Merge pull request 'fix webpage' (#25) from fix-export into master

Reviewed-on: #25

import_export_canalblog.py

@@ -55,7 +55,7 @@ def remove(index, number, args, basic, logger, ssl_wordpress):
 
 def download(name_thread, max_thread, url, logger, parser, directory, html, img, ssl_canalblog, revert, tmp):
     exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, directory=directory, ssl_canalblog=ssl_canalblog)    
-    if not revert:
+    if revert is False:
         exportWp.getUrlPage(name_thread, max_thread)
     for i in ["article", "page"]:
         for j in ["publications", "principal"]:
@@ -170,7 +170,7 @@ if __name__ == '__main__':
     import_parser.add_argument("--no-create", help="No create post", dest="create", default="store_false", action="store_true")
     import_parser.add_argument("--no-update", help="No update post", dest="update", default="store_false", action="store_true")
     import_parser.add_argument("--no-image", help="No image add or update", dest="image", default="store_false", action="store_true")
-    import_parser.add_argument("--author-album", dest=author, help="Define author for page album", default="")
+    import_parser.add_argument("--author", dest="author", help="Define author", default="")
 
 
 
@@ -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)

lib/WPExport.py

@@ -58,14 +58,26 @@ class WPExport:
     # Download HTML
 
     def downloadHTML(self, first, second):
-        self._downloadPage(webpage[first][second], self._dir)
+        try:
+            with open("{0}/{1}.json".format(self._tmp, self._name)) as file:
+                webpage = json.loads(file.read())
+                self._downloadPage(webpage[first][second], self._dir)
+        except Exception as ex:
+            self._logger.error("{0} : Read file json from tmp : {1}".format(self._name, ex))
 
     # Download Image
     
     def downloadImg(self, first, second):
-        page_src = self._getImg(webpage[first][second])
+        try:
-        o = urlparse(self._url)
+            with open("{0}/{1}.json".format(self._tmp, self._name)) as file:
-        self._downloadPage(page_src, "{0}/{1}/{2}".format(self._dir, o.path, "img"))
+                webpage = json.loads(file.read())
+                page_src = self._getImg(webpage[first][second])
+                o = urlparse(self._url)
+                self._downloadPage(page_src, "{0}/{1}/{2}".format(self._dir, o.path, "img"))
+        except Exception as ex:
+            self._logger.error("{0} : Read file json from tmp : {1}".format(self._name, ex))
+
+
 
 
      # Get URL

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)
 
@@ -139,6 +139,40 @@ class WPimport:
             self._logger.error("{0} : Exception error for get author : {1}".format(self._name, err))
         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:
+            self._logger.info("{0} : get album info from web : {1}".format(self._name, link_o))
+            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))
+                    page_img = response.content
+            except ConnectionError as err:
+                self._logger.error("{0} : Connection error for get album info : {1}".format(self._name, err))
+                exit(1)
+            except Exception as err:
+                self._logger.error("{0} : Exception error for get album info : {1}".format(self._name, err))
+                exit(1)
+        else:
+            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(page_img, self._parser)
+        paragraph = soup.find("div", class_="albumbody").find("p")
+        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
+
+
     def _addOrUpdateAlbum(self, soup):
         self._logger.info("{0} : Add/Update Album".format(self._name))
         albumbody = soup.find("div", class_="albumbody")
@@ -195,8 +229,19 @@ class WPimport:
                 data = {"title":albumtitle, "content":content_html, "status":"publish"}
                 if len(self._author) > 0:
                     author = self._getAuthor(self._author)
-                    if author != 0:
+                else:
-                        data = {"title":albumtitle, "content":content_html, "status":"publish", "author":author}
+                    link_a = albumbody.find_all("a")
+                    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))
+                    author = self._getAuthor(author)
+                data = {"title":albumtitle, "content":content_html, "status":"publish"}
+
+                if author != 0:
+                     data = {"title":albumtitle, "content":content_html, "status":"publish", "author":author}
                 self._logger.debug("{0} : data for album page : {1}".format(self._name, data))
                 for index in range(1,10):
                     params = {"search": albumtitle, "per_page":100, "page": index}
@@ -806,7 +851,9 @@ class WPimport:
                         self._logger.error("{0} : Exception error for post {1} : {2}".format(self._name, i, err))
 
         title = articletitle[0].text
-        author = articleacreator[0].text.lower()        
+        author = articleacreator[0].text.lower()
+        if len(self._author) > 0:
+            author = self._author   
         body = articlebody[0].find_all("p")
         bodyhtml = "<p>"
         for i in body: