()
                 media["id"] = res["id"]
                 media["rendered"] = res["guid"]["rendered"]

From 5768b37cd1fa5ad21ae26c2d3c0c4e0d354692a0 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Thu, 6 Apr 2023 20:59:11 +0200
Subject: [PATCH 33/60] ajout de verification de existence fichier

---
 insert_wordpress.py | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 1f6812c..2c3828e 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -15,14 +15,15 @@ class WPimport:
 
     def fromFile(self, files):
         for file in files.split(","):
-            with open(file, 'r') as f:
-                content = f.read()
-                soup = BeautifulSoup(content, 'html.parser')
-                articlebody = soup.find_all("div", class_="articlebody")
-                if len(articlebody) > 0:
-                    self._addOrUpdatePost(soup)
-                else:
-                    self._addOrUpdateFeaturedMedia(soup)
+            if os.path.exists(file):
+                with open(file, 'r') as f:
+                    content = f.read()
+                    soup = BeautifulSoup(content, 'html.parser')
+                    articlebody = soup.find_all("div", class_="articlebody")
+                    if len(articlebody) > 0:
+                        self._addOrUpdatePost(soup)
+                    else:
+                        self._addOrUpdateFeaturedMedia(soup)
     
     # Private method
 

From 1f7e442d04c1e8092a708e2cc12e4ad1606d5efb Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Thu, 6 Apr 2023 21:53:56 +0200
Subject: [PATCH 34/60] wip directory

---
 insert_wordpress.py | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 2c3828e..c91964b 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -13,6 +13,13 @@ class WPimport:
 
     # Public method
 
+    def fromDirectory(self, directory):
+        directory = "{0}/archives".format(directory)
+        for item in os.listdir(directory):
+            subdirectory = self._checkDirectory(item)
+            print(subdirectory)
+
+
     def fromFile(self, files):
         for file in files.split(","):
             if os.path.exists(file):
@@ -27,6 +34,11 @@ class WPimport:
     
     # Private method
 
+    def _checkDirectory(self, item):
+        if os.path.isdir(item):
+            self._checkDirectory(item)
+        return item
+
     ## Add or update featured media
 
     def _addOrUpdateFeaturedMedia(self, soup):
@@ -243,7 +255,8 @@ class WPimport:
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument("--user", help="wordpress user", required=True)
-    parser.add_argument("--file", help="HTML file", required=True)
+    parser.add_argument("--file", help="HTML file", default="")
+    parser.add_argument("--directory", help="HTML directory", default="")
     parser.add_argument("--wordpress", help="URL Wordpress", required=True)
     args = parser.parse_args()
     password = getpass()
@@ -253,4 +266,8 @@ if __name__ == '__main__':
 
     basic = HTTPBasicAuth(args.user, password)
     importWp = WPimport(basic, args.wordpress)
-    importWp.fromFile(args.file)
\ No newline at end of file
+    if len(args.file) > 0:
+        importWp.fromFile(args.file)
+        exit(0)
+    if len(args.directory) > 0:
+        importWp.fromDirectory(args.directory)
\ No newline at end of file

From 34115a3a7d89e9404c0c465a42b539ffe445b853 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Fri, 7 Apr 2023 22:38:34 +0200
Subject: [PATCH 35/60] recursive functions for directories

---
 insert_wordpress.py | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index c91964b..db2e8a0 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -15,9 +15,8 @@ class WPimport:
 
     def fromDirectory(self, directory):
         directory = "{0}/archives".format(directory)
-        for item in os.listdir(directory):
-            subdirectory = self._checkDirectory(item)
-            print(subdirectory)
+        subdirectory = self._checkDirectory([], "{0}".format(directory))
+        print(subdirectory)
 
 
     def fromFile(self, files):
@@ -34,10 +33,13 @@ class WPimport:
     
     # Private method
 
-    def _checkDirectory(self, item):
-        if os.path.isdir(item):
-            self._checkDirectory(item)
-        return item
+    def _checkDirectory(self, subdirectory, item):
+        sub = subdirectory
+        for i in os.listdir(item):
+            if os.path.isdir("{0}/{1}".format(item, i)):
+                sub.append("{0}/{1}".format(item, i))
+                subdirectory = self._checkDirectory(sub, "{0}/{1}".format(item, i))
+        return subdirectory
 
     ## Add or update featured media
 

From 9ab33c169eecfe246d3b2616df8f6b74bb852919 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Fri, 7 Apr 2023 22:55:27 +0200
Subject: [PATCH 36/60] add directory parameter

---
 insert_wordpress.py | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index db2e8a0..2c29e80 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -15,13 +15,15 @@ class WPimport:
 
     def fromDirectory(self, directory):
         directory = "{0}/archives".format(directory)
-        subdirectory = self._checkDirectory([], "{0}".format(directory))
-        print(subdirectory)
-
+        directories = self._getDirectories([], "{0}".format(directory))
+        files = self._getFiles(directories)
+        self.fromFile(files)
+        
 
     def fromFile(self, files):
-        for file in files.split(","):
+        for file in files:
             if os.path.exists(file):
+                print(file)
                 with open(file, 'r') as f:
                     content = f.read()
                     soup = BeautifulSoup(content, 'html.parser')
@@ -33,12 +35,24 @@ class WPimport:
     
     # Private method
 
-    def _checkDirectory(self, subdirectory, item):
+    ## Get all files
+
+    def _getFiles(self, item):
+        files = []
+        for i in item:
+            for j in os.listdir(i):
+                if os.path.isfile("{0}/{1}".format(i, j)):
+                    files.append("{0}/{1}".format(i, j))
+        return files
+
+    ## Get directories
+
+    def _getDirectories(self, subdirectory, item):
         sub = subdirectory
         for i in os.listdir(item):
             if os.path.isdir("{0}/{1}".format(item, i)):
                 sub.append("{0}/{1}".format(item, i))
-                subdirectory = self._checkDirectory(sub, "{0}/{1}".format(item, i))
+                subdirectory = self._getDirectories(sub, "{0}/{1}".format(item, i))
         return subdirectory
 
     ## Add or update featured media
@@ -269,7 +283,7 @@ if __name__ == '__main__':
     basic = HTTPBasicAuth(args.user, password)
     importWp = WPimport(basic, args.wordpress)
     if len(args.file) > 0:
-        importWp.fromFile(args.file)
+        importWp.fromFile(args.file.split(","))
         exit(0)
     if len(args.directory) > 0:
         importWp.fromDirectory(args.directory)
\ No newline at end of file

From d58ead52b2a157e8a0743a185463e17a4334f800 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 8 Apr 2023 12:17:43 +0200
Subject: [PATCH 37/60] replace print by logger

---
 insert_wordpress.py | 55 ++++++++++++++++++++++++++++++++++-----------
 1 file changed, 42 insertions(+), 13 deletions(-)

diff --git a/insert_wordpress.py b/insert_wordpress.py
index 2c29e80..2fc36fa 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -7,9 +7,10 @@ import requests, os, argparse, logging, re, json
 
 class WPimport:
     # Constructor
-    def __init__(self, basic, wordpress):
+    def __init__(self, basic, wordpress, logger):
         self._basic = basic
         self._wordpress = wordpress
+        self._logger = logger
 
     # Public method
 
@@ -23,7 +24,7 @@ class WPimport:
     def fromFile(self, files):
         for file in files:
             if os.path.exists(file):
-                print(file)
+                logger.info("Fichier en cours de traitement : {0}".format(file))
                 with open(file, 'r') as f:
                     content = f.read()
                     soup = BeautifulSoup(content, 'html.parser')
@@ -84,9 +85,9 @@ class WPimport:
                                         data = {"featured_media": id_media}
                                         r = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, result[0]["id"]), auth=self._basic, headers=headers, data=json.dumps(data))
                                         if r.status_code == 200:
-                                            print("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
+                                            logger.info("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
                                     else:
-                                        print("Aucun media trouvé pour {0}".format(h2))
+                                        logger.info("Aucun media trouvé pour {0}".format(h2))
                 
     ## Association image to post
 
@@ -95,7 +96,7 @@ class WPimport:
             data = {"post": post_id}
             r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, i["id"]), auth=self._basic, data=data)
             if r.status_code == 200:
-                print("Association d'une image à l'article {0}".format(title))
+                logger.info("Association d'une image à l'article {0}".format(title))
     
     ## Add or update img 
 
@@ -111,7 +112,7 @@ class WPimport:
                 params = {"force":1}
                 r = requests.delete("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, res[0]["id"]), auth=self._basic, params=params)
                 if r.status_code == 200:
-                    print("Image supprimé {0}".format(img_name))
+                    logger.info("Image supprimé {0}".format(img_name))
             data = page.content
             img_type = "image/png"
             if img_name.split(".")[1] == "jpg" or img_name.split(".")[1] == "jpeg":
@@ -119,7 +120,7 @@ class WPimport:
             headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
             r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
             if r.status_code == 201:
-                print("Ajout d'image {0}".format(img_name))
+                logger.info("Ajout d'image {0}".format(img_name))
                 res = r.json()
                 media["id"] = res["id"]
                 media["rendered"] = res["guid"]["rendered"]
@@ -241,12 +242,12 @@ class WPimport:
             if len(result) == 0:
                 page_exist = False
             else:
-                print("La page {0} existe deja et mis à jour".format(title))
+                logger.info("La page {0} existe deja et mis à jour".format(title))
                 post_id = result[0]["id"]
                 page = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, data=json.dumps(data))
                 if page.status_code == 200:
                     result = page.json()
-                    print("Article mis à jour : {0}".format(result["title"]["raw"]))
+                    logger.info("Article mis à jour : {0}".format(result["title"]["raw"]))
                     self._linkImgPost(result["title"]["raw"], list_img, result["id"])
 
 
@@ -255,12 +256,12 @@ class WPimport:
             page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
             if page.status_code == 201:
                 result = page.json()
-                print("Article ajoute : {0}".format(result["title"]["raw"]))
+                logger.info("Article ajoute : {0}".format(result["title"]["raw"]))
                 for i in comment_post:
                     data = {"post": result["id"], "content": i["content"], "date": i["date"], "author_name": i["author"]}
                     page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, data=data)
                     if page.status_code == 201:
-                        print("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
+                        logger.info("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
                 self._linkImgPost(result["title"]["raw"], list_img, result["id"])
 
 
@@ -274,14 +275,42 @@ if __name__ == '__main__':
     parser.add_argument("--file", help="HTML file", default="")
     parser.add_argument("--directory", help="HTML directory", default="")
     parser.add_argument("--wordpress", help="URL Wordpress", required=True)
+    parser.add_argument("--debug", help="Verbosity",  action="store_true")
+    parser.add_argument("--logfile", help="Log file",  default="")
+    parser.add_argument("--quiet", help="No console output", action="store_true")
+
     args = parser.parse_args()
+    logger = logging.getLogger('insert wordpress')
+    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+
+    if args.quiet is False:
+        ch = logging.StreamHandler()
+        if args.debug is True:
+            logger.setLevel(logging.DEBUG)
+            ch.setLevel(logging.DEBUG)
+        else:
+            logger.setLevel(logging.INFO)
+            ch.setLevel(logging.INFO)
+        ch.setFormatter(formatter)
+        logger.addHandler(ch)
+
+
+    if len(args.logfile) > 0:
+        fileHandler = logging.FileHandler(args.logfile)
+        if args.debug is True:
+            fileHandler.setLevel(logging.DEBUG)
+        else:
+            fileHandler.setLevel(logging.INFO)
+        fileHandler.setFormatter(formatter)
+        logger.addHandler(fileHandler)
+
     password = getpass()
     if len(password) == 0:
-        print("No password error !!! ")
+        logger.error("No password error !!! ")
         exit(1)
 
     basic = HTTPBasicAuth(args.user, password)
-    importWp = WPimport(basic, args.wordpress)
+    importWp = WPimport(basic, args.wordpress, logger)
     if len(args.file) > 0:
         importWp.fromFile(args.file.split(","))
         exit(0)

From 6f7504e669897443a06dfd880db736f33bb048fa Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 8 Apr 2023 12:27:30 +0200
Subject: [PATCH 38/60] separate file class

---
 WPImport.py         | 268 ++++++++++++++++++++++++++++++++++++++++++++
 insert_wordpress.py | 268 +-------------------------------------------
 2 files changed, 270 insertions(+), 266 deletions(-)
 create mode 100644 WPImport.py

diff --git a/WPImport.py b/WPImport.py
new file mode 100644
index 0000000..9b4691c
--- /dev/null
+++ b/WPImport.py
@@ -0,0 +1,268 @@
+#!/usr/bin/python3
+
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse
+import requests, os, logging, re, json
+
+class WPimport:
+    # Constructor
+    def __init__(self, basic, wordpress, logger):
+        self._basic = basic
+        self._wordpress = wordpress
+        self._logger = logger
+
+    # Public method
+
+    def fromDirectory(self, directory):
+        directory = "{0}/archives".format(directory)
+        directories = self._getDirectories([], "{0}".format(directory))
+        files = self._getFiles(directories)
+        self.fromFile(files)
+        
+
+    def fromFile(self, files):
+        for file in files:
+            if os.path.exists(file):
+                logger.info("Fichier en cours de traitement : {0}".format(file))
+                with open(file, 'r') as f:
+                    content = f.read()
+                    soup = BeautifulSoup(content, 'html.parser')
+                    articlebody = soup.find_all("div", class_="articlebody")
+                    if len(articlebody) > 0:
+                        self._addOrUpdatePost(soup)
+                    else:
+                        self._addOrUpdateFeaturedMedia(soup)
+    
+    # Private method
+
+    ## Get all files
+
+    def _getFiles(self, item):
+        files = []
+        for i in item:
+            for j in os.listdir(i):
+                if os.path.isfile("{0}/{1}".format(i, j)):
+                    files.append("{0}/{1}".format(i, j))
+        return files
+
+    ## Get directories
+
+    def _getDirectories(self, subdirectory, item):
+        sub = subdirectory
+        for i in os.listdir(item):
+            if os.path.isdir("{0}/{1}".format(item, i)):
+                sub.append("{0}/{1}".format(item, i))
+                subdirectory = self._getDirectories(sub, "{0}/{1}".format(item, i))
+        return subdirectory
+
+    ## Add or update featured media
+
+    def _addOrUpdateFeaturedMedia(self, soup):
+        item_div = soup.find_all("div", {"data-edittype": "post"})
+        for i in item_div:
+            h2 = i.find_all("h2")[0].text
+            params = {"search":h2, "type":"post"}
+            page = requests.get("http://{0}/wp-json/wp/v2/search".format(self._wordpress), auth=self._basic, params=params)
+            if page.status_code == 200:
+                result = page.json()
+                if len(result) > 0:
+                    if h2 == result[0]["title"]:
+                        img = i.find_all("img")
+                        if len(img) > 0:
+                            img_src = img[0].get("src")
+                            page = requests.get(img_src)
+                            if page.status_code == 200:
+                                name_img = img_src.replace("_q", "")
+                                name_img = name_img.split("/")[len(name_img.split("/"))-1]
+                                params = {"search": name_img}
+                                page = requests.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
+                                if page.status_code == 200:
+                                    res = page.json()
+                                    if len(res) > 0:
+                                        id_media = res[0]["id"]
+                                        headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
+                                        data = {"featured_media": id_media}
+                                        r = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, result[0]["id"]), auth=self._basic, headers=headers, data=json.dumps(data))
+                                        if r.status_code == 200:
+                                            logger.info("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
+                                    else:
+                                        logger.info("Aucun media trouvé pour {0}".format(h2))
+                
+    ## Association image to post
+
+    def _linkImgPost(self, title, list_img, post_id):
+        for i in list_img:
+            data = {"post": post_id}
+            r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, i["id"]), auth=self._basic, data=data)
+            if r.status_code == 200:
+                logger.info("Association d'une image à l'article {0}".format(title))
+    
+    ## Add or update img 
+
+    def _addOrUpdateMedia(self, href_img, page):
+        media = {"id":"", "rendered":""}
+        split_fileimg = href_img.split("/")
+        img_name = split_fileimg[len(split_fileimg)-1]
+        params = { "search": img_name}
+        r = requests.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
+        if r.status_code == 200:
+            res = r.json()
+            if len(res) > 0:
+                params = {"force":1}
+                r = requests.delete("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, res[0]["id"]), auth=self._basic, params=params)
+                if r.status_code == 200:
+                    logger.info("Image supprimé {0}".format(img_name))
+            data = page.content
+            img_type = "image/png"
+            if img_name.split(".")[1] == "jpg" or img_name.split(".")[1] == "jpeg":
+                img_type = "image/jpg"
+            headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
+            r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
+            if r.status_code == 201:
+                logger.info("Ajout d'image {0}".format(img_name))
+                res = r.json()
+                media["id"] = res["id"]
+                media["rendered"] = res["guid"]["rendered"]
+        return media
+    
+    ## Add or Update post 
+
+    def _addOrUpdatePost(self, soup):
+        tags = []
+        month = {"janvier":"01", "février": "02", "mars": "03", "avril":"04", "mai": "05", "juin": "06", "juillet": "07", "août": "08", "septembre": "09", "octobre": "10", "novembre": "11", "décembre": "12"}
+        liste = ["categories", "tags"]
+        elements = {}
+        element = {}
+        listelement = {}
+
+        for i in liste:
+            page = requests.get("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress,i))
+            if page.status_code == 200:
+                elements[i] = page.json()
+                element[i] = []
+                listelement[i] = []
+
+        articletitle = soup.find_all("h2", class_="articletitle")
+        articlebody = soup.find_all("div", class_="articlebody")
+        articledate = soup.find_all("span", class_="articledate")
+        articleacreator = soup.find_all("span", class_="articlecreator")
+        dateheader = soup.find_all("div", class_="dateheader")
+        itemfooter = soup.find_all("div", class_="itemfooter")
+        comment = soup.find_all("div", class_="comment_item")
+        img_a = articlebody[0].find_all("a", {"target": "_blank"})
+        list_img = []
+        for i in img_a:
+            new_img = {}
+            img = i.find_all("img")
+            if len(img) > 0:
+                href_a = i.get("href")
+                href_img = img[0].get("src")
+                new_img["old_src"]=href_img
+                new_img["old_href"]=href_a
+                page_img = requests.get(href_img)
+                if page_img.status_code == 404:
+                    href_img = href_a
+                    page_img = requests.get(href_a)
+                if page_img.status_code == 200:
+                    media=self._addOrUpdateMedia(href_img, page_img)
+                    new_img["id"]=media["id"]
+                    new_img["new_src"]=media["rendered"]
+                    list_img.append(new_img)
+                    if href_img != href_a:
+                        media=self._addOrUpdateMedia(href_a, page_img)
+                        new_img["id"]=media["id"]
+                        new_img["new_src"]=media["rendered"]
+                        list_img.append(new_img)
+                
+        comment_post = []
+        for i in comment:
+            comment_item = i.text.split("\n")
+            footer = i.find_all("div", class_="itemfooter")
+            comment_author = footer[0].text.split(",")[0].replace("Posté par ", "")
+            comment_date = footer[0].find_all("abbr")[0].get("title")
+            comment_content = "<p>"
+            for j in range(0, len(comment_item)-2):
+                if len(comment_item[j]) > 0:
+                    comment_content = comment_content + comment_item[j] + "<br />"
+            comment_content = comment_content + "</p>"
+            comment_post.append({"author": comment_author, "date": comment_date, "content": comment_content})
+        a = itemfooter[0].find_all("a", {"rel": True})
+        for i in a:
+            rel = i.get("rel")
+            if rel[0] == 'tag':
+                href = i.get("href")
+                if re.search(r'/tag/', href):
+                    element["tags"].append(i.text)
+                if re.search(r'/archives/', href):
+                    element["categories"].append(i.text)
+        for i in liste:
+            for j in element[i]:
+                element_exist = False
+                for k in elements[i]:
+                    if k["name"] == j:
+                        element_exist = True
+                        listelement[i].append(k["id"])
+                if element_exist is False:
+                    data = {"name": j}
+                    page = requests.post("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i), auth=self._basic, data=data)
+                    if page.status_code == 201:
+                        result = page.json()
+                        listelement[i].append(result["id"])
+
+        title = articletitle[0].text
+        author = articleacreator[0].text.lower()        
+        body = articlebody[0].find_all("p")
+        bodyhtml = "<p>"
+        for i in body:
+            if len(i.text) == 1:
+                bodyhtml = bodyhtml + "<br />"
+            else:
+                bodyhtml = bodyhtml + str(i).replace("<p>", "").replace("</p>", "").replace("<br>", "<br />") + "<br />"
+        bodyhtml = bodyhtml + "</p>"
+        for i in list_img:
+            o = urlparse(i["new_src"])
+            bodyhtml = bodyhtml.replace(i["old_href"], o.path)
+            bodyhtml = bodyhtml.replace(i["old_src"], o.path)
+        hour = articledate[0].text
+        time = dateheader[0].text.split(" ")
+        data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
+        params = {"search":author}
+        page = requests.get("http://{0}/wp-json/wp/v2/users".format(self._wordpress), auth=self._basic, params=params)
+        if page.status_code == 200:
+            result = page.json()
+            data["author"] = result[0]["id"]
+
+        params = {"search":title}
+        page = requests.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params)
+        page_exist = True
+        headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
+        if page.status_code == 200:
+            result = page.json()
+            if len(result) == 0:
+                page_exist = False
+            else:
+                logger.info("La page {0} existe deja et mis à jour".format(title))
+                post_id = result[0]["id"]
+                page = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, data=json.dumps(data))
+                if page.status_code == 200:
+                    result = page.json()
+                    logger.info("Article mis à jour : {0}".format(result["title"]["raw"]))
+                    self._linkImgPost(result["title"]["raw"], list_img, result["id"])
+
+
+
+        if page_exist == False:
+            page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
+            if page.status_code == 201:
+                result = page.json()
+                logger.info("Article ajoute : {0}".format(result["title"]["raw"]))
+                for i in comment_post:
+                    data = {"post": result["id"], "content": i["content"], "date": i["date"], "author_name": i["author"]}
+                    page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, data=data)
+                    if page.status_code == 201:
+                        logger.info("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
+                self._linkImgPost(result["title"]["raw"], list_img, result["id"])
+
+
+
+    
diff --git a/insert_wordpress.py b/insert_wordpress.py
index 2fc36fa..68d2244 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -1,272 +1,8 @@
 #!/usr/bin/python3
-from bs4 import BeautifulSoup
-from urllib.parse import urlparse
 from requests.auth import HTTPBasicAuth
 from getpass import getpass
-import requests, os, argparse, logging, re, json
-
-class WPimport:
-    # Constructor
-    def __init__(self, basic, wordpress, logger):
-        self._basic = basic
-        self._wordpress = wordpress
-        self._logger = logger
-
-    # Public method
-
-    def fromDirectory(self, directory):
-        directory = "{0}/archives".format(directory)
-        directories = self._getDirectories([], "{0}".format(directory))
-        files = self._getFiles(directories)
-        self.fromFile(files)
-        
-
-    def fromFile(self, files):
-        for file in files:
-            if os.path.exists(file):
-                logger.info("Fichier en cours de traitement : {0}".format(file))
-                with open(file, 'r') as f:
-                    content = f.read()
-                    soup = BeautifulSoup(content, 'html.parser')
-                    articlebody = soup.find_all("div", class_="articlebody")
-                    if len(articlebody) > 0:
-                        self._addOrUpdatePost(soup)
-                    else:
-                        self._addOrUpdateFeaturedMedia(soup)
-    
-    # Private method
-
-    ## Get all files
-
-    def _getFiles(self, item):
-        files = []
-        for i in item:
-            for j in os.listdir(i):
-                if os.path.isfile("{0}/{1}".format(i, j)):
-                    files.append("{0}/{1}".format(i, j))
-        return files
-
-    ## Get directories
-
-    def _getDirectories(self, subdirectory, item):
-        sub = subdirectory
-        for i in os.listdir(item):
-            if os.path.isdir("{0}/{1}".format(item, i)):
-                sub.append("{0}/{1}".format(item, i))
-                subdirectory = self._getDirectories(sub, "{0}/{1}".format(item, i))
-        return subdirectory
-
-    ## Add or update featured media
-
-    def _addOrUpdateFeaturedMedia(self, soup):
-        item_div = soup.find_all("div", {"data-edittype": "post"})
-        for i in item_div:
-            h2 = i.find_all("h2")[0].text
-            params = {"search":h2, "type":"post"}
-            page = requests.get("http://{0}/wp-json/wp/v2/search".format(self._wordpress), auth=self._basic, params=params)
-            if page.status_code == 200:
-                result = page.json()
-                if len(result) > 0:
-                    if h2 == result[0]["title"]:
-                        img = i.find_all("img")
-                        if len(img) > 0:
-                            img_src = img[0].get("src")
-                            page = requests.get(img_src)
-                            if page.status_code == 200:
-                                name_img = img_src.replace("_q", "")
-                                name_img = name_img.split("/")[len(name_img.split("/"))-1]
-                                params = {"search": name_img}
-                                page = requests.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
-                                if page.status_code == 200:
-                                    res = page.json()
-                                    if len(res) > 0:
-                                        id_media = res[0]["id"]
-                                        headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
-                                        data = {"featured_media": id_media}
-                                        r = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, result[0]["id"]), auth=self._basic, headers=headers, data=json.dumps(data))
-                                        if r.status_code == 200:
-                                            logger.info("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
-                                    else:
-                                        logger.info("Aucun media trouvé pour {0}".format(h2))
-                
-    ## Association image to post
-
-    def _linkImgPost(self, title, list_img, post_id):
-        for i in list_img:
-            data = {"post": post_id}
-            r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, i["id"]), auth=self._basic, data=data)
-            if r.status_code == 200:
-                logger.info("Association d'une image à l'article {0}".format(title))
-    
-    ## Add or update img 
-
-    def _addOrUpdateMedia(self, href_img, page):
-        media = {"id":"", "rendered":""}
-        split_fileimg = href_img.split("/")
-        img_name = split_fileimg[len(split_fileimg)-1]
-        params = { "search": img_name}
-        r = requests.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
-        if r.status_code == 200:
-            res = r.json()
-            if len(res) > 0:
-                params = {"force":1}
-                r = requests.delete("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, res[0]["id"]), auth=self._basic, params=params)
-                if r.status_code == 200:
-                    logger.info("Image supprimé {0}".format(img_name))
-            data = page.content
-            img_type = "image/png"
-            if img_name.split(".")[1] == "jpg" or img_name.split(".")[1] == "jpeg":
-                img_type = "image/jpg"
-            headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
-            r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
-            if r.status_code == 201:
-                logger.info("Ajout d'image {0}".format(img_name))
-                res = r.json()
-                media["id"] = res["id"]
-                media["rendered"] = res["guid"]["rendered"]
-        return media
-    
-    ## Add or Update post 
-
-    def _addOrUpdatePost(self, soup):
-        tags = []
-        month = {"janvier":"01", "février": "02", "mars": "03", "avril":"04", "mai": "05", "juin": "06", "juillet": "07", "août": "08", "septembre": "09", "octobre": "10", "novembre": "11", "décembre": "12"}
-        liste = ["categories", "tags"]
-        elements = {}
-        element = {}
-        listelement = {}
-
-        for i in liste:
-            page = requests.get("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress,i))
-            if page.status_code == 200:
-                elements[i] = page.json()
-                element[i] = []
-                listelement[i] = []
-
-        articletitle = soup.find_all("h2", class_="articletitle")
-        articlebody = soup.find_all("div", class_="articlebody")
-        articledate = soup.find_all("span", class_="articledate")
-        articleacreator = soup.find_all("span", class_="articlecreator")
-        dateheader = soup.find_all("div", class_="dateheader")
-        itemfooter = soup.find_all("div", class_="itemfooter")
-        comment = soup.find_all("div", class_="comment_item")
-        img_a = articlebody[0].find_all("a", {"target": "_blank"})
-        list_img = []
-        for i in img_a:
-            new_img = {}
-            img = i.find_all("img")
-            if len(img) > 0:
-                href_a = i.get("href")
-                href_img = img[0].get("src")
-                new_img["old_src"]=href_img
-                new_img["old_href"]=href_a
-                page_img = requests.get(href_img)
-                if page_img.status_code == 404:
-                    href_img = href_a
-                    page_img = requests.get(href_a)
-                if page_img.status_code == 200:
-                    media=self._addOrUpdateMedia(href_img, page_img)
-                    new_img["id"]=media["id"]
-                    new_img["new_src"]=media["rendered"]
-                    list_img.append(new_img)
-                    if href_img != href_a:
-                        media=self._addOrUpdateMedia(href_a, page_img)
-                        new_img["id"]=media["id"]
-                        new_img["new_src"]=media["rendered"]
-                        list_img.append(new_img)
-                
-        comment_post = []
-        for i in comment:
-            comment_item = i.text.split("\n")
-            footer = i.find_all("div", class_="itemfooter")
-            comment_author = footer[0].text.split(",")[0].replace("Posté par ", "")
-            comment_date = footer[0].find_all("abbr")[0].get("title")
-            comment_content = "<p>"
-            for j in range(0, len(comment_item)-2):
-                if len(comment_item[j]) > 0:
-                    comment_content = comment_content + comment_item[j] + "<br />"
-            comment_content = comment_content + "</p>"
-            comment_post.append({"author": comment_author, "date": comment_date, "content": comment_content})
-        a = itemfooter[0].find_all("a", {"rel": True})
-        for i in a:
-            rel = i.get("rel")
-            if rel[0] == 'tag':
-                href = i.get("href")
-                if re.search(r'/tag/', href):
-                    element["tags"].append(i.text)
-                if re.search(r'/archives/', href):
-                    element["categories"].append(i.text)
-        for i in liste:
-            for j in element[i]:
-                element_exist = False
-                for k in elements[i]:
-                    if k["name"] == j:
-                        element_exist = True
-                        listelement[i].append(k["id"])
-                if element_exist is False:
-                    data = {"name": j}
-                    page = requests.post("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i), auth=self._basic, data=data)
-                    if page.status_code == 201:
-                        result = page.json()
-                        listelement[i].append(result["id"])
-
-        title = articletitle[0].text
-        author = articleacreator[0].text.lower()        
-        body = articlebody[0].find_all("p")
-        bodyhtml = "<p>"
-        for i in body:
-            if len(i.text) == 1:
-                bodyhtml = bodyhtml + "<br />"
-            else:
-                bodyhtml = bodyhtml + str(i).replace("<p>", "").replace("</p>", "").replace("<br>", "<br />") + "<br />"
-        bodyhtml = bodyhtml + "</p>"
-        for i in list_img:
-            o = urlparse(i["new_src"])
-            bodyhtml = bodyhtml.replace(i["old_href"], o.path)
-            bodyhtml = bodyhtml.replace(i["old_src"], o.path)
-        hour = articledate[0].text
-        time = dateheader[0].text.split(" ")
-        data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
-        params = {"search":author}
-        page = requests.get("http://{0}/wp-json/wp/v2/users".format(self._wordpress), auth=self._basic, params=params)
-        if page.status_code == 200:
-            result = page.json()
-            data["author"] = result[0]["id"]
-
-        params = {"search":title}
-        page = requests.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params)
-        page_exist = True
-        headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
-        if page.status_code == 200:
-            result = page.json()
-            if len(result) == 0:
-                page_exist = False
-            else:
-                logger.info("La page {0} existe deja et mis à jour".format(title))
-                post_id = result[0]["id"]
-                page = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, data=json.dumps(data))
-                if page.status_code == 200:
-                    result = page.json()
-                    logger.info("Article mis à jour : {0}".format(result["title"]["raw"]))
-                    self._linkImgPost(result["title"]["raw"], list_img, result["id"])
-
-
-
-        if page_exist == False:
-            page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
-            if page.status_code == 201:
-                result = page.json()
-                logger.info("Article ajoute : {0}".format(result["title"]["raw"]))
-                for i in comment_post:
-                    data = {"post": result["id"], "content": i["content"], "date": i["date"], "author_name": i["author"]}
-                    page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, data=data)
-                    if page.status_code == 201:
-                        logger.info("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
-                self._linkImgPost(result["title"]["raw"], list_img, result["id"])
-
-
-
-    
+import argparse, logging
+import WPImport
 
 
 if __name__ == '__main__':

From 481fc40929357d30dc8eb5b9ba9768189428ba7f Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 8 Apr 2023 21:27:35 +0200
Subject: [PATCH 39/60] separate class file for WPimport

---
 WPImport.py         | 20 ++++++++++----------
 insert_wordpress.py |  2 +-
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/WPImport.py b/WPImport.py
index 9b4691c..e3164f1 100644
--- a/WPImport.py
+++ b/WPImport.py
@@ -23,7 +23,7 @@ class WPimport:
     def fromFile(self, files):
         for file in files:
             if os.path.exists(file):
-                logger.info("Fichier en cours de traitement : {0}".format(file))
+                self._logger.info("Fichier en cours de traitement : {0}".format(file))
                 with open(file, 'r') as f:
                     content = f.read()
                     soup = BeautifulSoup(content, 'html.parser')
@@ -84,9 +84,9 @@ class WPimport:
                                         data = {"featured_media": id_media}
                                         r = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, result[0]["id"]), auth=self._basic, headers=headers, data=json.dumps(data))
                                         if r.status_code == 200:
-                                            logger.info("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
+                                            self._logger.info("Ajout media featured : {0}".format(r.json()["title"]["raw"]))
                                     else:
-                                        logger.info("Aucun media trouvé pour {0}".format(h2))
+                                        self._logger.info("Aucun media trouvé pour {0}".format(h2))
                 
     ## Association image to post
 
@@ -95,7 +95,7 @@ class WPimport:
             data = {"post": post_id}
             r = requests.post("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, i["id"]), auth=self._basic, data=data)
             if r.status_code == 200:
-                logger.info("Association d'une image à l'article {0}".format(title))
+                self._logger.info("Association d'une image à l'article {0}".format(title))
     
     ## Add or update img 
 
@@ -111,7 +111,7 @@ class WPimport:
                 params = {"force":1}
                 r = requests.delete("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, res[0]["id"]), auth=self._basic, params=params)
                 if r.status_code == 200:
-                    logger.info("Image supprimé {0}".format(img_name))
+                    self._logger.info("Image supprimé {0}".format(img_name))
             data = page.content
             img_type = "image/png"
             if img_name.split(".")[1] == "jpg" or img_name.split(".")[1] == "jpeg":
@@ -119,7 +119,7 @@ class WPimport:
             headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
             r = requests.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
             if r.status_code == 201:
-                logger.info("Ajout d'image {0}".format(img_name))
+                self._logger.info("Ajout d'image {0}".format(img_name))
                 res = r.json()
                 media["id"] = res["id"]
                 media["rendered"] = res["guid"]["rendered"]
@@ -241,12 +241,12 @@ class WPimport:
             if len(result) == 0:
                 page_exist = False
             else:
-                logger.info("La page {0} existe deja et mis à jour".format(title))
+                self._logger.info("La page {0} existe deja et mis à jour".format(title))
                 post_id = result[0]["id"]
                 page = requests.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, data=json.dumps(data))
                 if page.status_code == 200:
                     result = page.json()
-                    logger.info("Article mis à jour : {0}".format(result["title"]["raw"]))
+                    self._logger.info("Article mis à jour : {0}".format(result["title"]["raw"]))
                     self._linkImgPost(result["title"]["raw"], list_img, result["id"])
 
 
@@ -255,12 +255,12 @@ class WPimport:
             page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
             if page.status_code == 201:
                 result = page.json()
-                logger.info("Article ajoute : {0}".format(result["title"]["raw"]))
+                self._logger.info("Article ajoute : {0}".format(result["title"]["raw"]))
                 for i in comment_post:
                     data = {"post": result["id"], "content": i["content"], "date": i["date"], "author_name": i["author"]}
                     page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, data=data)
                     if page.status_code == 201:
-                        logger.info("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
+                        self._logger.info("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
                 self._linkImgPost(result["title"]["raw"], list_img, result["id"])
 
 
diff --git a/insert_wordpress.py b/insert_wordpress.py
index 68d2244..4c828cc 100644
--- a/insert_wordpress.py
+++ b/insert_wordpress.py
@@ -46,7 +46,7 @@ if __name__ == '__main__':
         exit(1)
 
     basic = HTTPBasicAuth(args.user, password)
-    importWp = WPimport(basic, args.wordpress, logger)
+    importWp = WPImport.WPimport(basic, args.wordpress, logger)
     if len(args.file) > 0:
         importWp.fromFile(args.file.split(","))
         exit(0)

From 2289066dd5360006cebc0de71c25f8a31c4ea43b Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 8 Apr 2023 21:44:52 +0200
Subject: [PATCH 40/60] rename main file

---
 insert_wordpress.py => import_export_canalblog.py | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename insert_wordpress.py => import_export_canalblog.py (100%)

diff --git a/insert_wordpress.py b/import_export_canalblog.py
similarity index 100%
rename from insert_wordpress.py
rename to import_export_canalblog.py

From 8384dcb2b618532b9703be0c12bbc0553fa7d96a Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 8 Apr 2023 22:14:20 +0200
Subject: [PATCH 41/60] create class WPExport

---
 WPExport.py | 242 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 242 insertions(+)
 create mode 100644 WPExport.py

diff --git a/WPExport.py b/WPExport.py
new file mode 100644
index 0000000..87571d7
--- /dev/null
+++ b/WPExport.py
@@ -0,0 +1,242 @@
+#!/usr/bin/python3
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse
+import requests, os, argparse, logging
+
+class WPExport:
+    def __init__(self, url, logger):
+        self._url = url
+        self._logger = logger
+        
+    def _mkdirPath(self, path_dir, logger):
+        if not os.path.exists(path_dir):
+            makedir = []
+            pathh = path_dir.split("/")
+            for i in pathh:
+                makedir.append(i)
+                repath = "/".join(makedir)
+                if not os.path.exists(repath):
+                    self._logger.debug("Dossier crée : {0}".format(repath))
+                    try:
+                        if len(repath) > 0:
+                            os.mkdir(repath)
+                    except Exception as err:
+                        self._logger.error("Directory error : {0}".format(err))
+                        self._logger.debug("Directory error : {0} {1} {2} {3} {4}".format(err, path_dir, repath, pathh, makedir))
+                        exit(1)
+
+
+    def _getScriptCss(self, js, css, logger):
+        try:
+            page = requests.get(url)
+        except Exception as err:
+            self._logger.error("Connection error : {0}".format(err))
+            exit(1)
+        page_url = []
+        if page.status_code == 200:
+            soup = BeautifulSoup(page.text, 'html.parser')
+            if js is True:
+                script = soup.find_all("script")
+                for anchor in script:
+                    src = anchor.get("src", "/")
+                    if src != "/":
+                        try:
+                            u = urlparse(url)
+                            o = urlparse(src)
+                        except Exception as err:
+                            self._logger.error("parsing error : {0}".format(err))
+                            exit(1)
+                        if o.netloc == "":
+                            o = o._replace(netloc=u.netloc)
+                            o = o._replace(scheme=u.scheme)
+                        page_url.append(o.geturl())
+            if css is True:
+                link = soup.find_all("link")
+                for anchor in link:
+                    rel = anchor.get("rel")
+                    if rel[0] == "stylesheet":
+                        href = anchor.get("href", "/")
+                        if href != "/":
+                            try:
+                                u = urlparse(url)
+                                o = urlparse(href)
+                            except Exception as err:
+                                self._logger.error("parsing error : {0}".format(err))
+                                exit(1)
+                            if o.netloc == "":
+                                o = o._replace(netloc=u.netloc)
+                                o = o._replace(scheme=u.scheme)
+                            page_url.append(o.geturl())        
+        return page_url
+
+    def _getImg(self, webpage):
+        page_img = []
+        for i in webpage:
+            try:
+                page = requests.get(i)
+            except Exception as err:
+                self._logger.error("Connection error : {0}".format(err))
+                exit(1)
+            if page.status_code == 200:
+                soup = BeautifulSoup(page.text, 'html.parser')
+                img = soup.find_all("img")
+                self._logger.info("image from page: {0} : ".format(i))
+                for anchor in img:
+                    src = anchor.get("src", "/")
+                    if src != "/":
+                        if src not in page_img:
+                            self._logger.info("image: {0} : ".format(src))
+                            page_img.append(src)
+        return page_img
+
+    def _getUrlPage(self):
+        try:
+            page = requests.get(self._url)
+        except Exception as err:
+            self._logger.error("Connection error : {0}".format(err))
+            exit(1)
+        page_url = []
+        if page.status_code == 200:
+            soup = BeautifulSoup(page.text, 'html.parser')
+            ul = soup.find_all("ul", id="listsmooth")
+            for anchor in ul[0].find_all("a"):
+                href = anchor.get('href', '/')
+                if href != "#":
+                    page_url.append(href)
+
+        webpage = []
+        for i in page_url:
+            try:
+                page = requests.get(i)
+            except Exception as err:
+                self._logger.error("Connection error : {0}".format(err))
+                exit(1)
+            if page.status_code == 200:
+                self._logger.info("page : {0}".format(i))
+                if i not in webpage:
+                    webpage.append(i)
+                soup = BeautifulSoup(page.text, 'html.parser')
+                class_div = pagingfirstline = soup.find_all("div", class_="pagingfirstline")
+                if len(class_div) > 0:
+                    pagingfirstline = class_div[0].find_all("a")
+                    if len(pagingfirstline) > 1:
+                        lastpage = pagingfirstline[len(pagingfirstline)-1].get("href", "/")
+                        element_lastpage = lastpage.split("/")[len(lastpage.split("/"))-1]
+                        number_page = element_lastpage.split("-")[0].split("p")[1]
+                        number_lastpage = int(number_page) / 10
+                        for j in range(1,int(number_lastpage)):
+                            paging = j * 10
+                            categorie = urlparse(i).path.split("/")
+                            url_paging = "{0}/archives/p{1}-10.html".format(url, paging)
+                            if len(categorie) > 2:
+                                url_paging = "{0}/archives/{1}/p{2}-10.html".format(url, categorie[2], paging)
+                            self._logger.info(url_paging)
+                            if url_paging not in webpage:
+                                webpage.append(url_paging)
+                            page = requests.get(url_paging)
+                            if page.status_code == 200:
+                                soup = BeautifulSoup(page.text, 'html.parser')
+                                h2 = soup.find_all("h2")
+                                for title in h2:
+                                    href = title.find_all("a")[0].get("href", "/")
+                                    if href not in webpage:
+                                        try:
+                                            o = urlparse(href)
+                                            o = o._replace(scheme="https").geturl()
+                                        except Exception as err:
+                                            self._logger.error("parsing error : {0}".format(err))
+                                            exit(1)
+                                        webpage.append(o)
+        return webpage
+
+
+    def _downloadPage(self, webpage, backup_dir):
+   
+        for i in range(0, len(webpage)):
+            try:
+                o = urlparse(webpage[i])
+            except Exception as err:
+                self._logger.error("parsing error : {0}".format(err))
+                exit(1)
+            path_web = o.path.split("/")
+            filePageWeb = path_web[len(path_web)-1]
+            path_web.pop(len(path_web)-1)
+            dir_page_web = "/".join(path_web)
+            self._mkdirPath("{0}/{1}/{2}".format(backup_dir, o.netloc, dir_page_web))
+            try:
+                r = requests.get(webpage[i])
+            except Exception as err:
+                self._logger.error("Connection error : {0}".format(err))
+                exit(1)
+            if r.status_code == 200:
+                fileDownload = "{0}/{1}/index.html".format(backup_dir, o.netloc)
+                if len(dir_page_web) > 0 and len(filePageWeb) > 0:
+                    fileDownload = "{0}/{1}{2}/{3}".format(backup_dir, o.netloc, dir_page_web, filePageWeb)
+                self._logger.info("{0}/{1} : {2}".format(i+1, len(webpage), fileDownload))
+                try:
+                    open(fileDownload, "wb").write(r.content)
+                except Exception as err:
+                    self._logger.error("file error : {0}".format(err))
+                    exit(1)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--url", help="canblog URL to be scraping", required=True)
+    parser.add_argument("--dir",
+                      default="backup",
+                      help="backup file path")
+    parser.add_argument("--debug", help="Verbosity",  action="store_true")
+    parser.add_argument("--logfile", help="Log file",  default="")
+    parser.add_argument("--no-css", help="No CSS", dest="css",  action="store_true")
+    parser.add_argument("--no-js", help="No JS", dest="js",  action="store_true")
+    parser.add_argument("--no-img", help="No img", dest="img",  action="store_true")
+    parser.add_argument("--no-html", help="No HTML", dest="html", action="store_true")
+    parser.add_argument("--quiet", help="No console output", action="store_true")
+    args = parser.parse_args()
+    logger = logging.getLogger('web_scrap')
+    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+
+    if args.quiet is False:
+        ch = logging.StreamHandler()
+        if args.debug is True:
+            logger.setLevel(logging.DEBUG)
+            ch.setLevel(logging.DEBUG)
+        else:
+            logger.setLevel(logging.INFO)
+            ch.setLevel(logging.INFO)
+        ch.setFormatter(formatter)
+        logger.addHandler(ch)
+
+
+    if len(args.logfile) > 0:
+        fileHandler = logging.FileHandler(args.logfile)
+        if args.debug is True:
+            fileHandler.setLevel(logging.DEBUG)
+        else:
+            fileHandler.setLevel(logging.INFO)
+        fileHandler.setFormatter(formatter)
+        logger.addHandler(fileHandler)
+    
+    try:
+        o = urlparse(args.url)
+        o = o._replace(scheme="https")
+        url = o.geturl().replace(":///", "://")
+    except Exception as err:
+        logger.error("parsing error : {0}".format(err))
+    if args.js is False:
+        script = getScriptCss(url, True, False, logger)
+        downloadPage(script, "{0}/{1}/{2}".format(args.dir, o.path, "dists/js"), logger)
+    
+    if args.css is False:
+        css = getScriptCss(url, False, True, logger)
+        downloadPage(css, "{0}/{1}/{2}".format(args.dir, o.path, "dists/css"), logger)
+    
+    if args.html is False or args.img is False:
+        webpage = getUrlPage(url, logger)
+    if args.html is False:
+        downloadPage(webpage, args.dir, logger)
+    
+    if args.img is False:
+        page_src = getImg(webpage, logger)
+        downloadPage(page_src, "{0}/{1}/{2}".format(args.dir, o.path, "img"), logger)

From b3f623cbd5ea66560165ad1c4f9fab691b0174e5 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 8 Apr 2023 23:20:52 +0200
Subject: [PATCH 42/60] subparser import

---
 import_export_canalblog.py | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 4c828cc..ed55576 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -7,14 +7,19 @@ import WPImport
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument("--user", help="wordpress user", required=True)
-    parser.add_argument("--file", help="HTML file", default="")
-    parser.add_argument("--directory", help="HTML directory", default="")
-    parser.add_argument("--wordpress", help="URL Wordpress", required=True)
     parser.add_argument("--debug", help="Verbosity",  action="store_true")
     parser.add_argument("--logfile", help="Log file",  default="")
     parser.add_argument("--quiet", help="No console output", action="store_true")
 
+    subparsers = parser.add_subparsers()
+
+    import_parser = subparsers.add_parser("import")
+    import_parser.add_argument("--user", help="wordpress user", required=True)
+    import_parser.add_argument("--file", help="HTML file", default="")
+    import_parser.add_argument("--directory", help="HTML directory", default="")
+    import_parser.add_argument("--wordpress", help="URL Wordpress", required=True)
+    
+
     args = parser.parse_args()
     logger = logging.getLogger('insert wordpress')
     formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')

From ebc6206ec9c6b430461b9c10df2c1c0cbdcfeccc Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 8 Apr 2023 23:34:56 +0200
Subject: [PATCH 43/60] add subparser export

---
 import_export_canalblog.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index ed55576..f1e07df 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -18,6 +18,18 @@ if __name__ == '__main__':
     import_parser.add_argument("--file", help="HTML file", default="")
     import_parser.add_argument("--directory", help="HTML directory", default="")
     import_parser.add_argument("--wordpress", help="URL Wordpress", required=True)
+
+    export_parser = subparsers.add_parser("export")
+
+    export_parser.add_argument("--url", help="canblog URL to be scraping", required=True)
+    export_parser.add_argument("--directory",
+                      default="backup",
+                      help="backup file path")
+    export_parser.add_argument("--no-css", help="No CSS", dest="css",  action="store_true")
+    export_parser.add_argument("--no-js", help="No JS", dest="js",  action="store_true")
+    export_parser.add_argument("--no-img", help="No img", dest="img",  action="store_true")
+    export_parser.add_argument("--no-html", help="No HTML", dest="html", action="store_true")
+
     
 
     args = parser.parse_args()

From 7e484fa308a9020effd8beedfadf123da06615ff Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sat, 8 Apr 2023 23:43:06 +0200
Subject: [PATCH 44/60] add args command name

---
 import_export_canalblog.py | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index f1e07df..7e5ea30 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -11,7 +11,7 @@ if __name__ == '__main__':
     parser.add_argument("--logfile", help="Log file",  default="")
     parser.add_argument("--quiet", help="No console output", action="store_true")
 
-    subparsers = parser.add_subparsers()
+    subparsers = parser.add_subparsers(dest="command")
 
     import_parser = subparsers.add_parser("import")
     import_parser.add_argument("--user", help="wordpress user", required=True)
@@ -33,6 +33,7 @@ if __name__ == '__main__':
     
 
     args = parser.parse_args()
+
     logger = logging.getLogger('insert wordpress')
     formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
 
@@ -57,15 +58,16 @@ if __name__ == '__main__':
         fileHandler.setFormatter(formatter)
         logger.addHandler(fileHandler)
 
-    password = getpass()
-    if len(password) == 0:
-        logger.error("No password error !!! ")
-        exit(1)
+    if args.command == "export":
+        password = getpass()
+        if len(password) == 0:
+            logger.error("No password error !!! ")
+            exit(1)
 
-    basic = HTTPBasicAuth(args.user, password)
-    importWp = WPImport.WPimport(basic, args.wordpress, logger)
-    if len(args.file) > 0:
-        importWp.fromFile(args.file.split(","))
-        exit(0)
-    if len(args.directory) > 0:
-        importWp.fromDirectory(args.directory)
\ No newline at end of file
+        basic = HTTPBasicAuth(args.user, password)
+        importWp = WPImport.WPimport(basic, args.wordpress, logger)
+        if len(args.file) > 0:
+            importWp.fromFile(args.file.split(","))
+            exit(0)
+        if len(args.directory) > 0:
+            importWp.fromDirectory(args.directory)
\ No newline at end of file

From cd6b03b0ffbb592e619ea74485f6d9b68dcd5d8e Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 9 Apr 2023 21:17:49 +0200
Subject: [PATCH 45/60] add parameter parser

---
 WPImport.py                | 5 +++--
 import_export_canalblog.py | 3 ++-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/WPImport.py b/WPImport.py
index e3164f1..92f6681 100644
--- a/WPImport.py
+++ b/WPImport.py
@@ -6,10 +6,11 @@ import requests, os, logging, re, json
 
 class WPimport:
     # Constructor
-    def __init__(self, basic, wordpress, logger):
+    def __init__(self, basic, wordpress, logger, parser):
         self._basic = basic
         self._wordpress = wordpress
         self._logger = logger
+        self._parser = parser
 
     # Public method
 
@@ -26,7 +27,7 @@ class WPimport:
                 self._logger.info("Fichier en cours de traitement : {0}".format(file))
                 with open(file, 'r') as f:
                     content = f.read()
-                    soup = BeautifulSoup(content, 'html.parser')
+                    soup = BeautifulSoup(content, self._parser)
                     articlebody = soup.find_all("div", class_="articlebody")
                     if len(articlebody) > 0:
                         self._addOrUpdatePost(soup)
diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 7e5ea30..cc19a06 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -10,6 +10,7 @@ if __name__ == '__main__':
     parser.add_argument("--debug", help="Verbosity",  action="store_true")
     parser.add_argument("--logfile", help="Log file",  default="")
     parser.add_argument("--quiet", help="No console output", action="store_true")
+    parser.add_argument("--parser", help="Parser content", default="html.parser")
 
     subparsers = parser.add_subparsers(dest="command")
 
@@ -65,7 +66,7 @@ if __name__ == '__main__':
             exit(1)
 
         basic = HTTPBasicAuth(args.user, password)
-        importWp = WPImport.WPimport(basic, args.wordpress, logger)
+        importWp = WPImport.WPimport(basic, args.wordpress, logger, args.parser)
         if len(args.file) > 0:
             importWp.fromFile(args.file.split(","))
             exit(0)

From 9ed08ea964f2725812236f3897f2d9c5c976e2b7 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 9 Apr 2023 21:45:51 +0200
Subject: [PATCH 46/60] add parameter parser

---
 WPExport.py | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/WPExport.py b/WPExport.py
index 87571d7..6fd0b8a 100644
--- a/WPExport.py
+++ b/WPExport.py
@@ -4,9 +4,10 @@ from urllib.parse import urlparse
 import requests, os, argparse, logging
 
 class WPExport:
-    def __init__(self, url, logger):
+    def __init__(self, url, logger, parser):
         self._url = url
         self._logger = logger
+        self._parser = parser
         
     def _mkdirPath(self, path_dir, logger):
         if not os.path.exists(path_dir):
@@ -34,7 +35,7 @@ class WPExport:
             exit(1)
         page_url = []
         if page.status_code == 200:
-            soup = BeautifulSoup(page.text, 'html.parser')
+            soup = BeautifulSoup(page.text, self._parser)
             if js is True:
                 script = soup.find_all("script")
                 for anchor in script:
@@ -78,7 +79,7 @@ class WPExport:
                 self._logger.error("Connection error : {0}".format(err))
                 exit(1)
             if page.status_code == 200:
-                soup = BeautifulSoup(page.text, 'html.parser')
+                soup = BeautifulSoup(page.text, self._parser)
                 img = soup.find_all("img")
                 self._logger.info("image from page: {0} : ".format(i))
                 for anchor in img:
@@ -97,7 +98,7 @@ class WPExport:
             exit(1)
         page_url = []
         if page.status_code == 200:
-            soup = BeautifulSoup(page.text, 'html.parser')
+            soup = BeautifulSoup(page.text, self._parser)
             ul = soup.find_all("ul", id="listsmooth")
             for anchor in ul[0].find_all("a"):
                 href = anchor.get('href', '/')
@@ -115,7 +116,7 @@ class WPExport:
                 self._logger.info("page : {0}".format(i))
                 if i not in webpage:
                     webpage.append(i)
-                soup = BeautifulSoup(page.text, 'html.parser')
+                soup = BeautifulSoup(page.text, self._parser)
                 class_div = pagingfirstline = soup.find_all("div", class_="pagingfirstline")
                 if len(class_div) > 0:
                     pagingfirstline = class_div[0].find_all("a")
@@ -135,7 +136,7 @@ class WPExport:
                                 webpage.append(url_paging)
                             page = requests.get(url_paging)
                             if page.status_code == 200:
-                                soup = BeautifulSoup(page.text, 'html.parser')
+                                soup = BeautifulSoup(page.text, self._parser)
                                 h2 = soup.find_all("h2")
                                 for title in h2:
                                     href = title.find_all("a")[0].get("href", "/")

From bba6cd1ca7561f3a8c8be70ce1aee6fd6eb4b2b0 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 9 Apr 2023 22:49:44 +0200
Subject: [PATCH 47/60] add export canalblog

---
 WPExport.py                | 264 +++++++++++++++++--------------------
 import_export_canalblog.py |  28 +++-
 2 files changed, 147 insertions(+), 145 deletions(-)

diff --git a/WPExport.py b/WPExport.py
index 6fd0b8a..6db20ad 100644
--- a/WPExport.py
+++ b/WPExport.py
@@ -4,93 +4,44 @@ from urllib.parse import urlparse
 import requests, os, argparse, logging
 
 class WPExport:
-    def __init__(self, url, logger, parser):
+    def __init__(self, url, logger, parser, directory):
         self._url = url
         self._logger = logger
         self._parser = parser
-        
-    def _mkdirPath(self, path_dir, logger):
-        if not os.path.exists(path_dir):
-            makedir = []
-            pathh = path_dir.split("/")
-            for i in pathh:
-                makedir.append(i)
-                repath = "/".join(makedir)
-                if not os.path.exists(repath):
-                    self._logger.debug("Dossier crée : {0}".format(repath))
-                    try:
-                        if len(repath) > 0:
-                            os.mkdir(repath)
-                    except Exception as err:
-                        self._logger.error("Directory error : {0}".format(err))
-                        self._logger.debug("Directory error : {0} {1} {2} {3} {4}".format(err, path_dir, repath, pathh, makedir))
-                        exit(1)
+        self._dir = directory
 
 
-    def _getScriptCss(self, js, css, logger):
-        try:
-            page = requests.get(url)
-        except Exception as err:
-            self._logger.error("Connection error : {0}".format(err))
-            exit(1)
-        page_url = []
-        if page.status_code == 200:
-            soup = BeautifulSoup(page.text, self._parser)
-            if js is True:
-                script = soup.find_all("script")
-                for anchor in script:
-                    src = anchor.get("src", "/")
-                    if src != "/":
-                        try:
-                            u = urlparse(url)
-                            o = urlparse(src)
-                        except Exception as err:
-                            self._logger.error("parsing error : {0}".format(err))
-                            exit(1)
-                        if o.netloc == "":
-                            o = o._replace(netloc=u.netloc)
-                            o = o._replace(scheme=u.scheme)
-                        page_url.append(o.geturl())
-            if css is True:
-                link = soup.find_all("link")
-                for anchor in link:
-                    rel = anchor.get("rel")
-                    if rel[0] == "stylesheet":
-                        href = anchor.get("href", "/")
-                        if href != "/":
-                            try:
-                                u = urlparse(url)
-                                o = urlparse(href)
-                            except Exception as err:
-                                self._logger.error("parsing error : {0}".format(err))
-                                exit(1)
-                            if o.netloc == "":
-                                o = o._replace(netloc=u.netloc)
-                                o = o._replace(scheme=u.scheme)
-                            page_url.append(o.geturl())        
-        return page_url
+    # Public method
 
-    def _getImg(self, webpage):
-        page_img = []
-        for i in webpage:
-            try:
-                page = requests.get(i)
-            except Exception as err:
-                self._logger.error("Connection error : {0}".format(err))
-                exit(1)
-            if page.status_code == 200:
-                soup = BeautifulSoup(page.text, self._parser)
-                img = soup.find_all("img")
-                self._logger.info("image from page: {0} : ".format(i))
-                for anchor in img:
-                    src = anchor.get("src", "/")
-                    if src != "/":
-                        if src not in page_img:
-                            self._logger.info("image: {0} : ".format(src))
-                            page_img.append(src)
-        return page_img
+    # Download JS
 
-    def _getUrlPage(self):
+    def downloadJs(self):
+        script = self._getScriptCss(True, False)
+        o = urlparse(self._url)
+        self._downloadPage(script, "{0}/{1}/{2}".format(self._dir, o.path, "dists/js"))
+
+    # Download CSS
+
+    def downloadCss(self):
+        css = self._getScriptCss(False, True)
+        o = urlparse(self._url)
+        self._downloadPage(script, "{0}/{1}/{2}".format(self._dir, o.path, "dists/css"))
+
+    # Download HTML
+
+    def downloadHTML(self, webpage):
+        self._downloadPage(webpage, self._dir)
+
+    # Download Image
+    
+    def downloadImg(self, webpage):
+        page_src = self._getImg(webpage)
+        o = urlparse(self._url)
+        self._downloadPage(page_src, "{0}/{1}/{2}".format(self._dir, o.path, "img"))
+
+
+     # Get URL
+    def getUrlPage(self):
         try:
             page = requests.get(self._url)
         except Exception as err:
@@ -151,6 +102,95 @@ class WPExport:
         return webpage
 
 
+    # Private method
+    # 
+    # Create path        
+    def _mkdirPath(self, path_dir, logger):
+        if not os.path.exists(path_dir):
+            makedir = []
+            pathh = path_dir.split("/")
+            for i in pathh:
+                makedir.append(i)
+                repath = "/".join(makedir)
+                if not os.path.exists(repath):
+                    self._logger.debug("Dossier crée : {0}".format(repath))
+                    try:
+                        if len(repath) > 0:
+                            os.mkdir(repath)
+                    except Exception as err:
+                        self._logger.error("Directory error : {0}".format(err))
+                        self._logger.debug("Directory error : {0} {1} {2} {3} {4}".format(err, path_dir, repath, pathh, makedir))
+                        exit(1)
+
+
+    # Get Css and JS
+    def _getScriptCss(self, js, css):
+        try:
+            page = requests.get(url)
+        except Exception as err:
+            self._logger.error("Connection error : {0}".format(err))
+            exit(1)
+        page_url = []
+        if page.status_code == 200:
+            soup = BeautifulSoup(page.text, self._parser)
+            if js is True:
+                script = soup.find_all("script")
+                for anchor in script:
+                    src = anchor.get("src", "/")
+                    if src != "/":
+                        try:
+                            u = urlparse(url)
+                            o = urlparse(src)
+                        except Exception as err:
+                            self._logger.error("parsing error : {0}".format(err))
+                            exit(1)
+                        if o.netloc == "":
+                            o = o._replace(netloc=u.netloc)
+                            o = o._replace(scheme=u.scheme)
+                        page_url.append(o.geturl())
+            if css is True:
+                link = soup.find_all("link")
+                for anchor in link:
+                    rel = anchor.get("rel")
+                    if rel[0] == "stylesheet":
+                        href = anchor.get("href", "/")
+                        if href != "/":
+                            try:
+                                u = urlparse(url)
+                                o = urlparse(href)
+                            except Exception as err:
+                                self._logger.error("parsing error : {0}".format(err))
+                                exit(1)
+                            if o.netloc == "":
+                                o = o._replace(netloc=u.netloc)
+                                o = o._replace(scheme=u.scheme)
+                            page_url.append(o.geturl())        
+        return page_url
+
+    # Get image
+
+    def _getImg(self, webpage):
+        page_img = []
+        for i in webpage:
+            try:
+                page = requests.get(i)
+            except Exception as err:
+                self._logger.error("Connection error : {0}".format(err))
+                exit(1)
+            if page.status_code == 200:
+                soup = BeautifulSoup(page.text, self._parser)
+                img = soup.find_all("img")
+                self._logger.info("image from page: {0} : ".format(i))
+                for anchor in img:
+                    src = anchor.get("src", "/")
+                    if src != "/":
+                        if src not in page_img:
+                            self._logger.info("image: {0} : ".format(src))
+                            page_img.append(src)
+        return page_img
+
+
+    # Download page
     def _downloadPage(self, webpage, backup_dir):
    
         for i in range(0, len(webpage)):
@@ -178,66 +218,4 @@ class WPExport:
                     open(fileDownload, "wb").write(r.content)
                 except Exception as err:
                     self._logger.error("file error : {0}".format(err))
-                    exit(1)
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--url", help="canblog URL to be scraping", required=True)
-    parser.add_argument("--dir",
-                      default="backup",
-                      help="backup file path")
-    parser.add_argument("--debug", help="Verbosity",  action="store_true")
-    parser.add_argument("--logfile", help="Log file",  default="")
-    parser.add_argument("--no-css", help="No CSS", dest="css",  action="store_true")
-    parser.add_argument("--no-js", help="No JS", dest="js",  action="store_true")
-    parser.add_argument("--no-img", help="No img", dest="img",  action="store_true")
-    parser.add_argument("--no-html", help="No HTML", dest="html", action="store_true")
-    parser.add_argument("--quiet", help="No console output", action="store_true")
-    args = parser.parse_args()
-    logger = logging.getLogger('web_scrap')
-    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-
-    if args.quiet is False:
-        ch = logging.StreamHandler()
-        if args.debug is True:
-            logger.setLevel(logging.DEBUG)
-            ch.setLevel(logging.DEBUG)
-        else:
-            logger.setLevel(logging.INFO)
-            ch.setLevel(logging.INFO)
-        ch.setFormatter(formatter)
-        logger.addHandler(ch)
-
-
-    if len(args.logfile) > 0:
-        fileHandler = logging.FileHandler(args.logfile)
-        if args.debug is True:
-            fileHandler.setLevel(logging.DEBUG)
-        else:
-            fileHandler.setLevel(logging.INFO)
-        fileHandler.setFormatter(formatter)
-        logger.addHandler(fileHandler)
-    
-    try:
-        o = urlparse(args.url)
-        o = o._replace(scheme="https")
-        url = o.geturl().replace(":///", "://")
-    except Exception as err:
-        logger.error("parsing error : {0}".format(err))
-    if args.js is False:
-        script = getScriptCss(url, True, False, logger)
-        downloadPage(script, "{0}/{1}/{2}".format(args.dir, o.path, "dists/js"), logger)
-    
-    if args.css is False:
-        css = getScriptCss(url, False, True, logger)
-        downloadPage(css, "{0}/{1}/{2}".format(args.dir, o.path, "dists/css"), logger)
-    
-    if args.html is False or args.img is False:
-        webpage = getUrlPage(url, logger)
-    if args.html is False:
-        downloadPage(webpage, args.dir, logger)
-    
-    if args.img is False:
-        page_src = getImg(webpage, logger)
-        downloadPage(page_src, "{0}/{1}/{2}".format(args.dir, o.path, "img"), logger)
+                    exit(1)
\ No newline at end of file
diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index cc19a06..b38d5be 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -18,6 +18,7 @@ if __name__ == '__main__':
     import_parser.add_argument("--user", help="wordpress user", required=True)
     import_parser.add_argument("--file", help="HTML file", default="")
     import_parser.add_argument("--directory", help="HTML directory", default="")
+    import_parser.add_argument("--canalblog", help="URL Canalblog", default="")
     import_parser.add_argument("--wordpress", help="URL Wordpress", required=True)
 
     export_parser = subparsers.add_parser("export")
@@ -59,7 +60,7 @@ if __name__ == '__main__':
         fileHandler.setFormatter(formatter)
         logger.addHandler(fileHandler)
 
-    if args.command == "export":
+    if args.command == "import":
         password = getpass()
         if len(password) == 0:
             logger.error("No password error !!! ")
@@ -71,4 +72,27 @@ if __name__ == '__main__':
             importWp.fromFile(args.file.split(","))
             exit(0)
         if len(args.directory) > 0:
-            importWp.fromDirectory(args.directory)
\ No newline at end of file
+            importWp.fromDirectory(args.directory)
+        exit(0)
+    if args.command == "export":
+        try:
+            o = urlparse(args.url)
+            o = o._replace(scheme="https")
+            url = o.geturl().replace(":///", "://")
+        except Exception as err:
+            logger.error("parsing error : {0}".format(err))
+            exit(1)
+        exportWp = WPExport.WPExport(url, logger, args.parser, args.dir)
+        if args.js is False:
+            exportWp.downloadJs()
+    
+        if args.css is False:
+            exportWp.downloadCss()
+    
+        if args.html is False or args.img is False:
+            webpage = exportWp.getUrlPage()
+        if args.html is False:
+            exportWp.downloadHTML(webpage)
+    
+        if args.img is False:
+            exportWp.downloadImg(webpage)
\ No newline at end of file

From 19c62f38d40b3d92e9ece6e6af5b380fe17c0bdf Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 9 Apr 2023 22:50:41 +0200
Subject: [PATCH 48/60] add exit

---
 import_export_canalblog.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index b38d5be..edce4ab 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -95,4 +95,5 @@ if __name__ == '__main__':
             exportWp.downloadHTML(webpage)
     
         if args.img is False:
-            exportWp.downloadImg(webpage)
\ No newline at end of file
+            exportWp.downloadImg(webpage)
+        exit(0)
\ No newline at end of file

From cd50e45493ae05b2846fb3fb2816524acf4c894f Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 9 Apr 2023 23:49:10 +0200
Subject: [PATCH 49/60] fix WPExport

---
 WPExport.py                | 14 +++++++-------
 import_export_canalblog.py |  5 +++--
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/WPExport.py b/WPExport.py
index 6db20ad..9657cf6 100644
--- a/WPExport.py
+++ b/WPExport.py
@@ -25,7 +25,7 @@ class WPExport:
     def downloadCss(self):
         css = self._getScriptCss(False, True)
         o = urlparse(self._url)
-        self._downloadPage(script, "{0}/{1}/{2}".format(self._dir, o.path, "dists/css"))
+        self._downloadPage(css, "{0}/{1}/{2}".format(self._dir, o.path, "dists/css"))
 
     # Download HTML
 
@@ -79,9 +79,9 @@ class WPExport:
                         for j in range(1,int(number_lastpage)):
                             paging = j * 10
                             categorie = urlparse(i).path.split("/")
-                            url_paging = "{0}/archives/p{1}-10.html".format(url, paging)
+                            url_paging = "{0}/archives/p{1}-10.html".format(self._url, paging)
                             if len(categorie) > 2:
-                                url_paging = "{0}/archives/{1}/p{2}-10.html".format(url, categorie[2], paging)
+                                url_paging = "{0}/archives/{1}/p{2}-10.html".format(self._url, categorie[2], paging)
                             self._logger.info(url_paging)
                             if url_paging not in webpage:
                                 webpage.append(url_paging)
@@ -105,7 +105,7 @@ class WPExport:
     # Private method
     # 
     # Create path        
-    def _mkdirPath(self, path_dir, logger):
+    def _mkdirPath(self, path_dir):
         if not os.path.exists(path_dir):
             makedir = []
             pathh = path_dir.split("/")
@@ -126,7 +126,7 @@ class WPExport:
     # Get Css and JS
     def _getScriptCss(self, js, css):
         try:
-            page = requests.get(url)
+            page = requests.get(self._url)
         except Exception as err:
             self._logger.error("Connection error : {0}".format(err))
             exit(1)
@@ -139,7 +139,7 @@ class WPExport:
                     src = anchor.get("src", "/")
                     if src != "/":
                         try:
-                            u = urlparse(url)
+                            u = urlparse(self._url)
                             o = urlparse(src)
                         except Exception as err:
                             self._logger.error("parsing error : {0}".format(err))
@@ -156,7 +156,7 @@ class WPExport:
                         href = anchor.get("href", "/")
                         if href != "/":
                             try:
-                                u = urlparse(url)
+                                u = urlparse(self._url)
                                 o = urlparse(href)
                             except Exception as err:
                                 self._logger.error("parsing error : {0}".format(err))
diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index edce4ab..6b8325d 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -1,8 +1,9 @@
 #!/usr/bin/python3
 from requests.auth import HTTPBasicAuth
 from getpass import getpass
+from urllib.parse import urlparse
 import argparse, logging
-import WPImport
+import WPImport, WPExport
 
 
 if __name__ == '__main__':
@@ -82,7 +83,7 @@ if __name__ == '__main__':
         except Exception as err:
             logger.error("parsing error : {0}".format(err))
             exit(1)
-        exportWp = WPExport.WPExport(url, logger, args.parser, args.dir)
+        exportWp = WPExport.WPExport(url, logger, args.parser, args.directory)
         if args.js is False:
             exportWp.downloadJs()
     

From e74dfc2b73438eebaf64385409805344ec40793a Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 10 Apr 2023 00:00:01 +0200
Subject: [PATCH 50/60] add import from url

---
 WPImport.py                | 12 ++++++++++++
 import_export_canalblog.py | 17 +++++++++++++++--
 2 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/WPImport.py b/WPImport.py
index 92f6681..d17adce 100644
--- a/WPImport.py
+++ b/WPImport.py
@@ -14,6 +14,18 @@ class WPimport:
 
     # Public method
 
+    def fromUrl(self, webpage):
+        for page in webpage:
+            r = requests.get(page)
+            if r.status_code == 200:
+                soup = BeautifulSoup(r.content, self._parser)
+                articlebody = soup.find_all("div", class_="articlebody")
+                if len(articlebody) > 0:
+                    self._addOrUpdatePost(soup)
+                else:
+                    self._addOrUpdateFeaturedMedia(soup)
+
+
     def fromDirectory(self, directory):
         directory = "{0}/archives".format(directory)
         directories = self._getDirectories([], "{0}".format(directory))
diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 6b8325d..96314ec 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -37,7 +37,7 @@ if __name__ == '__main__':
 
     args = parser.parse_args()
 
-    logger = logging.getLogger('insert wordpress')
+    logger = logging.getLogger('import export canalblog')
     formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
 
     if args.quiet is False:
@@ -74,7 +74,20 @@ if __name__ == '__main__':
             exit(0)
         if len(args.directory) > 0:
             importWp.fromDirectory(args.directory)
-        exit(0)
+            exit(0)
+        if len(args.canalblog) > 0:
+            try:
+                o = urlparse(args.canalblog)
+                o = o._replace(scheme="https")
+                url = o.geturl().replace(":///", "://")
+            except Exception as err:
+                logger.error("parsing error : {0}".format(err))
+                exit(1)
+            exportWp = WPExport.WPExport(url, logger, args.parser, args.directory)
+            webpage = exportWp.getUrlPage()
+            importWp.fromUrl(webpage)
+
+
     if args.command == "export":
         try:
             o = urlparse(args.url)

From ed78f22f2e920c1fdbda967a93f817a7bc5781e9 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 10 Apr 2023 11:05:32 +0200
Subject: [PATCH 51/60] fix WPImport from URL

---
 WPImport.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/WPImport.py b/WPImport.py
index d17adce..bb41e9c 100644
--- a/WPImport.py
+++ b/WPImport.py
@@ -15,9 +15,10 @@ class WPimport:
     # Public method
 
     def fromUrl(self, webpage):
-        for page in webpage:
-            r = requests.get(page)
+        for i in range(0, len(webpage)):
+            r = requests.get(webpage[i])
             if r.status_code == 200:
+                self._logger.info("({0}/{1} : Page en cours d'import : {2}".format(i+1, len(webpage), webpage[i]))
                 soup = BeautifulSoup(r.content, self._parser)
                 articlebody = soup.find_all("div", class_="articlebody")
                 if len(articlebody) > 0:

From 4ddc4a7cd3358774af22942fdb38ece0e0c11f23 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 10 Apr 2023 15:41:14 +0200
Subject: [PATCH 52/60] rm web_scrap + add set url + add backup1 to gitignore

---
 .gitignore   |   1 +
 WPExport.py  |   5 ++
 WPImport.py  |   3 +
 web_scrap.py | 241 ---------------------------------------------------
 4 files changed, 9 insertions(+), 241 deletions(-)
 delete mode 100644 web_scrap.py

diff --git a/.gitignore b/.gitignore
index d9171fe..6280820 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,2 +1,3 @@
 backup/
+backup1/
 web_scrap.log
diff --git a/WPExport.py b/WPExport.py
index 9657cf6..c5b6be9 100644
--- a/WPExport.py
+++ b/WPExport.py
@@ -13,6 +13,11 @@ class WPExport:
 
     # Public method
 
+    # Set URL
+
+    def setUrl(self, url):
+        self._url = url
+
     # Download JS
 
     def downloadJs(self):
diff --git a/WPImport.py b/WPImport.py
index bb41e9c..339a8c0 100644
--- a/WPImport.py
+++ b/WPImport.py
@@ -14,6 +14,9 @@ class WPimport:
 
     # Public method
 
+    def setUrl(self, wordpress):
+        self._wordpress = wordpress
+
     def fromUrl(self, webpage):
         for i in range(0, len(webpage)):
             r = requests.get(webpage[i])
diff --git a/web_scrap.py b/web_scrap.py
deleted file mode 100644
index adf2988..0000000
--- a/web_scrap.py
+++ /dev/null
@@ -1,241 +0,0 @@
-#!/usr/bin/python3
-from bs4 import BeautifulSoup
-from urllib.parse import urlparse
-import requests, os, argparse, logging
-
-def mkdirPath(path_dir, logger):
-    if not os.path.exists(path_dir):
-        makedir = []
-        pathh = path_dir.split("/")
-        for i in pathh:
-            makedir.append(i)
-            repath = "/".join(makedir)
-            if not os.path.exists(repath):
-                logger.debug("Dossier crée : {0}".format(repath))
-                try:
-                    if len(repath) > 0:
-                        os.mkdir(repath)
-                except Exception as err:
-                    logger.error("Directory error : {0}".format(err))
-                    logger.debug("Directory error : {0} {1} {2} {3} {4}".format(err, path_dir, repath, pathh, makedir))
-                    exit(1)
-
-
-def getScriptCss(url, js, css, logger):
-    try:
-        page = requests.get(url)
-    except Exception as err:
-        logger.error("Connection error : {0}".format(err))
-        exit(1)
-    page_url = []
-    if page.status_code == 200:
-        soup = BeautifulSoup(page.text, 'html.parser')
-        if js is True:
-            script = soup.find_all("script")
-            for anchor in script:
-                src = anchor.get("src", "/")
-                if src != "/":
-                    try:
-                        u = urlparse(url)
-                        o = urlparse(src)
-                    except Exception as err:
-                        logger.error("parsing error : {0}".format(err))
-                        exit(1)
-                    if o.netloc == "":
-                        o = o._replace(netloc=u.netloc)
-                        o = o._replace(scheme=u.scheme)
-                    page_url.append(o.geturl())
-        if css is True:
-            link = soup.find_all("link")
-            for anchor in link:
-                rel = anchor.get("rel")
-                if rel[0] == "stylesheet":
-                    href = anchor.get("href", "/")
-                    if href != "/":
-                        try:
-                            u = urlparse(url)
-                            o = urlparse(href)
-                        except Exception as err:
-                            logger.error("parsing error : {0}".format(err))
-                            exit(1)
-                        if o.netloc == "":
-                            o = o._replace(netloc=u.netloc)
-                            o = o._replace(scheme=u.scheme)
-                        page_url.append(o.geturl())
-                
-                
-    return page_url
-
-def getImg(webpage, logger):
-    page_img = []
-    for i in webpage:
-        try:
-            page = requests.get(i)
-        except Exception as err:
-            logger.error("Connection error : {0}".format(err))
-            exit(1)
-        if page.status_code == 200:
-            soup = BeautifulSoup(page.text, 'html.parser')
-            img = soup.find_all("img")
-            logger.info("image from page: {0} : ".format(i))
-            for anchor in img:
-                src = anchor.get("src", "/")
-                if src != "/":
-                    if src not in page_img:
-                        logger.info("image: {0} : ".format(src))
-                        page_img.append(src)
-
-
-    return page_img
-
-def getUrlPage(url, logger):
-    try:
-        page = requests.get(url)
-    except Exception as err:
-            logger.error("Connection error : {0}".format(err))
-            exit(1)
-    page_url = []
-    if page.status_code == 200:
-        soup = BeautifulSoup(page.text, 'html.parser')
-        ul = soup.find_all("ul", id="listsmooth")
-        for anchor in ul[0].find_all("a"):
-            href = anchor.get('href', '/')
-            if href != "#":
-                page_url.append(href)
-
-    webpage = []
-    for i in page_url:
-        try:
-            page = requests.get(i)
-        except Exception as err:
-            logger.error("Connection error : {0}".format(err))
-            exit(1)
-        if page.status_code == 200:
-            logger.info("page : {0}".format(i))
-            if i not in webpage:
-                webpage.append(i)
-            soup = BeautifulSoup(page.text, 'html.parser')
-            class_div = pagingfirstline = soup.find_all("div", class_="pagingfirstline")
-            if len(class_div) > 0:
-                pagingfirstline = class_div[0].find_all("a")
-                if len(pagingfirstline) > 1:
-                    lastpage = pagingfirstline[len(pagingfirstline)-1].get("href", "/")
-                    element_lastpage = lastpage.split("/")[len(lastpage.split("/"))-1]
-                    number_page = element_lastpage.split("-")[0].split("p")[1]
-                    number_lastpage = int(number_page) / 10
-                    for j in range(1,int(number_lastpage)):
-                        paging = j * 10
-                        categorie = urlparse(i).path.split("/")
-                        url_paging = "{0}/archives/p{1}-10.html".format(url, paging)
-                        if len(categorie) > 2:
-                            url_paging = "{0}/archives/{1}/p{2}-10.html".format(url, categorie[2], paging)
-                        logger.info(url_paging)
-                        if url_paging not in webpage:
-                            webpage.append(url_paging)
-                        page = requests.get(url_paging)
-                        if page.status_code == 200:
-                            soup = BeautifulSoup(page.text, 'html.parser')
-                            h2 = soup.find_all("h2")
-                            for title in h2:
-                                href = title.find_all("a")[0].get("href", "/")
-                                if href not in webpage:
-                                    try:
-                                        o = urlparse(href)
-                                        o = o._replace(scheme="https").geturl()
-                                    except Exception as err:
-                                        logger.error("parsing error : {0}".format(err))
-                                        exit(1)
-                                    webpage.append(o)
-    return webpage
-
-
-def downloadPage(webpage, backup_dir, logger):
-   
-    for i in range(0, len(webpage)):
-        try:
-            o = urlparse(webpage[i])
-        except Exception as err:
-            logger.error("parsing error : {0}".format(err))
-            exit(1)
-        path_web = o.path.split("/")
-        filePageWeb = path_web[len(path_web)-1]
-        path_web.pop(len(path_web)-1)
-        dir_page_web = "/".join(path_web)
-        mkdirPath("{0}/{1}/{2}".format(backup_dir, o.netloc, dir_page_web), logger)
-        try:
-            r = requests.get(webpage[i])
-        except Exception as err:
-            logger.error("Connection error : {0}".format(err))
-            exit(1)
-        if r.status_code == 200:
-            fileDownload = "{0}/{1}/index.html".format(backup_dir, o.netloc)
-            if len(dir_page_web) > 0 and len(filePageWeb) > 0:
-                fileDownload = "{0}/{1}{2}/{3}".format(backup_dir, o.netloc, dir_page_web, filePageWeb)
-            logger.info("{0}/{1} : {2}".format(i+1, len(webpage), fileDownload))
-            try:
-                open(fileDownload, "wb").write(r.content)
-            except Exception as err:
-                logger.error("file error : {0}".format(err))
-                exit(1)
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--url", help="canblog URL to be scraping", required=True)
-    parser.add_argument("--dir",
-                      default="backup",
-                      help="backup file path")
-    parser.add_argument("--debug", help="Verbosity",  action="store_true")
-    parser.add_argument("--logfile", help="Log file",  default="")
-    parser.add_argument("--no-css", help="No CSS", dest="css",  action="store_true")
-    parser.add_argument("--no-js", help="No JS", dest="js",  action="store_true")
-    parser.add_argument("--no-img", help="No img", dest="img",  action="store_true")
-    parser.add_argument("--no-html", help="No HTML", dest="html", action="store_true")
-    parser.add_argument("--quiet", help="No console output", action="store_true")
-    args = parser.parse_args()
-    logger = logging.getLogger('web_scrap')
-    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-
-    if args.quiet is False:
-        ch = logging.StreamHandler()
-        if args.debug is True:
-            logger.setLevel(logging.DEBUG)
-            ch.setLevel(logging.DEBUG)
-        else:
-            logger.setLevel(logging.INFO)
-            ch.setLevel(logging.INFO)
-        ch.setFormatter(formatter)
-        logger.addHandler(ch)
-
-
-    if len(args.logfile) > 0:
-        fileHandler = logging.FileHandler(args.logfile)
-        if args.debug is True:
-            fileHandler.setLevel(logging.DEBUG)
-        else:
-            fileHandler.setLevel(logging.INFO)
-        fileHandler.setFormatter(formatter)
-        logger.addHandler(fileHandler)
-    
-    try:
-        o = urlparse(args.url)
-        o = o._replace(scheme="https")
-        url = o.geturl().replace(":///", "://")
-    except Exception as err:
-        logger.error("parsing error : {0}".format(err))
-    if args.js is False:
-        script = getScriptCss(url, True, False, logger)
-        downloadPage(script, "{0}/{1}/{2}".format(args.dir, o.path, "dists/js"), logger)
-    
-    if args.css is False:
-        css = getScriptCss(url, False, True, logger)
-        downloadPage(css, "{0}/{1}/{2}".format(args.dir, o.path, "dists/css"), logger)
-    
-    if args.html is False or args.img is False:
-        webpage = getUrlPage(url, logger)
-    if args.html is False:
-        downloadPage(webpage, args.dir, logger)
-    
-    if args.img is False:
-        page_src = getImg(webpage, logger)
-        downloadPage(page_src, "{0}/{1}/{2}".format(args.dir, o.path, "img"), logger)

From aa5c8893ec8051344ea5d5fa162bf99115e93299 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 10 Apr 2023 16:02:40 +0200
Subject: [PATCH 53/60] loop for url

---
 import_export_canalblog.py | 56 +++++++++++++++++++++-----------------
 1 file changed, 31 insertions(+), 25 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 96314ec..817c905 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -76,38 +76,44 @@ if __name__ == '__main__':
             importWp.fromDirectory(args.directory)
             exit(0)
         if len(args.canalblog) > 0:
+            exportWp = WPExport.WPExport("", logger, args.parser, args.directory)
+            canalblog = args.canalblog.split(",")
+            for canal in canalblog:
+                try:
+                    o = urlparse(canal)
+                    o = o._replace(scheme="https")
+                    url = o.geturl().replace(":///", "://")
+                except Exception as err:
+                    logger.error("parsing error : {0}".format(err))
+                    exit(1)
+                exportWp.setUrl(url)
+                webpage = exportWp.getUrlPage()
+                importWp.fromUrl(webpage)
+
+
+    if args.command == "export":
+        canalblog = args.url.split(",")
+        exportWp = WPExport.WPExport("", logger, args.parser, args.directory)
+        for canal in canalblog:
             try:
-                o = urlparse(args.canalblog)
+                o = urlparse(canal)
                 o = o._replace(scheme="https")
                 url = o.geturl().replace(":///", "://")
             except Exception as err:
                 logger.error("parsing error : {0}".format(err))
                 exit(1)
-            exportWp = WPExport.WPExport(url, logger, args.parser, args.directory)
-            webpage = exportWp.getUrlPage()
-            importWp.fromUrl(webpage)
-
-
-    if args.command == "export":
-        try:
-            o = urlparse(args.url)
-            o = o._replace(scheme="https")
-            url = o.geturl().replace(":///", "://")
-        except Exception as err:
-            logger.error("parsing error : {0}".format(err))
-            exit(1)
-        exportWp = WPExport.WPExport(url, logger, args.parser, args.directory)
-        if args.js is False:
-            exportWp.downloadJs()
+            exportWp.setUrl(url)
+            if args.js is False:
+                exportWp.downloadJs()
     
-        if args.css is False:
-            exportWp.downloadCss()
+            if args.css is False:
+                exportWp.downloadCss()
     
