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", help="Define author for page album", default="")
+    import_parser.add_argument("--author", dest="author", help="Define author", default="")
 
 
 
@@ -259,12 +259,11 @@ 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)
                 importWp.fromFile(files=args.file.split(","))
-                exit(0)
                 menuWp = WPMenu(name="Thread-1", basic=basic, wordpress=args.wordpress, logger=logger, parser=args.parser, ssl_canalblog=ssl_canalblog, ssl_wordpress=ssl_wordpress)    
                 menuWp.fromFile("{0}".format(args.file.split(",")[0]))
         if len(args.directory) > 0:

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])
-        o = urlparse(self._url)
-        self._downloadPage(page_src, "{0}/{1}/{2}".format(self._dir, o.path, "img"))
+        try:
+            with open("{0}/{1}.json".format(self._tmp, self._name)) as file:
+                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:
-                        data = {"title":albumtitle, "content":content_html, "status":"publish", "author":author}
+                else:
+                    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}
@@ -807,6 +852,8 @@ class WPimport:
 
         title = articletitle[0].text
         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:

lib/WPMenu.py

@@ -85,19 +85,28 @@ class WPMenu:
     def _getIdfromTitlePost(self, content):
         idMenu = {"id":0, "type":"", "link":""}
         soup = BeautifulSoup(content, self._parser)
-        articletitle = soup.find("h2", class_="articletitle").get_text()
+        articletitle = soup.find_all("h2", class_="articletitle")
+        if len(articletitle) > 0:
+            articletitle = articletitle[0].get_text()
+        search = "posts"
+        post_type = "post"
         if len(articletitle) == 0:
-            articletitle = soup.find("div", class_="albumbody").find("h2").get_text()
+            articletitle = soup.find_all("div", class_="albumbody")
+            if len(articletitle) > 0:
+                articletitle = articletitle[0].find("h2").get_text()
+                search = "pages"
+                post_type = "page"
+
         exist = False
         for index in range(1,10):
             if exist is False:
                 params = {"search":articletitle, "per_page":100, "page":index}
                 try:
-                    self._logger.debug("{0} : Get Url for post : {1} {2}".format(self._name, "{1}://{0}/wp-json/wp/v2/posts".format(self._wordpress, self._protocol_wordpress), params))
-                    page = self._request_wordpress.get("{1}://{0}/wp-json/wp/v2/posts".format(self._wordpress, self._protocol_wordpress), auth=self._basic, params=params)
+                    self._logger.debug("{0} : Get Url for {3} : {1} {2}".format(self._name, "{1}://{0}/wp-json/wp/v2/{2}".format(self._wordpress, self._protocol_wordpress, search), params, search))
+                    page = self._request_wordpress.get("{1}://{0}/wp-json/wp/v2/{2}".format(self._wordpress, self._protocol_wordpress, search), auth=self._basic, params=params)
                     if page.status_code == 200:
                         result = page.json()
-                        self._logger.info("{0} : Get content post : {1}".format(self._name, len(result)))
+                        self._logger.info("{0} : Get content {2} : {1}".format(self._name, len(result), search))
                         if len(result) > 0:
                             for i in result:
                                 title_rendered = i["title"]["rendered"]
@@ -105,8 +114,8 @@ class WPMenu:
                                     title_rendered = self._replaceCaracter(title_rendered)
                                 self._logger.debug("{0} : comparaison debug {1} {2}".format(self._name, articletitle, title_rendered))
                                 if articletitle == title_rendered:
-                                    self._logger.debug("{0} : get post id : {1}".format(self._name, i))
-                                    idMenu = {"id":i["id"], "type":"post", "link": i["link"]}
+                                    self._logger.debug("{0} : get {2} id : {1}".format(self._name, i, search))
+                                    idMenu = {"id":i["id"], "type":post_type, "link": i["link"]}
                                     exist = True
                         else:
                             self._logger.debug("{0} : {2} {1}".format(self._name, result, len(result)))
@@ -156,13 +165,18 @@ class WPMenu:
         idMenu = {"id":0, "type":"", "link":""}
         if href != "#":
             title = href[::-1]
+            second_title = title.split("/")[2]
+            second_title = second_title[::-1]
             link = title.split("/")[0]
             link = link[::-1]
             title = title.split("/")[1]
             title = title[::-1]
             self._logger.info("{0} link {1} title {2}".format(self._name, link, title))
             if link == "index.html":
-                idMenu = self._getId(title)
+                if second_title == "albums":
+                    idMenu = self._getIdFromPost(href)
+                else:
+                    idMenu = self._getId(title)
             else:
                 idMenu = self._getIdFromPost(href)