From 7b154e3a1dbae8896f82c2dbb6a3a333daeadc40 Mon Sep 17 00:00:00 2001
From: Valentin CZERYBA <valcze80@gmail.com>
Date: Thu, 31 Aug 2023 22:50:31 +0200
Subject: [PATCH] add author

---
 import_export_canalblog.py |  2 +-
 lib/WPImport.py            | 19 ++++++++++++++-----
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/import_export_canalblog.py b/import_export_canalblog.py
index d5d2a18..eca7e72 100644
--- a/import_export_canalblog.py
+++ b/import_export_canalblog.py
@@ -259,7 +259,7 @@ if __name__ == '__main__':
         basic = HTTPBasicAuth(args.user, password)
     if args.command == "import":
         wordpress = args.wordpress.split(",")
-        importWp = WPimport(basic=basic, wordpress="", logger=logger, parser=args.parser, ssl_wordpress=ssl_wordpress, author=args.author)
+        importWp = WPimport(basic=basic, wordpress="", logger=logger, parser=args.parser, ssl_wordpress=ssl_wordpress, author=args.author, ssl_canalblog=ssl_canalblog)
         if len(args.file) > 0:
             for i in wordpress:
                 importWp.setUrl(i)
diff --git a/lib/WPImport.py b/lib/WPImport.py
index b3e5d80..56c51a7 100644
--- a/lib/WPImport.py
+++ b/lib/WPImport.py
@@ -8,7 +8,7 @@ from requests.packages.urllib3.util.retry import Retry
 
 class WPimport:
     # Constructor
-    def __init__(self, name="Thread-0", basic=None, wordpress="", logger=None, parser="html.parser", ssl_wordpress=True, no_create=False, no_update=False, no_image=False, tmp="/tmp/import_export_canablog", author=""):
+    def __init__(self, name="Thread-0", basic=None, wordpress="", logger=None, parser="html.parser", ssl_wordpress=True, no_create=False, no_update=False, no_image=False, tmp="/tmp/import_export_canablog", author="", ssl_canalblog=True):
         self._name = name
         self._basic = basic
         self._wordpress = wordpress
@@ -20,7 +20,7 @@ class WPimport:
         if ssl_wordpress is False:
             self._protocol = "http"
         self._request = requests.Session()
-
+        self._ssl_canalblog = ssl_canalblog
         retries = Retry(connect=10, read=10, redirect=5,
                 status_forcelist=[429, 500, 502, 503, 504], backoff_factor=2)
 
@@ -140,6 +140,8 @@ class WPimport:
         return author
 
     def _getInfoAlbum(self, link):
+        if self._ssl_canalblog:
+            link = link.replace("http", "https")
         self._logger.info("{0} : Info album : {1}".format(self._name, link))
         link_o = urlparse(link)
         if len(link_o.netloc) > 0:
@@ -147,7 +149,7 @@ class WPimport:
             try:
                 response = self._request.get(link)
                 if response.status_code == 200:
-                    self._logger.info("{0} : get content info from web : {1}".format(self._name, link_o))
+                    self._logger.info("{0} : get content info from web : {1}".format(self._name, link))
                     page_img = response.content
             except ConnectionError as err:
                 self._logger.error("{0} : Connection error for get album info : {1}".format(self._name, err))
@@ -159,9 +161,15 @@ class WPimport:
             self._logger.info("{0} : get album info from file : {1}".format(self._name, link_o))
             if os.path.exists("{0}/..{1}".format(self._directory, link_o)):
                 page_img = open("{0}/..{1}".format(self._directory, link_o), "r")
-        soup = BeautifulSoup(content, self._parser)
+        soup = BeautifulSoup(page_img, self._parser)
         paragraph = soup.find("div", class_="albumbody").find("p")
-        author = paragraph.split("<br>")[1].split(":")[1].replace(" ", "").lower()
+        self._logger.info("{0} get paragraph : {1}".format(self._name, paragraph))
+        split_paragraph = str(paragraph).split("<br>")
+        self._logger.info("{0} length paragraph splitted : {1}".format(self._name, len(split_paragraph)))
+        if len(split_paragraph) == 1:
+            split_paragraph = str(paragraph).split("<br/>")
+        self._logger.info("{0} get paragraph splitted : {1}".format(self._name, split_paragraph))
+        author = split_paragraph[1].split(":")[1].replace(" ", "").lower()
         return author
 
 
@@ -226,6 +234,7 @@ class WPimport:
                     for i in link_a:
                         if re.search(r"/albums/", i.get("href", "/")):
                             href_a = i.get("href", "/")
+                            break
                     author = self._getInfoAlbum(href_a)
                     self._logger.info("{0} : author : {1}".format(self._name, author))
                     self._getAuthor(author)