import_export_canalblog.py

@@ -36,7 +36,6 @@ def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, bas
                 exit(1)
             exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser)
             webpage = exportWp.getUrlPage(name_thread, max_thread)
-        
             for j in wordpress:
                 importWp = WPimport(name=name, basic=basic, wordpress=j, logger=logger, parser=parser)
                 importWp.fromUrl(webpage)
@@ -60,8 +59,7 @@ def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, bas
 
 def importDirectory(name_thread, max_thread, directory, logger, parser, wordpress, basic, serial):
     name = "Thread-{0}".format(int(name_thread) + 1)
-    directory = directory.split(",")
-    wordpress = wordpress.split(",")
+    directory = args.directory.split(",")
     if serial is False:
         for i in wordpress:
             importWp = WPimport(name=name, basic=basic, wordpress=i, logger=logger, parser=parser)

lib/WPExport.py

@@ -103,7 +103,7 @@ class WPExport:
 
                         setPageDivided = int(number_lastpage) / max_thread
                         setPagePart = setPageDivided * (index_thread + 1)
-                        firstPagePart = (setPagePart - setPageDivided)
+                        firstPagePart = (setPagePart - setPageDivided) + 1
 
                         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)))

lib/WPImport.py

@@ -36,7 +36,7 @@ class WPimport:
                 self._logger.error("{0} : Connection error for get url {1} : {2}".format(self._name, webpage[i], err))
                 exit(1)
             if r.status_code == 200:
-                self._logger.info("{0} : ({1}/{2}) : Page is importing : {3}".format(self._name, i+1, len(webpage), webpage[i]))
+                self._logger.info("{0} : ({1}/{2} : Page is importing : {3}".format(self._name, i+1, len(webpage), webpage[i]))
                 soup = BeautifulSoup(r.content, self._parser)
                 articlebody = soup.find_all("div", class_="articlebody")
                 if len(articlebody) > 0:
@@ -72,7 +72,6 @@ class WPimport:
                 self._logger.info("{0} : File is being processed : {1}".format(self._name, files[i]))
                 with open(files[i], 'r') as f:
                     content = f.read()
-                    self._logger.debug("{0} : Size of article : {1}".format(self._name, len(content)))
                     soup = BeautifulSoup(content, self._parser)
                     articlebody = soup.find_all("div", class_="articlebody")
                     self._logger.debug("{0} : Number of article : {1}".format(self._name, len(articlebody)))
@@ -190,14 +189,12 @@ class WPimport:
         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:
@@ -362,7 +359,6 @@ class WPimport:
             listelement[i] = []
 
         articletitle = soup.find_all("h2", class_="articletitle")
-        self._logger.debug("{0} : Title of the article : {1}".format(self._name, articletitle))
         articlebody = soup.find_all("div", class_="articlebody")
         articledate = soup.find_all("span", class_="articledate")
         articleacreator = soup.find_all("span", class_="articlecreator")
@@ -370,12 +366,10 @@ class WPimport:
         itemfooter = soup.find_all("div", class_="itemfooter")
         comment = soup.find_all("li", class_="comment")
         img_a = articlebody[0].find_all("a", {"target": "_blank"})
-        self._logger.debug("{0} : Number of image's link : {1}".format(self._name, len(img_a)))
         list_img = []
         for i in img_a:
             new_img = {}
             img = i.find_all("img")
-            self._logger.debug("{0} : Number of image's tag : {1}".format(self._name, len(img)))
             if len(img) > 0:
                 href_a = i.get("href")
                 href_img = img[0].get("src")
@@ -393,7 +387,7 @@ class WPimport:
                     except Exception as err:
                         self._logger.error("{0} : Connection error for get image : {1}".format(self._name, err))
                         exit(1)
-                self._logger.debug("{0} : Status code for image {1} : {2}".format(self._name, href_img, page_img.status_code))
+                
                 if page_img.status_code == 200:
                     media=self._addOrUpdateMedia(href_img, page_img)
                     new_img["id"]=media["id"]
@@ -408,7 +402,7 @@ class WPimport:
                     self._logger.error("{0} : Connection error with status code for get image : {1}".format(self._name, page_img.status_code))
                     self._logger.debug("{0} : {1}".format(self._name, page_img.content))
 
-        self._debug("{0} : Number of image : {1}".format(self._name, len(list_img)))
+                
         comment_post = self._getComment(comment)
 
         a = itemfooter[0].find_all("a", {"rel": True})