From 4789fe80aa5d57719563decc3e3279b9f10a6f1e Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 2 May 2023 16:59:31 +0200
Subject: [PATCH 01/19] fix import 50%

---
 lib/WPImport.py | 152 ++++++++++++++++++++++++------------------------
 1 file changed, 77 insertions(+), 75 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index e3ed2ee..50b58b6 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -18,7 +18,7 @@ class WPimport:
 
         self._request = requests.Session()
 
-        retries = Retry(total=10,
+        retries = Retry(connect=10, read=10, redirect=5,
                 status_forcelist=[429, 500, 502, 503, 504], backoff_factor=2)
 
         self._request.mount('http://', HTTPAdapter(max_retries=retries))
@@ -26,7 +26,7 @@ class WPimport:
     
     # Destructor 
     def __del__(self):
-        self._logger.info("{0} : Import finished for {1}".format(self._name, self._wordpress))
+        print("{0} : Import finished for {1}".format(self._name, self._wordpress))
     
     # Public method
 
@@ -192,54 +192,60 @@ class WPimport:
     ## Add or update img 
 
     def _addOrUpdateMedia(self, href_img, page):
+        media_authorized = ["png", "jpg", "jpeg", "svg"]
         media = {"id":"", "rendered":""}
         split_fileimg = href_img.split("/")
         img_name = split_fileimg[len(split_fileimg)-1]
-        self._logger.debug("{0} : Search for image {1} with URL {2}".format(self._name, img_name, "http://{0}/wp-json/wp/v2/media".format(self._wordpress)))
-        params = { "search": img_name}
-        try:
-            r = self._request.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
-        except Exception as err:
-            self._logger.error("{0} : Connection error for search media : {1}".format(self._name, err))
-            exit(1)
-        self._logger.debug("{0} : Search for image {1} and his status code {2}".format(self._name, img_name, r.status_code))
-        if r.status_code == 200:
-            res = r.json()
-            if len(res) > 0:
-                params = {"force":1}
+        img_type_file = img_name.split(".")[len(img_name.split("."))-1]
+        is_img = True
+        if img_type_file not in media_authorized:
+            self._logger.error("{0} : Element {1} is not image".format(self._name,img_name))
+            is_img = False
+        if is_img is True:
+            self._logger.debug("{0} : Search for image {1} with URL {2}".format(self._name, img_name, "http://{0}/wp-json/wp/v2/media".format(self._wordpress)))
+            params = { "search": img_name}
+            try:
+                r = self._request.get("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, params=params)
+            except Exception as err:
+                self._logger.error("{0} : Connection error for search media : {1}".format(self._name, err))
+                exit(1)
+            self._logger.debug("{0} : Search for image {1} and his status code {2}".format(self._name, img_name, r.status_code))
+            if r.status_code == 200:
+                res = r.json()
+                self._logger.debug("{0} : Number of image in search : {1}".format(self._name, len(res)))
+                if len(res) > 0:
+                    params = {"force":1}
+                    try:
+                        r = self._request.delete("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, res[0]["id"]), auth=self._basic, params=params)
+                    except Exception as err:
+                        self._logger.error("{0} Connection error for delete image : {1}".format(self._name, err))
+                        exit(1)
+                    if r.status_code == 200:
+                        self._logger.info("{0} : Image removed {1}".format(self._name, img_name))
+                    else:
+                        self._logger.error("{0} : Image {1} not removed due status code : {2}".format(self._name, img_name, r.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, r.content))
+
+                data = page.content
+                img_type = "image/{0}".format(img_type_file)
+                headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
                 try:
-                    r = self._request.delete("http://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, res[0]["id"]), auth=self._basic, params=params)
+                    r = self._request.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
                 except Exception as err:
-                    self._logger.error("{0} Connection error for delete image : {1}".format(self._name, err))
+                    self._logger.error("{0} : Connection error for add image : {1}".format(self._name, err))
                     exit(1)
-                if r.status_code == 200:
-                    self._logger.info("{0} : Image removed {1}".format(self._name, img_name))
+                if r.status_code == 201:
+                    self._logger.info("{0} : Image added {1}".format(self._name, img_name))
+                    res = r.json()
+                    media["id"] = res["id"]
+                    media["rendered"] = res["guid"]["rendered"]
                 else:
-                    self._logger.error("{0} : Image not removed due status code : {1}".format(self._name, r.status_code))
+                    self._logger.error("{0} : Image {1}.{2} not added due status code : {3}".format(self._name, img_name, img_type, r.status_code))
                     self._logger.debug("{0} : {1}".format(self._name, r.content))
 
-            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)}
-            try:
-                r = self._request.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
-            except Exception as err:
-                self._logger.error("{0} : Connection error for add image : {1}".format(self._name, err))
-                exit(1)
-            if r.status_code == 201:
-                self._logger.info("{0} : Image added {1}".format(self._name, img_name))
-                res = r.json()
-                media["id"] = res["id"]
-                media["rendered"] = res["guid"]["rendered"]
             else:
-                self._logger.error("{0} : Image not added due status code : {1}".format(self._name, r.status_code))
-                self._logger.debug(r.content)
-
-        else:
-            self._logger.error("{0} : Connection error for search image with status code : {1}".format(self._name, r.status_code))
-            self._logger.debug("{0} : {1}".format(self._name, r.content))
+                self._logger.error("{0} : Connection error for search image with status code : {1}".format(self._name, r.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, r.content))
 
         return media
 
@@ -498,45 +504,41 @@ class WPimport:
         except Exception as err:
             self._logger.error("{0} : Connection error for search post : {1}".format(self._name, err))
             exit(1)
-        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:
-                self._logger.info("{0} : Page {1} already exist and going to update".format(self._name, title))
-                post_id = result[0]["id"]
-                try:
-                    page = self._request.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, data=json.dumps(data))
-                except Exception as err:
-                    self._logger.error("{0} : Connection error for update post : {1}".format(self._name, err))
-                    exit(1)
-                if page.status_code == 200:
-                    result = page.json()
-                    self._logger.info("{0} : Post updated : {1}".format(self._name, result["title"]["raw"]))
-                    self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
-                    self._linkImgPost(result["title"]["raw"], list_img, result["id"])
-                else:
-                    self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
-                    self._logger.debug("{0} : {1}".format(self._name, page.content))
-
+            if len(result) > 0:
+                for i in result:
+                    self._logger.info("{0} : Page {1} already exist and going to delete".format(self._name, title))
+                    post_id = i["id"]
+                    try:
+                        params = {"force":1}
+                        page = self._request.delete("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, params=params)
+                    except Exception as err:
+                        self._logger.error("{0} : Connection error for delete post : {1}".format(self._name, err))
+                        exit(1)
+                    if page.status_code == 200:
+                        result = page.json()
+                        self._logger.info("{0} : Post deleted : {1}".format(self._name, title))
+                    
+                    else:
+                        self._logger.error("{0} : Post not deleted due status code : {1}".format(self._name, page.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, page.content))
         else:
-            self._logger.error("{0} : Connection for update post error with status code : {1}".format(self._name, page.status_code))
+            self._logger.error("{0} : Connection for delete post error with status code : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(self._name, page.content))
 
                     
-        if page_exist == False:
-            try:
-                page = self._request.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
-            except Exception as err:
-                self._logger.error("{0} : Connection error for create post : {1}".format(self._name, err))
-                exit(1)
-            if page.status_code == 201:
-                result = page.json()
-                self._logger.info("{0} : Post added : {1}".format(self._name, result["title"]["raw"]))
-                self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
-                self._linkImgPost(result["title"]["raw"], list_img, result["id"])
-            else:
-                self._logger.error("{0} : Post not added due status code : {1}".format(self._name, r.status_code))
-                self._logger.debug("{0} : {1}".format(self._name, r.content))
+        try:
+            page = self._request.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
+        except Exception as err:
+            self._logger.error("{0} : Connection error for create post : {1}".format(self._name, err))
+            exit(1)
+        if page.status_code == 201:
+            result = page.json()
+            self._logger.info("{0} : Post added : {1}".format(self._name, result["title"]["raw"]))
+            self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
+            self._linkImgPost(result["title"]["raw"], list_img, result["id"])
+        else:
+            self._logger.error("{0} : Post not added due status code : {1}".format(self._name, r.status_code))
+            self._logger.debug("{0} : {1}".format(self._name, r.content))

From 21d2f35e6ed2a0a3b19ba3b4fe883bc4c3c4037e Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Thu, 4 May 2023 00:47:06 +0200
Subject: [PATCH 02/19] add password parameter and fix post to delete 75%

---
 import_export_canalblog.py | 12 ++++++++----
 lib/WPImport.py            | 32 ++++++++++++++++++--------------
 2 files changed, 26 insertions(+), 18 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 8250a9e..b44ab9c 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -96,6 +96,7 @@ if __name__ == '__main__':
 
     import_parser = subparsers.add_parser("import")
     import_parser.add_argument("--user", help="wordpress user", required=True)
+    import_parser.add_argument("--password", help="password wordpress's user", default="")
     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="")
@@ -103,6 +104,7 @@ if __name__ == '__main__':
     import_parser.add_argument("--serial", help="Serial execution", action="store_true")
 
 
+
     export_parser = subparsers.add_parser("export")
 
     export_parser.add_argument("--url", help="canblog URL to be scraping", required=True)
@@ -143,10 +145,12 @@ if __name__ == '__main__':
         logger.addHandler(fileHandler)
 
     if args.command == "import":
-        password = getpass()
-        if len(password) == 0:
-            logger.error("No password error !!! ")
-            exit(1)
+        password = args.password
+        if len(args.password) == 0:
+            password = getpass()
+            if len(password) == 0:
+                logger.error("No password error !!! ")
+                exit(1)
 
         basic = HTTPBasicAuth(args.user, password)
         wordpress = args.wordpress.split(",")
diff --git a/lib/WPImport.py b/lib/WPImport.py
index 50b58b6..6f82ec4 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -228,6 +228,8 @@ class WPimport:
 
                 data = page.content
                 img_type = "image/{0}".format(img_type_file)
+                if img_type_file == "jpg":
+                    img_type = "image/jpeg"
                 headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
                 try:
                     r = self._request.post("http://{0}/wp-json/wp/v2/media".format(self._wordpress), auth=self._basic, headers=headers, data=data)
@@ -509,21 +511,23 @@ class WPimport:
             result = page.json()
             if len(result) > 0:
                 for i in result:
-                    self._logger.info("{0} : Page {1} already exist and going to delete".format(self._name, title))
-                    post_id = i["id"]
-                    try:
-                        params = {"force":1}
-                        page = self._request.delete("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, params=params)
-                    except Exception as err:
-                        self._logger.error("{0} : Connection error for delete post : {1}".format(self._name, err))
-                        exit(1)
-                    if page.status_code == 200:
-                        result = page.json()
-                        self._logger.info("{0} : Post deleted : {1}".format(self._name, title))
+                    self._logger.debug("{0} : Data for post to delete : {1}".format(self._name, i))
+                    if i["title"]["rendered"] == title:
+                        self._logger.info("{0} : Page {1} already exist and going to delete".format(self._name, title))
+                        post_id = i["id"]
+                        try:
+                            params = {"force":1}
+                            page = self._request.delete("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, params=params)
+                        except Exception as err:
+                            self._logger.error("{0} : Connection error for delete post : {1}".format(self._name, err))
+                            exit(1)
+                        if page.status_code == 200:
+                            result = page.json()
+                            self._logger.info("{0} : Post deleted : {1}".format(self._name, title))
                     
-                    else:
-                        self._logger.error("{0} : Post not deleted due status code : {1}".format(self._name, page.status_code))
-                        self._logger.debug("{0} : {1}".format(self._name, page.content))
+                        else:
+                            self._logger.error("{0} : Post not deleted due status code : {1}".format(self._name, page.status_code))
+                            self._logger.debug("{0} : {1}".format(self._name, page.content))
         else:
             self._logger.error("{0} : Connection for delete post error with status code : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(self._name, page.content))

From f9be6770e3581ddb44db8cf411749a57a6560b9c Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 7 May 2023 09:26:48 +0200
Subject: [PATCH 03/19] separate article and page

---
 .gitignore                 |  2 +-
 import_export_canalblog.py | 22 ++++++++++++++--------
 lib/WPExport.py            | 20 +++++++++++---------
 3 files changed, 26 insertions(+), 18 deletions(-)

diff --git a/.gitignore b/.gitignore
index a73c961..f82fde7 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,4 +1,4 @@
 backup*/
 wp-navigation
-web_scrap.log
+*.log
 __pycache__/
diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index b44ab9c..c931a5f 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -3,23 +3,27 @@ from requests.auth import HTTPBasicAuth
 from getpass import getpass
 from urllib.parse import urlparse
 from concurrent import futures
+from concurrent.futures import as_completed, wait
 
 import argparse, logging, threading
 from lib.WPImport import WPimport
 from lib.WPExport import WPExport
 
 
+
 def download(name_thread, max_thread, url, logger, parser, directory, html, img):
-    
-    exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, directory=directory)
-    
+    exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, directory=directory)    
     webpage = exportWp.getUrlPage(name_thread, max_thread)
     if html is False:
-        exportWp.downloadHTML(webpage)
-    
-    if args.img is False:
-        exportWp.downloadImg(webpage)
-    del exportWp
+        exportWp.downloadHTML(webpage["article"])
+        exportWp.downloadHTML(webpage["page"])
+
+    if img is False:
+        exportWp.downloadImg(webpage["article"])
+        exportWp.downloadImg(webpage["page"])
+
+
+
 
 def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, basic, serial):
     canalblog = canalblog.split(",")
@@ -198,6 +202,8 @@ if __name__ == '__main__':
             if args.css is False:
                 exportWp.downloadCss()
             del exportWp
+
+
     
             if args.html is False or args.img is False:
                 try:
diff --git a/lib/WPExport.py b/lib/WPExport.py
index 3bc4b6d..b817837 100644
--- a/lib/WPExport.py
+++ b/lib/WPExport.py
@@ -13,6 +13,7 @@ class WPExport:
         self._dir = directory
         self._name = name
 
+        
         self._request = requests.Session()
 
         retries = Retry(total=10,
@@ -27,6 +28,7 @@ class WPExport:
 
     # Public method
 
+
     # Set name
 
     def setName(self, name):
@@ -83,8 +85,8 @@ class WPExport:
             self._logger.error("{0} : URL did not get due status code : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(self._name, page.content))
 
+        webpage = {"page":[], "article":[]}
 
-        webpage = []
         for i in page_url:
             try:
                 page = self._request.get(i)
@@ -93,8 +95,8 @@ class WPExport:
                 exit(1)
             if page.status_code == 200:
                 self._logger.info("{0} : page : {1}".format(self._name, i))
-                if i not in webpage:
-                    webpage.append(i)
+                if i not in webpage["page"]:
+                    webpage["page"].append(i)
                 soup = BeautifulSoup(page.text, self._parser)
                 class_div = pagingfirstline = soup.find_all("div", class_="pagingfirstline")
                 if len(class_div) > 0:
@@ -120,27 +122,27 @@ class WPExport:
                             if len(categorie) > 2:
                                 url_paging = "{0}/archives/{1}/p{2}-10.html".format(self._url, categorie[2], paging)
                             self._logger.info("{0} : {1}".format(self._name, url_paging))
-                            if url_paging not in webpage:
-                                webpage.append(url_paging)
+                            if url_paging not in webpage["page"]:
+                                webpage["page"].append(url_paging)
                             page = self._request.get(url_paging)
                             if page.status_code == 200:
                                 soup = BeautifulSoup(page.text, self._parser)
                                 h2 = soup.find_all("h2")
                                 for title in h2:
                                     href = title.find_all("a")[0].get("href", "/")
-                                    if href not in webpage:
+                                    if href not in webpage["article"]:
                                         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)
+                                        webpage["article"].append(o)
             else:
                 self._logger.error("{0} : web didn't get due status code : {1}".format(self._name, page.status_code))
-                self._logger.debug(page.content)
-        
+                self._logger.debug("{0} : {1}".format(self._name, page.content))
         return webpage
+        
 
 
     # Private method

From 3c2f1cc0170f1e33b04744efa78b1c5f7768e17b Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 7 May 2023 17:38:44 +0200
Subject: [PATCH 04/19] separate publication and principal

---
 import_export_canalblog.py | 23 +++++++++++++++--------
 lib/WPExport.py            | 21 +++++++++++++--------
 lib/WPImport.py            | 30 ++++++++++++++----------------
 3 files changed, 42 insertions(+), 32 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index c931a5f..c6cc592 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -14,13 +14,13 @@ from lib.WPExport import WPExport
 def download(name_thread, max_thread, url, logger, parser, directory, html, img):
     exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, directory=directory)    
     webpage = exportWp.getUrlPage(name_thread, max_thread)
-    if html is False:
-        exportWp.downloadHTML(webpage["article"])
-        exportWp.downloadHTML(webpage["page"])
+    for i in ["article", "page"]:
+        for j in ["publications", "principal"]:
+            if html is False:
+                exportWp.downloadHTML(webpage[j][i])
 
-    if img is False:
-        exportWp.downloadImg(webpage["article"])
-        exportWp.downloadImg(webpage["page"])
+            if img is False:
+                exportWp.downloadImg(webpage[j][i])
 
 
 
@@ -44,7 +44,10 @@ def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, bas
             del exportWp
             for j in wordpress:
                 importWp = WPimport(name=name, basic=basic, wordpress=j, logger=logger, parser=parser)
-                importWp.fromUrl(webpage)
+                for k in ["article", "page"]:
+                    for l in ["publications", "principal"]:
+                        importWp.fromUrl(webpage[l][k])
+
                 del importWp
     else:
         if len(canalblog) != len(wordpress):
@@ -62,7 +65,11 @@ def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, bas
             webpage = exportWp.getUrlPage(name_thread, max_thread)
             del exportWp
             importWp = WPimport(name=name, basic=basic, wordpress=wordpress[i], logger=logger, parser=parser)
-            importWp.fromUrl(webpage)
+
+            for k in ["article", "page"]:
+                for l in ["publications", "principal"]:
+                    importWp.fromUrl(webpage[l][k])
+
             del importWp
     
 
diff --git a/lib/WPExport.py b/lib/WPExport.py
index b817837..d6b2ee9 100644
--- a/lib/WPExport.py
+++ b/lib/WPExport.py
@@ -85,9 +85,14 @@ class WPExport:
             self._logger.error("{0} : URL did not get due status code : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(self._name, page.content))
 
-        webpage = {"page":[], "article":[]}
-
+        webpage = {"principal": {"page":[], "article":[]}, "publications": {"page":[], "article":[]}}
         for i in page_url:
+            section = "publications"
+            o = urlparse(i)
+            o = o._replace(scheme="https")
+            i = o.geturl().replace(":///", "://")
+            if i == "{0}/".format(self._url):
+                section = "principal"
             try:
                 page = self._request.get(i)
             except Exception as err:
@@ -95,8 +100,8 @@ class WPExport:
                 exit(1)
             if page.status_code == 200:
                 self._logger.info("{0} : page : {1}".format(self._name, i))
-                if i not in webpage["page"]:
-                    webpage["page"].append(i)
+                if i not in webpage[section]["page"]:
+                    webpage[section]["page"].append(i)
                 soup = BeautifulSoup(page.text, self._parser)
                 class_div = pagingfirstline = soup.find_all("div", class_="pagingfirstline")
                 if len(class_div) > 0:
@@ -122,22 +127,22 @@ class WPExport:
                             if len(categorie) > 2:
                                 url_paging = "{0}/archives/{1}/p{2}-10.html".format(self._url, categorie[2], paging)
                             self._logger.info("{0} : {1}".format(self._name, url_paging))
-                            if url_paging not in webpage["page"]:
-                                webpage["page"].append(url_paging)
+                            if url_paging not in webpage[section]["page"]:
+                                webpage[section]["page"].append(url_paging)
                             page = self._request.get(url_paging)
                             if page.status_code == 200:
                                 soup = BeautifulSoup(page.text, self._parser)
                                 h2 = soup.find_all("h2")
                                 for title in h2:
                                     href = title.find_all("a")[0].get("href", "/")
-                                    if href not in webpage["article"]:
+                                    if href not in webpage[section]["article"]:
                                         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["article"].append(o)
+                                        webpage[section]["article"].append(o)
             else:
                 self._logger.error("{0} : web didn't get due status code : {1}".format(self._name, page.status_code))
                 self._logger.debug("{0} : {1}".format(self._name, page.content))
diff --git a/lib/WPImport.py b/lib/WPImport.py
index 6f82ec4..3badd98 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -512,22 +512,20 @@ class WPimport:
             if len(result) > 0:
                 for i in result:
                     self._logger.debug("{0} : Data for post to delete : {1}".format(self._name, i))
-                    if i["title"]["rendered"] == title:
-                        self._logger.info("{0} : Page {1} already exist and going to delete".format(self._name, title))
-                        post_id = i["id"]
-                        try:
-                            params = {"force":1}
-                            page = self._request.delete("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, params=params)
-                        except Exception as err:
-                            self._logger.error("{0} : Connection error for delete post : {1}".format(self._name, err))
-                            exit(1)
-                        if page.status_code == 200:
-                            result = page.json()
-                            self._logger.info("{0} : Post deleted : {1}".format(self._name, title))
-                    
-                        else:
-                            self._logger.error("{0} : Post not deleted due status code : {1}".format(self._name, page.status_code))
-                            self._logger.debug("{0} : {1}".format(self._name, page.content))
+                    self._logger.info("{0} : Page {1} already exist and going to delete".format(self._name, title))
+                    post_id = i["id"]
+                    try:
+                        params = {"force":1}
+                        page = self._request.delete("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, params=params)
+                    except Exception as err:
+                        self._logger.error("{0} : Connection error for delete post : {1}".format(self._name, err))
+                        exit(1)
+                    if page.status_code == 200:
+                        result = page.json()
+                        self._logger.info("{0} : Post deleted : {1}".format(self._name, title))
+                    else:
+                        self._logger.error("{0} : Post not deleted due status code : {1}".format(self._name, page.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, page.content))
         else:
             self._logger.error("{0} : Connection for delete post error with status code : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(self._name, page.content))

From 3d7aa19441dd0bc33aaa201db3d67701167e0d9d Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Fri, 12 May 2023 00:16:58 +0200
Subject: [PATCH 05/19] add update

---
 lib/WPImport.py | 55 +++++++++++++++++++++++++++----------------------
 1 file changed, 30 insertions(+), 25 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index 3badd98..adfa67f 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -5,6 +5,7 @@ from urllib.parse import urlparse
 import requests, os, logging, re, json
 from requests.adapters import HTTPAdapter
 from requests.packages.urllib3.util.retry import Retry
+from slugify import slugify
 
 class WPimport:
     # Constructor
@@ -499,48 +500,52 @@ class WPimport:
             self._logger.error("{0} : Connection error with status code for get author : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(page.content))
 
-
-        params = {"search":title}
+        slug = slugify(title)
+        params = {"slug":slug}
         try:
             page = self._request.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params)
         except Exception as err:
             self._logger.error("{0} : Connection error for search post : {1}".format(self._name, err))
             exit(1)
         headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
+        page_is_exist = True
         if page.status_code == 200:
             result = page.json()
-            if len(result) > 0:
+            if len(result) == 0:
+                page_is_exist = False
+            else:
                 for i in result:
-                    self._logger.debug("{0} : Data for post to delete : {1}".format(self._name, i))
-                    self._logger.info("{0} : Page {1} already exist and going to delete".format(self._name, title))
+                    self._logger.debug("{0} : Data for post to update : {1}".format(self._name, i))
+                    self._logger.info("{0} : Page {1} already exist and going to update".format(self._name, title))
                     post_id = i["id"]
                     try:
-                        params = {"force":1}
-                        page = self._request.delete("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, params=params)
+                        page = self._request.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, data=json.dumps(data))
                     except Exception as err:
-                        self._logger.error("{0} : Connection error for delete post : {1}".format(self._name, err))
+                        self._logger.error("{0} : Connection error for update post : {1}".format(self._name, err))
                         exit(1)
                     if page.status_code == 200:
                         result = page.json()
-                        self._logger.info("{0} : Post deleted : {1}".format(self._name, title))
+                        self._logger.info("{0} : Post updated : {1}".format(self._name, title))
+                        self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
+                        self._linkImgPost(result["title"]["raw"], list_img, result["id"])
                     else:
-                        self._logger.error("{0} : Post not deleted due status code : {1}".format(self._name, page.status_code))
+                        self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
                         self._logger.debug("{0} : {1}".format(self._name, page.content))
         else:
-            self._logger.error("{0} : Connection for delete post error with status code : {1}".format(self._name, page.status_code))
+            self._logger.error("{0} : Connection for update post error with status code : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(self._name, page.content))
 
-                    
-        try:
-            page = self._request.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
-        except Exception as err:
-            self._logger.error("{0} : Connection error for create post : {1}".format(self._name, err))
-            exit(1)
-        if page.status_code == 201:
-            result = page.json()
-            self._logger.info("{0} : Post added : {1}".format(self._name, result["title"]["raw"]))
-            self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
-            self._linkImgPost(result["title"]["raw"], list_img, result["id"])
-        else:
-            self._logger.error("{0} : Post not added due status code : {1}".format(self._name, r.status_code))
-            self._logger.debug("{0} : {1}".format(self._name, r.content))
+        if page_is_exist == False:
+            try:
+                page = self._request.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
+            except Exception as err:
+                self._logger.error("{0} : Connection error for create post : {1}".format(self._name, err))
+                exit(1)
+            if page.status_code == 201:
+                result = page.json()
+                self._logger.info("{0} : Post added : {1}".format(self._name, result["title"]["raw"]))
+                self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
+                self._linkImgPost(result["title"]["raw"], list_img, result["id"])
+            else:
+                self._logger.error("{0} : Post not added due status code : {1}".format(self._name, r.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, r.content))

From ece4d78dd8fd77cc708c76a18c3042716d974dba Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 14 May 2023 18:35:36 +0200
Subject: [PATCH 06/19] add remove all

---
 import_export_canalblog.py | 11 +++++-
 lib/WPImport.py            | 73 ++++++++++++++++++++++++++------------
 2 files changed, 61 insertions(+), 23 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index c6cc592..e6b4e28 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -113,6 +113,7 @@ if __name__ == '__main__':
     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")
+    import_parser.add_argument("--remove", help="Remove all articles", action="store_true")
 
 
 
@@ -165,12 +166,16 @@ if __name__ == '__main__':
 
         basic = HTTPBasicAuth(args.user, password)
         wordpress = args.wordpress.split(",")
-        importWp = WPimport(basic, "", logger, args.parser)
+        importWp = WPimport(basic=basic, wordpress="", logger=logger, parser=args.parser)
         if len(args.file) > 0:
             for i in wordpress:
                 importWp.setUrl(i)
                 importWp.fromFile(files=args.file.split(","))
         if len(args.directory) > 0:
+            if args.remove:
+                for i in args.wordpress.split(","):
+                    importWp.setUrl(i)
+                    importWp.removeAll()
             try:
                 with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
                     wait_for = [
@@ -180,6 +185,10 @@ if __name__ == '__main__':
             except Exception as err:
                 logger.error("Threading error : {0}".format(err))
         if len(args.canalblog) > 0:
+            if args.remove:
+                for i in args.wordpress.split(","):
+                    importWp.setUrl(i)
+                    importWp.removeAll()
             try:
                 with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
                     wait_for = [
diff --git a/lib/WPImport.py b/lib/WPImport.py
index adfa67f..f8d8a35 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -5,7 +5,6 @@ from urllib.parse import urlparse
 import requests, os, logging, re, json
 from requests.adapters import HTTPAdapter
 from requests.packages.urllib3.util.retry import Retry
-from slugify import slugify
 
 class WPimport:
     # Constructor
@@ -87,6 +86,35 @@ class WPimport:
                     else:
                         self._addOrUpdateFeaturedMedia(soup)
     
+    def removeAll(self):
+        params = {"per_page":100}
+        try:
+            self._logger.info("{0} : List posts to remove for url : {1}".format(self._name, self._wordpress))
+            
+            r = self._request.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params, headers=self._headers_json)
+        except Exception as err:
+            self._logger.error("{0} : Connection error for list post to remove : {1}".format(self._name, err))
+        if r.status_code == 200:
+            result = r.json()
+            if len(result) > 0:
+                for i in result:
+                    self._logger.info("{0} : Remove article for url {1} : {2}".format(self._name, self._wordpress, i["title"]["rendered"]))
+                    params = {"force":1}
+                    try:
+                        r = self._request.delete("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, i["id"]), auth=self._basic, headers=self._headers_json , params=params)
+                        if r.status_code == 200:
+                            self._logger.info("{0} : Post removed for URL {1} : {2}".format(self._name, self._wordpress, i["title"]["rendered"]))
+                        else:
+                            self._logger.error("{0} : Connection error for post {1} with status code {2}".format(self._name, self._wordpress, i["title"]["rendered"]))
+                    except Exception as err:
+                        self._logger.error("{0} : Connection error for post remove : {1}".format(self._name, err))
+                        exit(1)
+                self.removeAll()
+        else:
+            self._logger.error("{0} : Error for list to remove due status code {1}".format(self._name, r.status_code))
+            self._logger.debug("{0} : Content error : {1}".format(self._name, r.content))
+
+    
     # Private method
 
     ## Get all files
@@ -489,6 +517,7 @@ class WPimport:
         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}
         try:
+            self._logger.info("{0} : Get author : {1}".format(self._name, author))
             page = self._request.get("http://{0}/wp-json/wp/v2/users".format(self._wordpress), auth=self._basic, params=params)
         except Exception as err:
             self._logger.error("{0} : Connection error for get author : {1}".format(self._name, err))
@@ -499,15 +528,13 @@ class WPimport:
         else:
             self._logger.error("{0} : Connection error with status code for get author : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(page.content))
-
-        slug = slugify(title)
-        params = {"slug":slug}
+        
+        params = {"search": title}
         try:
             page = self._request.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params)
         except Exception as err:
             self._logger.error("{0} : Connection error for search post : {1}".format(self._name, err))
             exit(1)
-        headers = {'Content-Type': 'application/json', 'Accept':'application/json'}
         page_is_exist = True
         if page.status_code == 200:
             result = page.json()
@@ -515,29 +542,31 @@ class WPimport:
                 page_is_exist = False
             else:
                 for i in result:
-                    self._logger.debug("{0} : Data for post to update : {1}".format(self._name, i))
-                    self._logger.info("{0} : Page {1} already exist and going to update".format(self._name, title))
-                    post_id = i["id"]
-                    try:
-                        page = self._request.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=headers, data=json.dumps(data))
-                    except Exception as err:
-                        self._logger.error("{0} : Connection error for update post : {1}".format(self._name, err))
-                        exit(1)
-                    if page.status_code == 200:
-                        result = page.json()
-                        self._logger.info("{0} : Post updated : {1}".format(self._name, title))
-                        self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
-                        self._linkImgPost(result["title"]["raw"], list_img, result["id"])
-                    else:
-                        self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
-                        self._logger.debug("{0} : {1}".format(self._name, page.content))
+                    if i["title"]["rendered"] == title:
+                        post_id = i["id"]                
+                        self._logger.debug("{0} : Data for post to update : {1}".format(self._name, result[0]))
+                        self._logger.info("{0} : Page {1} already exist and going to update".format(self._name, title))
+                
+                        try:
+                            page = self._request.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
+                        except Exception as err:
+                            self._logger.error("{0} : Connection error for update post : {1}".format(self._name, err))
+                            exit(1)
+                        if page.status_code == 200:
+                            result = page.json()
+                            self._logger.info("{0} : Post updated : {1}".format(self._name, title))
+                            self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
+                            self._linkImgPost(result["title"]["raw"], list_img, result["id"])
+                        else:
+                            self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
+                            self._logger.debug("{0} : {1}".format(self._name, page.content))
         else:
             self._logger.error("{0} : Connection for update post error with status code : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(self._name, page.content))
 
         if page_is_exist == False:
             try:
-                page = self._request.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=headers, data=json.dumps(data))
+                page = self._request.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
             except Exception as err:
                 self._logger.error("{0} : Connection error for create post : {1}".format(self._name, err))
                 exit(1)

From ee8674fd595268deda4453c470156c80bef3b135 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 15 May 2023 23:13:55 +0200
Subject: [PATCH 07/19] add remove class

---
 lib/WPImport.py | 28 ------------------
 lib/WPRemove.py | 75 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+), 28 deletions(-)
 create mode 100644 lib/WPRemove.py

diff --git a/lib/WPImport.py b/lib/WPImport.py
index f8d8a35..6108582 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -86,34 +86,6 @@ class WPimport:
                     else:
                         self._addOrUpdateFeaturedMedia(soup)
     
-    def removeAll(self):
-        params = {"per_page":100}
-        try:
-            self._logger.info("{0} : List posts to remove for url : {1}".format(self._name, self._wordpress))
-            
-            r = self._request.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params, headers=self._headers_json)
-        except Exception as err:
-            self._logger.error("{0} : Connection error for list post to remove : {1}".format(self._name, err))
-        if r.status_code == 200:
-            result = r.json()
-            if len(result) > 0:
-                for i in result:
-                    self._logger.info("{0} : Remove article for url {1} : {2}".format(self._name, self._wordpress, i["title"]["rendered"]))
-                    params = {"force":1}
-                    try:
-                        r = self._request.delete("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, i["id"]), auth=self._basic, headers=self._headers_json , params=params)
-                        if r.status_code == 200:
-                            self._logger.info("{0} : Post removed for URL {1} : {2}".format(self._name, self._wordpress, i["title"]["rendered"]))
-                        else:
-                            self._logger.error("{0} : Connection error for post {1} with status code {2}".format(self._name, self._wordpress, i["title"]["rendered"]))
-                    except Exception as err:
-                        self._logger.error("{0} : Connection error for post remove : {1}".format(self._name, err))
-                        exit(1)
-                self.removeAll()
-        else:
-            self._logger.error("{0} : Error for list to remove due status code {1}".format(self._name, r.status_code))
-            self._logger.debug("{0} : Content error : {1}".format(self._name, r.content))
-
     
     # Private method
 
diff --git a/lib/WPRemove.py b/lib/WPRemove.py
new file mode 100644
index 0000000..ad4ab8a
--- /dev/null
+++ b/lib/WPRemove.py
@@ -0,0 +1,75 @@
+#!/usr/bin/python3
+
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse
+import requests, os, logging, re, json
+from requests.adapters import HTTPAdapter
+from requests.packages.urllib3.util.retry import Retry
+
+class WPRemove:
+    # Constructor
+    def __init__(self, name="Thread-0", basic=None, wordpress="", logger=None):
+        self._name = name
+        self._basic = basic
+        self._wordpress = wordpress
+        self._logger = logger
+        self._headers_json = {'Content-Type': 'application/json', 'Accept':'application/json'}
+
+        self._request = requests.Session()
+
+        retries = Retry(connect=10, read=10, redirect=5,
+                status_forcelist=[429, 500, 502, 503, 504], backoff_factor=2)
+
+        self._request.mount('http://', HTTPAdapter(max_retries=retries))
+
+    
+    # Destructor 
+    def __del__(self):
+        print("{0} : Import finished for {1}".format(self._name, self._wordpress))
+
+    # Public method
+
+    def setUrl(self, wordpress):
+        self._wordpress = wordpress
+    
+    def cleanPosts(self):
+        self._removeAll("posts")
+
+    def cleanTags(self):
+        self._removeAll("tags")
+
+    def cleanCategories(self):
+        self._removeAll("categories")
+    
+    def cleanMedia(self):
+        self._removeAll("media")
+
+    # Private method
+    
+    def _removeAll(self, composant):
+        params = {"per_page":100}
+        try:
+            self._logger.info("{0} : List {2} to remove for url : {1}".format(self._name, self._wordpress, composant))
+            
+            r = self._request.get("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress, composant), auth=self._basic, params=params, headers=self._headers_json)
+        except Exception as err:
+            self._logger.error("{0} : Connection error for list {1} to remove : {2}".format(self._name, composant, err))
+        if r.status_code == 200:
+            result = r.json()
+            if len(result) > 0:
+                for i in result:
+                    self._logger.info("{0} : Remove {2} for url {1} : {3}".format(self._name, self._wordpress, composant, i["title"]["rendered"]))
+                    params = {"force":1}
+                    try:
+                        r = self._request.delete("http://{0}/wp-json/wp/v2/{1}/{2}".format(self._wordpress, composant, i["id"]), auth=self._basic, headers=self._headers_json , params=params)
+                        if r.status_code == 200:
+                            self._logger.info("{0} : Post removed for URL {1} {2} : {3}".format(self._name, self._wordpress, composant, i["title"]["rendered"]))
+                        else:
+                            self._logger.error("{0} : Connection error for post {1} {2} {3} with status code {4}".format(self._name, self._wordpress, composant, i["title"]["rendered"], r.status_code))
+                    except Exception as err:
+                        self._logger.error("{0} : Connection error for {1} remove : {2}".format(self._name, composant, err))
+                        exit(1)
+                self._removeAll(composant)
+        else:
+            self._logger.error("{0} : Error for list to remove {1} due status code {2}".format(self._name, composant, r.status_code))
+            self._logger.debug("{0} : Content error for {1} : {2}".format(self._name, composant, r.content))

From cfb24bed0e16797c2209f62d753435bce2ceb869 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 15 May 2023 23:21:25 +0200
Subject: [PATCH 08/19] add remove parameters

---
 import_export_canalblog.py | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index e6b4e28..4c38ff3 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -113,7 +113,22 @@ if __name__ == '__main__':
     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")
-    import_parser.add_argument("--remove", help="Remove all articles", action="store_true")
+    import_parser.add_argument("--remove", help="Remove all", action="store_true")
+    remove_parser.add_argument("--remove-posts", help="Remove all posts", dest="posts", action="store_true")
+    remove_parser.add_argument("--remove-categories", help="Remove all categories", dest="categories", action="store_true")
+    remove_parser.add_argument("--remove-tags", help="Remove all tags", dest="tags", action="store_true")
+    remove_parser.add_argument("--remove-media", help="Remove all media", dest="media", action="store_true")
+
+
+    remove_parser = subparsers.add_parser("remove")
+    remove_parser.add_argument("--user", help="wordpress user", required=True)
+    remove_parser.add_argument("--password", help="password wordpress's user", default="")
+    remove_parser.add_argument("--wordpress", help="URL Wordpress", required=True)
+    remove_parser.add_argument("--all", help="Remove all (posts, media, tags, categories)", action="store_true")
+    remove_parser.add_argument("--posts", help="Remove all posts", action="store_true")
+    remove_parser.add_argument("--categories", help="Remove all categories", action="store_true")
+    remove_parser.add_argument("--tags", help="Remove all tags", action="store_true")
+    remove_parser.add_argument("--media", help="Remove all media", action="store_true")
 
 
 

From f3cb5c4069c0d1855759b4766aa622873aa8b4ba Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 15 May 2023 23:22:41 +0200
Subject: [PATCH 09/19] fix parameters

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

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 4c38ff3..81b3e00 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -113,7 +113,7 @@ if __name__ == '__main__':
     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")
-    import_parser.add_argument("--remove", help="Remove all", action="store_true")
+    import_parser.add_argument("--remove-all", dest="remove", help="Remove all", action="store_true")
     remove_parser.add_argument("--remove-posts", help="Remove all posts", dest="posts", action="store_true")
     remove_parser.add_argument("--remove-categories", help="Remove all categories", dest="categories", action="store_true")
     remove_parser.add_argument("--remove-tags", help="Remove all tags", dest="tags", action="store_true")
@@ -124,7 +124,7 @@ if __name__ == '__main__':
     remove_parser.add_argument("--user", help="wordpress user", required=True)
     remove_parser.add_argument("--password", help="password wordpress's user", default="")
     remove_parser.add_argument("--wordpress", help="URL Wordpress", required=True)
-    remove_parser.add_argument("--all", help="Remove all (posts, media, tags, categories)", action="store_true")
+    remove_parser.add_argument("--all", dest="remove", help="Remove all (posts, media, tags, categories)", action="store_true")
     remove_parser.add_argument("--posts", help="Remove all posts", action="store_true")
     remove_parser.add_argument("--categories", help="Remove all categories", action="store_true")
     remove_parser.add_argument("--tags", help="Remove all tags", action="store_true")

From 8bdaea391045f1352d370d91945e32c69630792b Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 15 May 2023 23:42:18 +0200
Subject: [PATCH 10/19] add remove command

---
 import_export_canalblog.py | 44 ++++++++++++++++++++++++++++++--------
 1 file changed, 35 insertions(+), 9 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 81b3e00..97a5bf3 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -8,7 +8,29 @@ from concurrent.futures import as_completed, wait
 import argparse, logging, threading
 from lib.WPImport import WPimport
 from lib.WPExport import WPExport
+from lib.WPRemove import WPRemove
 
+def remove(args, basic, logger):
+    removeWp = WPRemove(basic=basic, wordpress="", logger=logger)
+    if args.remove:
+        for i in args.wordpress.split(","):
+            removeWp.setUrl(i)
+            removeWp.cleanPosts()
+            removeWp.cleanTags()
+            removeWp.cleanCategories()
+            removeWp.cleanMedia()
+    else:
+        for i in args.wordpress.split(","):
+            removeWp.setUrl(i)
+            if args.posts:
+                removeWp.cleanPosts()
+            if args.categories:
+                removeWp.cleanCategories()
+            if args.tags:
+                removeWp.cleanTags()
+            if args.media:
+                removeWp.cleanMedia()
+    del removeWp
 
 
 def download(name_thread, max_thread, url, logger, parser, directory, html, img):
@@ -187,10 +209,7 @@ if __name__ == '__main__':
                 importWp.setUrl(i)
                 importWp.fromFile(files=args.file.split(","))
         if len(args.directory) > 0:
-            if args.remove:
-                for i in args.wordpress.split(","):
-                    importWp.setUrl(i)
-                    importWp.removeAll()
+            remove(args, basic, logger)
             try:
                 with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
                     wait_for = [
@@ -200,10 +219,7 @@ if __name__ == '__main__':
             except Exception as err:
                 logger.error("Threading error : {0}".format(err))
         if len(args.canalblog) > 0:
-            if args.remove:
-                for i in args.wordpress.split(","):
-                    importWp.setUrl(i)
-                    importWp.removeAll()
+            remove(args, basic, logger)
             try:
                 with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
                     wait_for = [
@@ -246,5 +262,15 @@ if __name__ == '__main__':
                 except Exception as err:
                     logger.error("Threading error : {0}".format(err))
 
-                
+
+        if args.command == "remove":
+            password = args.password
+            if len(args.password) == 0:
+                password = getpass()
+                if len(password) == 0:
+                    logger.error("No password error !!! ")
+                    exit(1)
+
+            basic = HTTPBasicAuth(args.user, password)
+            remove(args, basic, logger) 
         exit(0)
\ No newline at end of file

From d18f4e1579f725f607c5c81ba536522a7ae2c283 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Mon, 15 May 2023 23:51:45 +0200
Subject: [PATCH 11/19] Add clean

---
 import_export_canalblog.py | 34 ++++++++++++++--------------------
 1 file changed, 14 insertions(+), 20 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index 97a5bf3..6a2a3e3 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -12,7 +12,7 @@ from lib.WPRemove import WPRemove
 
 def remove(args, basic, logger):
     removeWp = WPRemove(basic=basic, wordpress="", logger=logger)
-    if args.remove:
+    if args.remove == True:
         for i in args.wordpress.split(","):
             removeWp.setUrl(i)
             removeWp.cleanPosts()
@@ -22,13 +22,13 @@ def remove(args, basic, logger):
     else:
         for i in args.wordpress.split(","):
             removeWp.setUrl(i)
-            if args.posts:
+            if args.posts == True:
                 removeWp.cleanPosts()
-            if args.categories:
+            if args.categories == True:
                 removeWp.cleanCategories()
-            if args.tags:
+            if args.tags == True:
                 removeWp.cleanTags()
-            if args.media:
+            if args.media == True:
                 removeWp.cleanMedia()
     del removeWp
 
@@ -136,10 +136,10 @@ if __name__ == '__main__':
     import_parser.add_argument("--wordpress", help="URL Wordpress", required=True)
     import_parser.add_argument("--serial", help="Serial execution", action="store_true")
     import_parser.add_argument("--remove-all", dest="remove", help="Remove all", action="store_true")
-    remove_parser.add_argument("--remove-posts", help="Remove all posts", dest="posts", action="store_true")
-    remove_parser.add_argument("--remove-categories", help="Remove all categories", dest="categories", action="store_true")
-    remove_parser.add_argument("--remove-tags", help="Remove all tags", dest="tags", action="store_true")
-    remove_parser.add_argument("--remove-media", help="Remove all media", dest="media", action="store_true")
+    import_parser.add_argument("--remove-posts", help="Remove all posts", dest="posts", action="store_true")
+    import_parser.add_argument("--remove-categories", help="Remove all categories", dest="categories", action="store_true")
+    import_parser.add_argument("--remove-tags", help="Remove all tags", dest="tags", action="store_true")
+    import_parser.add_argument("--remove-media", help="Remove all media", dest="media", action="store_true")
 
 
     remove_parser = subparsers.add_parser("remove")
@@ -193,7 +193,7 @@ if __name__ == '__main__':
         fileHandler.setFormatter(formatter)
         logger.addHandler(fileHandler)
 
-    if args.command == "import":
+    if args.command == "import" or args.command == "remove":
         password = args.password
         if len(args.password) == 0:
             password = getpass()
@@ -202,6 +202,7 @@ if __name__ == '__main__':
                 exit(1)
 
         basic = HTTPBasicAuth(args.user, password)
+    if args.command == "import":
         wordpress = args.wordpress.split(",")
         importWp = WPimport(basic=basic, wordpress="", logger=logger, parser=args.parser)
         if len(args.file) > 0:
@@ -261,16 +262,9 @@ if __name__ == '__main__':
                         ]
                 except Exception as err:
                     logger.error("Threading error : {0}".format(err))
+        exit(0)
 
 
-        if args.command == "remove":
-            password = args.password
-            if len(args.password) == 0:
-                password = getpass()
-                if len(password) == 0:
-                    logger.error("No password error !!! ")
-                    exit(1)
-
-            basic = HTTPBasicAuth(args.user, password)
-            remove(args, basic, logger) 
+    if args.command == "remove":
+        remove(args, basic, logger) 
         exit(0)
\ No newline at end of file

From ba42d56be1c6248d19a6b4fb118512fc2d044303 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 16 May 2023 00:15:16 +0200
Subject: [PATCH 12/19] fix webpage

---
 lib/WPExport.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/lib/WPExport.py b/lib/WPExport.py
index d6b2ee9..58827da 100644
--- a/lib/WPExport.py
+++ b/lib/WPExport.py
@@ -108,12 +108,14 @@ class WPExport:
                     pagingfirstline = class_div[0].find_all("a")
                     if len(pagingfirstline) > 1:
                         lastpage = pagingfirstline[len(pagingfirstline)-1].get("href", "/")
+                        self._logger.debug("{0} : Last page {1}".format(self._name, lastpage))
+
                         element_lastpage = lastpage.split("/")[len(lastpage.split("/"))-1]
                         number_page = element_lastpage.split("-")[0].split("p")[1]
                         number_lastpage = int(number_page) / 10
 
                         setPageDivided = int(number_lastpage) / max_thread
-                        setPagePart = setPageDivided * (index_thread + 1)
+                        setPagePart = setPageDivided * (index_thread + 1) + 1
                         firstPagePart = (setPagePart - setPageDivided)
 
                         self._logger.debug("{0} : Total page : {1}".format(self._name,int(number_lastpage)))

From 769b7f43fc7f29e7734cd9c44df9d2b7f92aaba4 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Thu, 18 May 2023 00:24:41 +0200
Subject: [PATCH 13/19] fix add or update post

---
 lib/WPExport.py | 10 +++++---
 lib/WPImport.py | 61 ++++++++++++++++++++++++++++---------------------
 2 files changed, 42 insertions(+), 29 deletions(-)

diff --git a/lib/WPExport.py b/lib/WPExport.py
index 58827da..90080b7 100644
--- a/lib/WPExport.py
+++ b/lib/WPExport.py
@@ -103,7 +103,7 @@ class WPExport:
                 if i not in webpage[section]["page"]:
                     webpage[section]["page"].append(i)
                 soup = BeautifulSoup(page.text, self._parser)
-                class_div = pagingfirstline = soup.find_all("div", class_="pagingfirstline")
+                class_div = soup.find_all("div", class_="pagingfirstline")
                 if len(class_div) > 0:
                     pagingfirstline = class_div[0].find_all("a")
                     if len(pagingfirstline) > 1:
@@ -115,14 +115,16 @@ class WPExport:
                         number_lastpage = int(number_page) / 10
 
                         setPageDivided = int(number_lastpage) / max_thread
-                        setPagePart = setPageDivided * (index_thread + 1) + 1
+                        if setPageDivided > int(setPageDivided):
+                            setPageDivided = setPageDivided + 1
+                        setPagePart = setPageDivided * (index_thread + 1)
                         firstPagePart = (setPagePart - setPageDivided)
 
                         self._logger.debug("{0} : Total page : {1}".format(self._name,int(number_lastpage)))
                         self._logger.debug("{0} : First range : {1}".format(self._name, int(firstPagePart)))
                         self._logger.debug("{0} : Last range : {1}".format(self._name, int(setPagePart)))
 
-                        for j in range(int(firstPagePart),int(setPagePart)):
+                        for j in range(int(firstPagePart),int(setPagePart)+1):
                             paging = j * 10
                             categorie = urlparse(i).path.split("/")
                             url_paging = "{0}/archives/p{1}-10.html".format(self._url, paging)
@@ -135,7 +137,9 @@ class WPExport:
                             if page.status_code == 200:
                                 soup = BeautifulSoup(page.text, self._parser)
                                 h2 = soup.find_all("h2")
+                                self._logger.debug("{0} : {1} H2 : {2}".format(self._name, url_paging, h2))
                                 for title in h2:
+                                    self._logger.debug("{0} : {1} a : {2}".format(self._name, url_paging, title.find_all("a")))
                                     href = title.find_all("a")[0].get("href", "/")
                                     if href not in webpage[section]["article"]:
                                         try:
diff --git a/lib/WPImport.py b/lib/WPImport.py
index 6108582..8e27a0e 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -489,12 +489,15 @@ class WPimport:
         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}
         try:
-            self._logger.info("{0} : Get author : {1}".format(self._name, author))
+            self._logger.info("{0} : Search author : {1}".format(self._name, author))
             page = self._request.get("http://{0}/wp-json/wp/v2/users".format(self._wordpress), auth=self._basic, params=params)
-        except Exception as err:
+        except ConnectionError as err:
             self._logger.error("{0} : Connection error for get author : {1}".format(self._name, err))
             exit(1)
+        except Exception as err:
+            self._logger.error("{0} : Exception error for get author : {1}".format(self._name, err))
         if page.status_code == 200:
+            self._logger.info("{0} : Get author id : {1}".format(self._name, result[0]["id"]))
             result = page.json()
             data["author"] = result[0]["id"]
         else:
@@ -503,45 +506,51 @@ class WPimport:
         
         params = {"search": title}
         try:
+            self._logger.info("{0} : Search post : {1}".format(self._name, title))
             page = self._request.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params)
-        except Exception as err:
+        except ConnectionError as err:
             self._logger.error("{0} : Connection error for search post : {1}".format(self._name, err))
             exit(1)
-        page_is_exist = True
+        except Exception as err:
+            self._logger.error("{0} : Exception error for search post : {1}".format(self._name, err))
+        page_is_exist = False
         if page.status_code == 200:
             result = page.json()
-            if len(result) == 0:
-                page_is_exist = False
-            else:
-                for i in result:
-                    if i["title"]["rendered"] == title:
-                        post_id = i["id"]                
-                        self._logger.debug("{0} : Data for post to update : {1}".format(self._name, result[0]))
-                        self._logger.info("{0} : Page {1} already exist and going to update".format(self._name, title))
+            self._logger.info("{0} : Number result posts : {1}".format(self._name, len(result)))
+            for i in result:
+                self._logger.info("{0} : Search title posts for {2} : {1}".format(self._name, i["title"]["rendered"], title))
+                if i["title"]["rendered"] == title:
+                    page_is_exist = True
+                    post_id = i["id"]                
+                    self._logger.debug("{0} : Data for post to update : {1}".format(self._name, result[0]))
+                    self._logger.info("{0} : Page {1} already exist and going to update".format(self._name, title))
                 
-                        try:
-                            page = self._request.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
-                        except Exception as err:
-                            self._logger.error("{0} : Connection error for update post : {1}".format(self._name, err))
-                            exit(1)
-                        if page.status_code == 200:
-                            result = page.json()
-                            self._logger.info("{0} : Post updated : {1}".format(self._name, title))
-                            self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
-                            self._linkImgPost(result["title"]["raw"], list_img, result["id"])
-                        else:
-                            self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
-                            self._logger.debug("{0} : {1}".format(self._name, page.content))
+                    try:
+                        page = self._request.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
+                    except Exception as err:
+                        self._logger.error("{0} : Connection error for update post : {1}".format(self._name, err))
+                        exit(1)
+                    if page.status_code == 200:
+                        result = page.json()
+                        self._logger.info("{0} : Post updated : {1}".format(self._name, title))
+                        self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
+                        self._linkImgPost(result["title"]["raw"], list_img, result["id"])
+                    else:
+                        self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, page.content))
         else:
             self._logger.error("{0} : Connection for update post error with status code : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(self._name, page.content))
 
         if page_is_exist == False:
             try:
+                self._logger.info("{0} : Creating posts : {1}".format(self._name, data["title"]))
                 page = self._request.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
-            except Exception as err:
+            except ConnectionError as err:
                 self._logger.error("{0} : Connection error for create post : {1}".format(self._name, err))
                 exit(1)
+            except Exception as err:
+                self._logger.error("{0} : Exception error for create post : {1}".format(self._name, err))
             if page.status_code == 201:
                 result = page.json()
                 self._logger.info("{0} : Post added : {1}".format(self._name, result["title"]["raw"]))

From 75772ba7f061809ec812a3bc2f4bcbb4d645ebc1 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 21 May 2023 21:12:00 +0200
Subject: [PATCH 14/19] remove doublon

---
 lib/WPImport.py | 120 ++++++++++++++++++++++++++++++++----------------
 1 file changed, 80 insertions(+), 40 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index 8e27a0e..7b78cad 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -5,6 +5,7 @@ from urllib.parse import urlparse
 import requests, os, logging, re, json
 from requests.adapters import HTTPAdapter
 from requests.packages.urllib3.util.retry import Retry
+from slugify import slugify
 
 class WPimport:
     # Constructor
@@ -14,7 +15,7 @@ class WPimport:
         self._wordpress = wordpress
         self._logger = logger
         self._parser = parser
-        self._headers_json = {'Content-Type': 'application/json', 'Accept':'application/json'}
+        self._headers_json = {'Content-Type': 'application/json; charset=utf-8', 'Accept':'application/json'}
 
         self._request = requests.Session()
 
@@ -487,7 +488,7 @@ class WPimport:
         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}
+        params = {"search":author, "per_page":100}
         try:
             self._logger.info("{0} : Search author : {1}".format(self._name, author))
             page = self._request.get("http://{0}/wp-json/wp/v2/users".format(self._wordpress), auth=self._basic, params=params)
@@ -503,46 +504,85 @@ class WPimport:
         else:
             self._logger.error("{0} : Connection error with status code for get author : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(page.content))
-        
-        params = {"search": title}
-        try:
-            self._logger.info("{0} : Search post : {1}".format(self._name, title))
-            page = self._request.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params)
-        except ConnectionError as err:
-            self._logger.error("{0} : Connection error for search post : {1}".format(self._name, err))
-            exit(1)
-        except Exception as err:
-            self._logger.error("{0} : Exception error for search post : {1}".format(self._name, err))
+        if title[len(title)-1] == " ":
+            title = title[:-1]
         page_is_exist = False
-        if page.status_code == 200:
-            result = page.json()
-            self._logger.info("{0} : Number result posts : {1}".format(self._name, len(result)))
-            for i in result:
-                self._logger.info("{0} : Search title posts for {2} : {1}".format(self._name, i["title"]["rendered"], title))
-                if i["title"]["rendered"] == title:
-                    page_is_exist = True
-                    post_id = i["id"]                
-                    self._logger.debug("{0} : Data for post to update : {1}".format(self._name, result[0]))
-                    self._logger.info("{0} : Page {1} already exist and going to update".format(self._name, title))
-                
-                    try:
-                        page = self._request.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
-                    except Exception as err:
-                        self._logger.error("{0} : Connection error for update post : {1}".format(self._name, err))
-                        exit(1)
-                    if page.status_code == 200:
-                        result = page.json()
-                        self._logger.info("{0} : Post updated : {1}".format(self._name, title))
-                        self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
-                        self._linkImgPost(result["title"]["raw"], list_img, result["id"])
-                    else:
-                        self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
-                        self._logger.debug("{0} : {1}".format(self._name, page.content))
-        else:
-            self._logger.error("{0} : Connection for update post error with status code : {1}".format(self._name, page.status_code))
-            self._logger.debug("{0} : {1}".format(self._name, page.content))
 
-        if page_is_exist == False:
+        for index in range(1,10):
+            params = {"search": title, "per_page":100, "page": index}
+            try:
+                self._logger.info("{0} : Search post : {1}".format(self._name, title))
+                page = self._request.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params, headers=self._headers_json)
+            except ConnectionError as err:
+                self._logger.error("{0} : Connection error for search post : {1}".format(self._name, err))
+                exit(1)
+            except Exception as err:
+                self._logger.error("{0} : Exception error for search post : {1}".format(self._name, err))
+            if page.status_code == 200:
+                self._logger.debug("{0} : Encoding : {1}".format(self._name, page.encoding))
+                page.encoding = "utf-8"
+                result = page.json()
+                if len(result) == 0:
+                    break
+                self._logger.info("{0} : Number result posts : {1}".format(self._name, len(result)))
+                count = 0
+                for i in result:
+                
+                    self._logger.info("{0} : Search title posts for |{2}| : |{1}|".format(self._name, i["title"]["rendered"], title))
+                    title_rendered = i["title"]["rendered"].replace('&rsquo;', "'")
+                    title_rendered = title_rendered.replace('&#8211;', '-')
+                    title_rendered = title_rendered.replace('&#8230;', '...')
+                    title_rendered = title_rendered.replace('« ', '"')
+                    title_rendered = title_rendered.replace(' »', '"')
+                    self._logger.debug("{0} : SIze of title : {1} - {2}".format(self._name, len(title), len(title_rendered)))
+                    if title_rendered == title:
+                        page_is_exist = True
+                        post_id = i["id"]
+                        count = count + 1
+                        if count > 1:
+                            self._logger.info("{0} : Page {1} is double and going to delete".format(self._name, title))
+                            try:
+                                params = {"force":1}
+                                page = self._request.delete("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=self._headers_json, params=params)
+                            except ConnectionError as err:
+                                self._logger.error("{0} : Connection error for deleted post : {1}".format(self._name, err))
+                                exit(1)
+                            except Exception as err:
+                                self._logger.error("{0} : Exception error for deleted post : {1}".format(self._name, err))
+                            if page.status_code == 200:
+                                self._logger.info("{0} : Post deleted : {1}".format(self._name, title))
+                            else:
+                                self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
+                                self._logger.debug("{0} : {1}".format(self._name, page.content))    
+                    
+                        else:
+                            self._logger.debug("{0} : Data for post to update : {1}".format(self._name, i))
+                            self._logger.info("{0} : Page {1} already exist and going to update".format(self._name, title))
+                
+                            try:
+                                page = self._request.post("http://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
+                            except ConnectionError as err:
+                                self._logger.error("{0} : Connection error for update post : {1}".format(self._name, err))
+                                exit(1)
+                            except Exception as err:
+                                self._logger.error("{0} : Exception error for update post : {1}".format(self._name, err))
+                            if page.status_code == 200:
+                                result = page.json()
+                                self._logger.info("{0} : Post updated : {1}".format(self._name, title))
+                                self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
+                                self._linkImgPost(result["title"]["raw"], list_img, result["id"])
+                            else:
+                                self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
+                                self._logger.debug("{0} : {1}".format(self._name, page.content))
+            if page.status_code == 400:
+                self._logger.error("{0} : Connection for update post unauthorized : {1}".format(self._name, page.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, page.content))
+                break
+            else:
+                self._logger.error("{0} : Connection for update post error with status code : {1}".format(self._name, page.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+        if page_is_exist is False:
             try:
                 self._logger.info("{0} : Creating posts : {1}".format(self._name, data["title"]))
                 page = self._request.post("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, headers=self._headers_json, data=json.dumps(data))

From 3718b807ba23883f852cda1776fc3eee6312beea Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Sun, 21 May 2023 21:14:36 +0200
Subject: [PATCH 15/19] more message debug

---
 lib/WPImport.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index 7b78cad..6e5ab5b 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -511,7 +511,7 @@ class WPimport:
         for index in range(1,10):
             params = {"search": title, "per_page":100, "page": index}
             try:
-                self._logger.info("{0} : Search post : {1}".format(self._name, title))
+                self._logger.info("{0} : Search post withi index {2} : {1}".format(self._name, title, index))
                 page = self._request.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params, headers=self._headers_json)
             except ConnectionError as err:
                 self._logger.error("{0} : Connection error for search post : {1}".format(self._name, err))
@@ -527,13 +527,13 @@ class WPimport:
                 self._logger.info("{0} : Number result posts : {1}".format(self._name, len(result)))
                 count = 0
                 for i in result:
-                
                     self._logger.info("{0} : Search title posts for |{2}| : |{1}|".format(self._name, i["title"]["rendered"], title))
                     title_rendered = i["title"]["rendered"].replace('&rsquo;', "'")
                     title_rendered = title_rendered.replace('&#8211;', '-')
                     title_rendered = title_rendered.replace('&#8230;', '...')
                     title_rendered = title_rendered.replace('« ', '"')
                     title_rendered = title_rendered.replace(' »', '"')
+                    self._logger.debug("{0} : Search title posts for |{2}| : |{1}|".format(self._name, title_rendered, title))
                     self._logger.debug("{0} : SIze of title : {1} - {2}".format(self._name, len(title), len(title_rendered)))
                     if title_rendered == title:
                         page_is_exist = True

From 0fc6e78a183067595387de247dffbd14b1f22010 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 23 May 2023 00:02:51 +0200
Subject: [PATCH 16/19] fix title rendered

---
 lib/WPImport.py | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index 6e5ab5b..dbffb0f 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -528,11 +528,17 @@ class WPimport:
                 count = 0
                 for i in result:
                     self._logger.info("{0} : Search title posts for |{2}| : |{1}|".format(self._name, i["title"]["rendered"], title))
-                    title_rendered = i["title"]["rendered"].replace('&rsquo;', "'")
-                    title_rendered = title_rendered.replace('&#8211;', '-')
-                    title_rendered = title_rendered.replace('&#8230;', '...')
-                    title_rendered = title_rendered.replace('« ', '"')
-                    title_rendered = title_rendered.replace(' »', '"')
+                    if len(i["title"]["rendered"]) == len(title):
+                        title_rendered = i["title"]["rendered"]
+                    else:
+                        title_rendered = i["title"]["rendered"].replace('&rsquo;', "'")
+                        title_rendered = title_rendered.replace('&#8211;', '-')
+                        title_rendered = title_rendered.replace('&#8230;', '...')
+                        title_rendered = title_rendered.replace('« ', '"')
+                        title_rendered = title_rendered.replace(' »', '"')
+                        title_rendered = title_rendered.replace('« ', '"')
+                        title_rendered = title_rendered.replace(' »', '"')
+                        title_rendered = title_rendered.replace('&#8217;', "'")
                     self._logger.debug("{0} : Search title posts for |{2}| : |{1}|".format(self._name, title_rendered, title))
                     self._logger.debug("{0} : SIze of title : {1} - {2}".format(self._name, len(title), len(title_rendered)))
                     if title_rendered == title:

From d3ec7d147d0476e9d26ea5ff76830624037579c6 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 23 May 2023 11:22:37 +0200
Subject: [PATCH 17/19] loop replace

---
 lib/WPImport.py | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index dbffb0f..bf04c98 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -506,6 +506,8 @@ class WPimport:
             self._logger.debug("{0} : {1}".format(page.content))
         if title[len(title)-1] == " ":
             title = title[:-1]
+        if title[0] == " ":
+            title = title[1:]
         page_is_exist = False
 
         for index in range(1,10):
@@ -531,14 +533,10 @@ class WPimport:
                     if len(i["title"]["rendered"]) == len(title):
                         title_rendered = i["title"]["rendered"]
                     else:
-                        title_rendered = i["title"]["rendered"].replace('&rsquo;', "'")
-                        title_rendered = title_rendered.replace('&#8211;', '-')
-                        title_rendered = title_rendered.replace('&#8230;', '...')
-                        title_rendered = title_rendered.replace('« ', '"')
-                        title_rendered = title_rendered.replace(' »', '"')
-                        title_rendered = title_rendered.replace('« ', '"')
-                        title_rendered = title_rendered.replace(' »', '"')
-                        title_rendered = title_rendered.replace('&#8217;', "'")
+                        title_rendered = i["title"]["rendered"]
+                        list_replace = {'&rsquo;': "'", '&#8211;': '-', '&#8230;': '...', '« ': '"', ' »': '"', '« ': '"', ' »': '"', '&#8217;': "'", '"&lsquo;': "'"}
+                        for old, new in list_replace.items():
+                            title_rendered = title_rendered.replace(old, new)
                     self._logger.debug("{0} : Search title posts for |{2}| : |{1}|".format(self._name, title_rendered, title))
                     self._logger.debug("{0} : SIze of title : {1} - {2}".format(self._name, len(title), len(title_rendered)))
                     if title_rendered == title:

From f69298179ad75ebc0d0e680500d6256560066766 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 23 May 2023 13:45:59 +0200
Subject: [PATCH 18/19] reduce line code and add private method

---
 lib/WPImport.py | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index bf04c98..b2af6d8 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -90,6 +90,23 @@ class WPimport:
     
     # Private method
 
+    ## replace caracter 
+
+    def _replaceCaracter(self, title_rendered):
+        list_replace = {'&rsquo;': "'", '&#8211;': '-', '&#8230;': '...', '« ': '"', ' »': '"', '« ': '"', ' »': '"', '&#8217;': "'", '"&lsquo;': "'"}
+        for old, new in list_replace.items():
+            title_rendered = title_rendered.replace(old, new)
+        return title_rendered
+
+    ## remove space 
+
+    def _removeSpace(self, title):
+        if title[len(title)-1] == " ":
+            title = title[:-1]
+        if title[0] == " ":
+            title = title[1:]
+        return title
+
     ## Get all files
 
     def _getFiles(self, item):
@@ -504,10 +521,7 @@ class WPimport:
         else:
             self._logger.error("{0} : Connection error with status code for get author : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(page.content))
-        if title[len(title)-1] == " ":
-            title = title[:-1]
-        if title[0] == " ":
-            title = title[1:]
+        title = self._removeSpace(title)
         page_is_exist = False
 
         for index in range(1,10):
@@ -529,14 +543,10 @@ class WPimport:
                 self._logger.info("{0} : Number result posts : {1}".format(self._name, len(result)))
                 count = 0
                 for i in result:
-                    self._logger.info("{0} : Search title posts for |{2}| : |{1}|".format(self._name, i["title"]["rendered"], title))
-                    if len(i["title"]["rendered"]) == len(title):
-                        title_rendered = i["title"]["rendered"]
-                    else:
-                        title_rendered = i["title"]["rendered"]
-                        list_replace = {'&rsquo;': "'", '&#8211;': '-', '&#8230;': '...', '« ': '"', ' »': '"', '« ': '"', ' »': '"', '&#8217;': "'", '"&lsquo;': "'"}
-                        for old, new in list_replace.items():
-                            title_rendered = title_rendered.replace(old, new)
+                    title_rendered = i["title"]["rendered"]
+                    self._logger.info("{0} : Search title posts for |{2}| : |{1}|".format(self._name, title_rendered, title))
+                    if len(title_rendered) != len(title):
+                        title_rendered = self._replaceCaracter(title_rendered)
                     self._logger.debug("{0} : Search title posts for |{2}| : |{1}|".format(self._name, title_rendered, title))
                     self._logger.debug("{0} : SIze of title : {1} - {2}".format(self._name, len(title), len(title_rendered)))
                     if title_rendered == title:

From 5c5dc707f5b7b4c8737a68d0b681ea3f122ece65 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Tue, 23 May 2023 16:46:07 +0200
Subject: [PATCH 19/19] fix headers search author

---
 lib/WPImport.py | 89 +++++++++++++++++++++++++++++++++----------------
 1 file changed, 61 insertions(+), 28 deletions(-)

diff --git a/lib/WPImport.py b/lib/WPImport.py
index b2af6d8..ba405ee 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -211,7 +211,7 @@ class WPimport:
     ## Add or update img 
 
     def _addOrUpdateMedia(self, href_img, page):
-        media_authorized = ["png", "jpg", "jpeg", "svg"]
+        media_authorized = ["png", "jpg", "jpeg", "svg", "gif"]
         media = {"id":"", "rendered":""}
         split_fileimg = href_img.split("/")
         img_name = split_fileimg[len(split_fileimg)-1]
@@ -455,33 +455,56 @@ class WPimport:
         for i in liste:
             for j in element[i]:
                 element_exist = False
-                try:
-                    params = {"params":j}
-                    page = self._request.get("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i), auth=self._basic, params=params)
-                except Exception as err:
-                    self._logger.error("{0} : Connection error for {1} : {2}".format(self._name, i, err))
-                    exit(1)
-                if page.status_code == 200:
-                    element_exist = True
-                    result = page.json()
-                    listelement[i].append(result[0]["id"])
-
-                else:
-                    self._logger.error("{0} : {1} not found due status code : {2}".format(self._name, i, page.status_code))
-                    self._logger.debug("{0} : {1}".format(self._name, page.content))
-
-
-                if element_exist is False:
-                    data = {"name": j}
-                    self._logger.debug("{0} : URL : {1} ".format("http://{1}/wp-json/wp/v2/{2}".format(self._name, self._wordpress, i)))
-                    self._logger.debug("{0} : data : {1}".format(self._name, data))
-                    self._logger.debug("{0} : headers : {1}".format(self._name, self._headers_form))
+                title_element = self._removeSpace(j)
+                for index in range(1,10):
+                    self._logger.info("{0} : search {1} with index {2} : {3}".format(self._name, i, index, title_element))
                     try:
-                        page = self._request.post("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i), auth=self._basic, headers=self._headers_json, data=data)
+                        params = {"search":title_element, "per_page":"100", "page":index}
+                        page = self._request.get("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i), auth=self._basic, params=params)
+                    except ConnectionError as err:
+                        self._logger.error("{0} : Connection error for {1} : {2}".format(self._name, i, err))
+                        exit(1)
                     except Exception as err:
+                        self._logger.error("{0} : Exception error for {1} : {2}".format(self._name, i, err))
+                    if page.status_code == 200:
+                        result = page.json()
+                        self._logger.debug("{0} : content {3} {2} : {1}".format(self._name, result, title_element, i))
+                        if len(result) > 0:
+                            for k in result:
+                                title_rendered = k["name"]
+                                self._logger.debug("{0} : content {2} : {1}".format(self._name, title_rendered, i))
+                                self._logger.debug("{0} : size of content {3} : {2} - {1}".format(self._name, len(title_rendered), len(title_element), i))
+                                if len(title_element) != len(title_rendered):
+                                    title_rendered = self._replaceCaracter(title_rendered)
+                        
+                                if title_element == title_rendered:    
+                                    self._logger.info("{0} : {1} found : {2}".format(self._name, i, title_rendered))
+                                    element_exist = True
+                                    listelement[i].append(k["id"])
+                        else:
+                            break
+                    if page.status_code == 400:
+                        self._logger.error("{0} : {1} not found due status code : {2}".format(self._name, i, page.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, page.content))
+                        break
+                    else:
+                        self._logger.error("{0} : {1} not found due status code : {2}".format(self._name, i, page.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+                self._logger.debug("{0} : Element {3} {2} is {1}".format(self._name, element_exist, title_element, i))
+                if element_exist == False:
+                    data = {"name": title_element}
+                    self._logger.info("{0} : Create {1} : {2}".format(self._name, i, title_element))
+                    self._logger.debug("{0} : Data : {1}".format(self._name, data))
+                    try:
+                        page = self._request.post("http://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
+                    except ConnectionError as err:
                         self._logger.error("{0} : Connection error for post {1} : {2}".format(self._name, i, err))
                         exit(1)
+                    except Exception as err:
+                        self._logger.error("{0} : Exception error for post {1} : {2}".format(self._name, i, err))
                     if page.status_code == 201:
+                        self._logger.info("{0} : {1} created : {2}".format(self._name, i, j))
                         result = page.json()
                         listelement[i].append(result["id"])
                     else:
@@ -504,30 +527,40 @@ class WPimport:
             bodyhtml = bodyhtml.replace(i["old_src"], o.path)
         hour = articledate[0].text
         time = dateheader[0].text.split(" ")
+        self._logger.debug("{0} : Title post : |{1}|".format(self._name, title))
+        title = self._removeSpace(title)
+        self._logger.debug("{0} : Rendered Title post : |{1}|".format(self._name, title))
+
         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"]}
+        self._logger.debug("{0} : Data for post : |{1}| : {2}" .format(self._name, title, data))
+
         params = {"search":author, "per_page":100}
         try:
             self._logger.info("{0} : Search author : {1}".format(self._name, author))
-            page = self._request.get("http://{0}/wp-json/wp/v2/users".format(self._wordpress), auth=self._basic, params=params)
+            page = self._request.get("http://{0}/wp-json/wp/v2/users".format(self._wordpress), auth=self._basic, headers=self._headers_json, params=params)
+            self._logger.debug("{0} : End Search author : {1}".format(self._name, author))
+            self._logger.debug("{0} : Debug requests : {1}".format(self._name, page.content))
+
+
         except ConnectionError as err:
             self._logger.error("{0} : Connection error for get author : {1}".format(self._name, err))
             exit(1)
         except Exception as err:
             self._logger.error("{0} : Exception error for get author : {1}".format(self._name, err))
         if page.status_code == 200:
-            self._logger.info("{0} : Get author id : {1}".format(self._name, result[0]["id"]))
+            self._logger.info("{0} : Get author id : {1}".format(self._name, result))
             result = page.json()
-            data["author"] = result[0]["id"]
+            for a in result:
+                data["author"] = a["id"]
         else:
             self._logger.error("{0} : Connection error with status code for get author : {1}".format(self._name, page.status_code))
             self._logger.debug("{0} : {1}".format(page.content))
-        title = self._removeSpace(title)
         page_is_exist = False
 
         for index in range(1,10):
             params = {"search": title, "per_page":100, "page": index}
             try:
-                self._logger.info("{0} : Search post withi index {2} : {1}".format(self._name, title, index))
+                self._logger.info("{0} : Search post with index {2} : {1}".format(self._name, title, index))
                 page = self._request.get("http://{0}/wp-json/wp/v2/posts".format(self._wordpress), auth=self._basic, params=params, headers=self._headers_json)
             except ConnectionError as err:
                 self._logger.error("{0} : Connection error for search post : {1}".format(self._name, err))