-        if args.html is False or args.img is False:
-            webpage = exportWp.getUrlPage()
-        if args.html is False:
-            exportWp.downloadHTML(webpage)
+            if args.html is False or args.img is False:
+                webpage = exportWp.getUrlPage()
+            if args.html is False:
+                exportWp.downloadHTML(webpage)
     
-        if args.img is False:
-            exportWp.downloadImg(webpage)
+            if args.img is False:
+                exportWp.downloadImg(webpage)
         exit(0)
\ No newline at end of file

From 48e77084e83e4e703678227bbfb30a88b0fa0b39 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 10 Apr 2023 16:07:14 +0200
Subject: [PATCH 54/60] remove newline

---
 WPImport.py | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/WPImport.py b/WPImport.py
index 339a8c0..9e2cec6 100644
--- a/WPImport.py
+++ b/WPImport.py
@@ -278,8 +278,4 @@ class WPimport:
                     page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, data=data)
                     if page.status_code == 201:
                         self._logger.info("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
-                self._linkImgPost(result["title"]["raw"], list_img, result["id"])
-
-
-
-    
+                self._linkImgPost(result["title"]["raw"], list_img, result["id"])
\ No newline at end of file

From 7c75116c5b9a8cb6725a581b18db3b0b9d02eacc Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 10 Apr 2023 16:15:13 +0200
Subject: [PATCH 55/60] add url list

---
 import_export_canalblog.py | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 817c905..3a6c748 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -68,12 +68,17 @@ if __name__ == '__main__':
             exit(1)
 
         basic = HTTPBasicAuth(args.user, password)
-        importWp = WPImport.WPimport(basic, args.wordpress, logger, args.parser)
+        wordpress = args.wordpress.split(",")
+        importWp = WPImport.WPimport(basic, "", logger, args.parser)
         if len(args.file) > 0:
-            importWp.fromFile(args.file.split(","))
+            for i in wordpress:
+                importWp.setUrl(i)
+                importWp.fromFile(args.file.split(","))
             exit(0)
         if len(args.directory) > 0:
-            importWp.fromDirectory(args.directory)
+            for i in wordpress:
+                importWp.setUrl(i)
+                importWp.fromDirectory(args.directory)
             exit(0)
         if len(args.canalblog) > 0:
             exportWp = WPExport.WPExport("", logger, args.parser, args.directory)

From 05a3a28c6fd12724985b1c24cde625d6e18cd21d Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 10 Apr 2023 16:36:49 +0200
Subject: [PATCH 56/60] add serial for url

---
 import_export_canalblog.py | 60 +++++++++++++++++++++++++++++---------
 1 file changed, 47 insertions(+), 13 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 3a6c748..785fbfd 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -21,6 +21,8 @@ if __name__ == '__main__':
     import_parser.add_argument("--directory", help="HTML directory", default="")
     import_parser.add_argument("--canalblog", help="URL Canalblog", default="")
     import_parser.add_argument("--wordpress", help="URL Wordpress", required=True)
+    import_parser.add_argument("--serial", help="Serial execution", action="store_true")
+
 
     export_parser = subparsers.add_parser("export")
 
@@ -76,24 +78,56 @@ if __name__ == '__main__':
                 importWp.fromFile(args.file.split(","))
             exit(0)
         if len(args.directory) > 0:
-            for i in wordpress:
-                importWp.setUrl(i)
-                importWp.fromDirectory(args.directory)
+            directory = args.directory.split(",")
+            if args.serial is False:
+                for i in wordpress:
+                    importWp.setUrl(i)
+                    for j in directory:
+                        importWp.fromDirectory(j)
+            else:
+                if len(directory) != len(wordpress):
+                    logger.error("ERREUR : Le nombre de dossier n'est pas equivalent au nombre d'URL wordpress")
+                    exit(1)
+                for i in range(0, len(wordpress)-1):
+                    importWp.setUrl(wordpress[i])
+                    importWp.fromDirectory(directory[i])
             exit(0)
         if len(args.canalblog) > 0:
             exportWp = WPExport.WPExport("", logger, args.parser, args.directory)
             canalblog = args.canalblog.split(",")
-            for canal in canalblog:
-                try:
-                    o = urlparse(canal)
-                    o = o._replace(scheme="https")
-                    url = o.geturl().replace(":///", "://")
-                except Exception as err:
-                    logger.error("parsing error : {0}".format(err))
+            wordpress = args.wordpress.split(",")
+
+            if serial is False:
+                for canal in canalblog:
+                    try:
+                        o = urlparse(canal)
+                        o = o._replace(scheme="https")
+                        url = o.geturl().replace(":///", "://")
+                    except Exception as err:
+                        logger.error("parsing error : {0}".format(err))
+                        exit(1)
+                    exportWp.setUrl(url)
+                    webpage = exportWp.getUrlPage()
+                    for j in wordpress:
+                        importWp.setUrl(j)
+                        importWp.fromUrl(webpage)
+            else:
+                if len(canalblog) != len(wordpress):
+                    logger.error("ERREUR : Le nombre de dossier n'est pas equivalent au nombre d'URL wordpress")
                     exit(1)
-                exportWp.setUrl(url)
-                webpage = exportWp.getUrlPage()
-                importWp.fromUrl(webpage)
+                for i in range(0, len(canalblog)-1):
+                    try:
+                        o = urlparse(canalblog[i])
+                        o = o._replace(scheme="https")
+                        url = o.geturl().replace(":///", "://")
+                    except Exception as err:
+                        logger.error("parsing error : {0}".format(err))
+                        exit(1)
+                    exportWp.setUrl(url)
+                    webpage = exportWp.getUrlPage()
+                    importWp.setUrl(wordpress[i])
+                    importWp.fromUrl(webpage)
+
 
 
     if args.command == "export":

From 7848968fa133f583d40fe523a9e2e8d2fa9312a5 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 11 Apr 2023 22:15:36 +0200
Subject: [PATCH 57/60] Organisation class in a folder

---
 .gitignore                     |  1 +
 import_export_canalblog.py     | 11 ++++++-----
 WPExport.py => lib/WPExport.py |  0
 WPImport.py => lib/WPImport.py |  0
 lib/__init__.py                |  0
 5 files changed, 7 insertions(+), 5 deletions(-)
 rename WPExport.py => lib/WPExport.py (100%)
 rename WPImport.py => lib/WPImport.py (100%)
 create mode 100644 lib/__init__.py

diff --git a/.gitignore b/.gitignore
index 6280820..1dfd775 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,4 @@
 backup/
 backup1/
 web_scrap.log
+__pycache__/
diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 785fbfd..6470699 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -3,7 +3,8 @@ from requests.auth import HTTPBasicAuth
 from getpass import getpass
 from urllib.parse import urlparse
 import argparse, logging
-import WPImport, WPExport
+from lib.WPImport import WPimport
+from lib.WPExport import WPExport
 
 
 if __name__ == '__main__':
@@ -71,7 +72,7 @@ if __name__ == '__main__':
 
         basic = HTTPBasicAuth(args.user, password)
         wordpress = args.wordpress.split(",")
-        importWp = WPImport.WPimport(basic, "", logger, args.parser)
+        importWp = WPimport(basic, "", logger, args.parser)
         if len(args.file) > 0:
             for i in wordpress:
                 importWp.setUrl(i)
@@ -93,11 +94,11 @@ if __name__ == '__main__':
                     importWp.fromDirectory(directory[i])
             exit(0)
         if len(args.canalblog) > 0:
-            exportWp = WPExport.WPExport("", logger, args.parser, args.directory)
+            exportWp = WPExport("", logger, args.parser, args.directory)
             canalblog = args.canalblog.split(",")
             wordpress = args.wordpress.split(",")
 
-            if serial is False:
+            if args.serial is False:
                 for canal in canalblog:
                     try:
                         o = urlparse(canal)
@@ -132,7 +133,7 @@ if __name__ == '__main__':
 
     if args.command == "export":
         canalblog = args.url.split(",")
-        exportWp = WPExport.WPExport("", logger, args.parser, args.directory)
+        exportWp = WPExport("", logger, args.parser, args.directory)
         for canal in canalblog:
             try:
                 o = urlparse(canal)
diff --git a/WPExport.py b/lib/WPExport.py
similarity index 100%
rename from WPExport.py
rename to lib/WPExport.py
diff --git a/WPImport.py b/lib/WPImport.py
similarity index 100%
rename from WPImport.py
rename to lib/WPImport.py
diff --git a/lib/__init__.py b/lib/__init__.py
new file mode 100644
index 0000000..e69de29

From a856311f044ce6ab3fd69d887ffdb6540373c25b Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 11 Apr 2023 22:30:00 +0200
Subject: [PATCH 58/60] add method for comment

---
 lib/WPImport.py | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index 9e2cec6..f5d68cb 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -141,6 +141,15 @@ class WPimport:
                 media["id"] = res["id"]
                 media["rendered"] = res["guid"]["rendered"]
         return media
+
+    ## Add or update comment
+
+    def _addOrUpdateComment(self, post, comment):
+        for i in comment:
+            data = {"post": post, "content": i["content"], "date": i["date"], "author_name": i["author"]}
+            page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, data=data)
+            if page.status_code == 201:
+                self._logger.info("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
     
     ## Add or Update post 
 
@@ -273,9 +282,5 @@ class WPimport:
             if page.status_code == 201:
                 result = page.json()
                 self._logger.info("Article ajoute : {0}".format(result["title"]["raw"]))
-                for i in comment_post:
-                    data = {"post": result["id"], "content": i["content"], "date": i["date"], "author_name": i["author"]}
-                    page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, data=data)
-                    if page.status_code == 201:
-                        self._logger.info("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
+                self._addOrUpdateComment(result["id"], comment_post)
                 self._linkImgPost(result["title"]["raw"], list_img, result["id"])
\ No newline at end of file

From 335266e1adff73b4387a3214f99daeb730243804 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 11 Apr 2023 23:26:40 +0200
Subject: [PATCH 59/60] update comment

---
 lib/WPImport.py | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index f5d68cb..6987877 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -144,12 +144,27 @@ class WPimport:
 
     ## Add or update comment
 
-    def _addOrUpdateComment(self, post, comment):
-        for i in comment:
-            data = {"post": post, "content": i["content"], "date": i["date"], "author_name": i["author"]}
-            page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, data=data)
-            if page.status_code == 201:
-                self._logger.info("Commentaire ajoute pour {0}".format(result["title"]["raw"]))
+    def _addOrUpdateComment(self, post, comment, title):
+        params = {"post": post}
+        block = True
+        page = requests.get("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, params=params)
+        if page.status_code == 200:
+            result = page.json()
+            for i in comment:
+                comment_exist = False
+                for j in result:
+                    if i["author"] == j["author_name"] and i["date"] == j["date"]:
+                        comment_exist = True
+                        id_comment = j["id"]
+                data = {"post": post, "content": i["content"], "date": i["date"], "author_name": i["author"]}
+                if comment_exist is True:
+                    page = page = requests.post("http://{0}/wp-json/wp/v2/comments/{1}".format(self._wordpress, id_comment), auth=self._basic, data=data)
+                    if page.status_code == 200:
+                        self._logger.info("Commentaire mise à jour pour {0}".format(title))
+                else:
+                    page = requests.post("http://{0}/wp-json/wp/v2/comments".format(self._wordpress), auth=self._basic, data=data)
+                    if page.status_code == 201:
+                        self._logger.info("Commentaire ajoute pour {0}".format(title))
     
     ## Add or Update post 
 
@@ -273,6 +288,7 @@ class WPimport:
                 if page.status_code == 200:
                     result = page.json()
                     self._logger.info("Article mis à jour : {0}".format(result["title"]["raw"]))
+                    self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
                     self._linkImgPost(result["title"]["raw"], list_img, result["id"])
 
 
@@ -282,5 +298,5 @@ class WPimport:
             if page.status_code == 201:
                 result = page.json()
                 self._logger.info("Article ajoute : {0}".format(result["title"]["raw"]))
-                self._addOrUpdateComment(result["id"], comment_post)
+                self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
                 self._linkImgPost(result["title"]["raw"], list_img, result["id"])
\ No newline at end of file

From 76d27718860afaf317304b975fb4b7ac74122767 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 11 Apr 2023 23:27:41 +0200
Subject: [PATCH 60/60] remove newline useless

---
 lib/WPImport.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index 6987877..60e8cbc 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -290,9 +290,7 @@ class WPimport:
                     self._logger.info("Article mis à jour : {0}".format(result["title"]["raw"]))
                     self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
                     self._linkImgPost(result["title"]["raw"], list_img, result["id"])
-
-
-
+                    
         if page_exist == False:
             page = requests.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
             if page.status_code == 201: