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="")
 
 
 

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

@@ -237,7 +237,9 @@ class WPimport:
                             break
                     author = self._getInfoAlbum(href_a)
                     self._logger.info("{0} : author : {1}".format(self._name, author))
-                    self._getAuthor(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))
@@ -849,7 +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: