menu and submenu

Reviewed-on: #21

import_export_canalblog.py

@@ -10,10 +10,23 @@ from lib.WPImport import WPimport
 from lib.WPExport import WPExport
 from lib.WPRemove import WPRemove
 from lib.WPChange import WPChange
+from lib.WPMenu import WPMenu
 
-def change(index, number, args, logger):
+def errorRevert(logger, revert, tmp):
-    changeWp = WPChange(logger=logger, index_name=index, number_thread=number)
+    if revert is True:
-    changeWp.fromDirectory(args.directory)
+        files_tmp = glob.glob("{0}/*.json".format(tmp))
+        if len(files_tmp) == 0:
+            logger.error("Error revert, because files not found")
+            exit(1)
+        if len(files_tmp) != int(args.parallel):
+            for file_r in files_tmp:
+                os.remove(file_r)
+            logger.error("Error revert, because number files tmp is incompatible with parallel number")
+            exit(1)
+
+def change(index, number, args, logger, tmp, revert):
+    changeWp = WPChange(logger=logger, index_name=index, number_thread=number, tmp=tmp)
+    changeWp.fromDirectory(args.directory, revert)
 
     del changeWp
 
@@ -106,7 +119,7 @@ def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, bas
             del importWp
     
 
-def importDirectory(name_thread, max_thread, directory, logger, parser, wordpress, basic, serial, ssl_wordpress, create, update, image):
+def importDirectory(name_thread, max_thread, directory, logger, parser, wordpress, basic, serial, ssl_wordpress, create, update, image, revert):
     name = "Thread-{0}".format(int(name_thread) + 1)
     directory = directory.split(",")
     wordpress = wordpress.split(",")
@@ -114,7 +127,7 @@ def importDirectory(name_thread, max_thread, directory, logger, parser, wordpres
         for i in wordpress:
             importWp = WPimport(name=name, basic=basic, wordpress=i, logger=logger, parser=parser, ssl_wordpress=ssl_wordpress, no_create=create, no_update=update, no_image=image)
             for j in directory:
-                importWp.fromDirectory(j, name_thread, max_thread)
+                importWp.fromDirectory(j, name_thread, max_thread, revert)
                 del importWp
 
     else:
@@ -123,7 +136,7 @@ def importDirectory(name_thread, max_thread, directory, logger, parser, wordpres
             exit(1)
         for i in range(0, len(wordpress)-1):
             importWp = WPimport(name=name, basic=basic, wordpress=wordpress[i], logger=logger, parser=parser, ssl_wordpress=ssl_wordpress, no_create=create, no_update=update, no_image=image)
-            importWp.fromDirectory(directory[i])
+            importWp.fromDirectory(directory[i], name_thread, max_thread, revert)
             del importWp
 
 
@@ -190,8 +203,14 @@ if __name__ == '__main__':
     change_parser.add_argument("--file",
                       default="",
                       help="File")
-
     
+    menu_parser = subparsers.add_parser("menu")
+    menu_parser.add_argument("--user", help="wordpress user", required=True)
+    menu_parser.add_argument("--password", help="password wordpress's user", default="")
+    menu_parser.add_argument("--file", help="HTML file", default="")
+    menu_parser.add_argument("--canalblog", help="URL Canalblog", default="")
+    menu_parser.add_argument("--wordpress", help="URL Wordpress", required=True)
+
     args = parser.parse_args()
 
     logger = logging.getLogger('import export canalblog')
@@ -228,7 +247,7 @@ if __name__ == '__main__':
 
     os.makedirs(args.tmp, exist_ok=True)
 
-    if args.command == "import" or args.command == "remove":
+    if args.command == "import" or args.command == "remove" or args.command == "menu":
         password = args.password
         if len(args.password) == 0:
             password = getpass()
@@ -249,8 +268,9 @@ if __name__ == '__main__':
                 with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
                     wait_for = [ ex.submit(remove, i, args.parallel, args, basic, logger, ssl_wordpress) for i in range(0, int(args.parallel)) ]
                     wait(wait_for, return_when=ALL_COMPLETED)
+                    errorRevert(logger, args.revert, args.tmp)
                     wait_for = [
-                    ex.submit(importDirectory, i, int(args.parallel), args.directory, logger, args.parser, args.wordpress, basic, args.serial, ssl_wordpress, args.create, args.update, args.image)
+                    ex.submit(importDirectory, i, int(args.parallel), args.directory, logger, args.parser, args.wordpress, basic, args.serial, ssl_wordpress, args.create, args.update, args.image, args.revert)
                     for i in range(0, int(args.parallel))
                     ]
             except Exception as err:
@@ -260,15 +280,7 @@ if __name__ == '__main__':
                 with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
                     wait_for = [ ex.submit(remove, i, args.parallel, args, basic, logger, ssl_wordpress) for i in range(0, int(args.parallel)) ]
                     wait(wait_for, return_when=ALL_COMPLETED)
-                    if args.revert is True:
+                    errorRevert(logger, args.revert, args.tmp)
-                        files_tmp = glob.glob("{0}/*.json".format(args.tmp))
-                        if len(files_tmp) == 0:
-                            logger.error("Error revert, because files not found")
-                            exit(1)
-                        if len(files_tmp) != int(args.parallel):
-                            for file_r in files_tmp:
-                                os.remove(file_r)
-                        
                     wait_for = [
                     ex.submit(importUrl, i, int(args.parallel), args.canalblog, logger, args.parser, args.wordpress, basic, args.serial, ssl_wordpress, ssl_canalblog, args.create, args.update, args.image, args.revert, args.tmp)
                     for i in range(0, int(args.parallel))
@@ -328,11 +340,20 @@ if __name__ == '__main__':
         if len(args.directory) > 0:
             try:
                 with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
-                    wait_for = [ ex.submit(change, i, args.parallel, args, logger) for i in range(0, int(args.parallel)) ]
+                    errorRevert(logger, args.revert, args.tmp)
+                    wait_for = [ ex.submit(change, i, args.parallel, args, logger, args.tmp, args.revert) for i in range(0, int(args.parallel)) ]
             except Exception as err:
                 logger.error("Thread error for remove : {0}".format(err))
         if len(args.file) > 0:
             changeWp = WPChange(logger=logger)
             for filei in args.file.split(","):
                 changeWp.fromFile(filei)
+        exit(0)
+    
+    if args.command == "menu":
+        menuWp = WPMenu(name="Thread-1", basic=basic, wordpress=args.wordpress, logger=logger, parser=args.parser, ssl_canalblog=ssl_canalblog, ssl_wordpress=ssl_wordpress)    
+        if len(args.file) > 0:
+            menuWp.fromFile(args.file)
+        if len(args.canalblog) > 0:
+            menuWp.fromUrl(args.canalblog)
         exit(0)

lib/WPChange.py

@@ -4,11 +4,13 @@ import requests, os, logging, re, json
 
 class WPChange:
     # Constructor
-    def __init__(self, index_name=1, number_thread=1, logger=None, parser="html.parser"):
+    def __init__(self, index_name=1, number_thread=1, logger=None, parser="html.parser", tmp="/tmp/import_export_canablog"):
         self._name = "Thread-{0}".format(index_name)
         self._logger = logger
         self._number_thread = number_thread
         self._parser = parser
+        self._tmp = tmp
+        self._index_name = index_name
     
     # Destructor 
     def __del__(self):
@@ -37,19 +39,62 @@ class WPChange:
                 
 
     ## From directory
-    
+
-    def fromDirectory(self, directory="", number_thread=1, max_thread=1):
+
+    def fromDirectory(self, directory="", revert=False):
+        self._directory = directory
         directory = "{0}/archives".format(directory)
         directories = self._getDirectories([], "{0}".format(directory))
         if len(directories) > 0:
             files = self._getFiles(directories)
-            self.fromFile(files, number_thread, max_thread)
+            if revert is False:
+                self._tmpFiles(files=files, number_thread=self._index_name, max_thread=self._number_thread)
+            self._fromFileTmp()
         else:
             self._logger.error("{0} : No files for {1}".format(self._name, directory))
+    
+
+    def fromFile(self, files=[]):
+        for i in range(0, len(files)):
+            if os.path.exists(files[i]):
+                self._logger.info("{0} : ({1}/{2}) File is being processed : {3}".format(self._name, i+1, len(files), files[i]))
+                self._change(files[i])
 
 
     # Private method
 
+    def _fromFileTmp(self):
+        try:
+            with open("{0}/{1}.json".format(self._tmp, self._name)) as file:
+                files = json.loads(file.read())
+                self._logger.debug("{0} : size of webpage : {1}".format(self._name, len(files)))
+                for i in range(0, len(files)):
+                    if os.path.exists(files[i]):
+                        self._logger.info("{0} : ({1}/{2}) File is being processed : {3}".format(self._name, i+1, len(files), files[i]))
+                        self._change(files[i])
+        except Exception as ex:
+            self._logger.error("{0} : Read file json from tmp : {1}".format(self._name, ex))
+
+
+    def _tmpFiles(self, files=[], number_thread=1, max_thread=1):
+        print()
+        divFiles = int(len(files) / int(max_thread))
+        currentRangeFiles = int(divFiles * (int(number_thread)+1))
+        firstRange = int(currentRangeFiles - divFiles)
+        self._logger.debug("{0} : index : {1}".format(self._name,number_thread))
+
+        self._logger.debug("{0} : first range : {1}".format(self._name,firstRange))
+        self._logger.debug("{0} : last range : {1}".format(self._name,currentRangeFiles))
+        webpage = []
+        for i in range(firstRange, currentRangeFiles):
+            webpage.append(files[i])
+        
+        try:
+            string_webpage = json.dumps(webpage)
+            open("{0}/{1}.json".format(self._tmp, self._name), "wt").write(string_webpage)
+        except Exception as ex:
+            self._logger.error("{0} : Error for writing webpage : {1}".format(self._name, ex))
+
     ## Get all files
 
     def _getFiles(self, item):

lib/WPImport.py

@@ -74,33 +74,23 @@ class WPimport:
             self._logger.error("{0} : Read file json from tmp : {1}".format(self._name, ex))
 
 
-    def fromDirectory(self, directory="", number_thread=1, max_thread=1):
+    def fromDirectory(self, directory="", number_thread=1, max_thread=1, revert=False):
         self._directory = directory
         directory = "{0}/archives".format(directory)
         directories = self._getDirectories([], "{0}".format(directory))
         if len(directories) > 0:
             files = self._getFiles(directories)
-            self.fromFile(files=files, number_thread=number_thread, max_thread=max_thread)
+            if revert is False:
+                self._tmpFiles(files=files, number_thread=number_thread, max_thread=max_thread)
+            self._fromFileTmp()
         else:
             self._logger.error("{0} : No files for {1}".format(self._name, directory))
     
-            
 
-
+    def fromFile(self, files=[]):
-        
+        for i in range(0, len(files)):
-
-    def fromFile(self, files=[], number_thread=1, max_thread=1):
-        divFiles = int(len(files) / max_thread)
-        currentRangeFiles = int(divFiles * (number_thread+1))
-        firstRange = int(currentRangeFiles - divFiles)
-        self._logger.debug("{0} : index : {1}".format(self._name,number_thread))
-
-        self._logger.debug("{0} : first range : {1}".format(self._name,firstRange))
-        self._logger.debug("{0} : last range : {1}".format(self._name,currentRangeFiles))
-
-        for i in range(firstRange, currentRangeFiles):
             if os.path.exists(files[i]):
-                self._logger.info("{0} : ({1}/{2}) File is being processed : {3}".format(self._name, i+1, currentRangeFiles + 1, files[i]))
+                self._logger.info("{0} : ({1}/{2}) File is being processed : {3}".format(self._name, i+1, len(files), 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)))
@@ -111,10 +101,52 @@ class WPimport:
                         self._addOrUpdatePost(soup)
                     else:
                         self._addOrUpdateFeaturedMedia(soup)
+        
     
     
     # Private method
 
+    def _fromFileTmp(self):
+        try:
+            with open("{0}/{1}.json".format(self._tmp, self._name)) as file:
+                files = json.loads(file.read())
+                self._logger.debug("{0} : size of webpage : {1}".format(self._name, len(files)))
+                for i in range(0, len(files)):
+                    if os.path.exists(files[i]):
+                        self._logger.info("{0} : ({1}/{2}) File is being processed : {3}".format(self._name, i+1, len(files), 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)))
+                            if len(articlebody) > 0:
+                                self._addOrUpdatePost(soup)
+                            else:
+                                self._addOrUpdateFeaturedMedia(soup)
+        except Exception as ex:
+            self._logger.error("{0} : Read file json from tmp : {1}".format(self._name, ex))
+
+
+    def _tmpFiles(self, files=[], number_thread=1, max_thread=1):
+        divFiles = int(len(files) / max_thread)
+        currentRangeFiles = int(divFiles * (number_thread+1))
+        firstRange = int(currentRangeFiles - divFiles)
+        self._logger.debug("{0} : index : {1}".format(self._name,number_thread))
+
+        self._logger.debug("{0} : first range : {1}".format(self._name,firstRange))
+        self._logger.debug("{0} : last range : {1}".format(self._name,currentRangeFiles))
+        webpage = []
+        for i in range(firstRange, currentRangeFiles):
+            webpage.append(files[i])
+        
+        try:
+            string_webpage = json.dumps(webpage)
+            open("{0}/{1}.json".format(self._tmp, self._name), "wt").write(string_webpage)
+        except Exception as ex:
+            self._logger.error("{0} : Error for writing webpage : {1}".format(self._name, ex))
+
+
     ## replace caracter 
 
     def _replaceCaracter(self, title_rendered):

lib/WPMenu.py

@@ -0,0 +1,136 @@
+#!/usr/bin/python3
+
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse
+import requests, os, logging, re, json
+from requests.adapters import HTTPAdapter
+from requests.packages.urllib3.util.retry import Retry
+
+class WPMenu:
+    # Constructor
+    def __init__(self, name="Thread-0", basic=None, canalblog="", wordpress="", logger=None, parser="html.parser", ssl_canalblog=True, ssl_wordpress=True):
+        self._name = name
+        self._basic = basic
+        self._canalblog = canalblog
+        self._wordpress = wordpress
+        self._logger = logger
+        self._parser = parser
+        self._headers_json = {'Content-Type': 'application/json; charset=utf-8', 'Accept':'application/json'}
+        self._protocol_wordpress = "https"
+        self._protocol_canalblog = "https"
+        self._directory = "backup"
+
+        if ssl_wordpress is False:
+            self._protocol_wordpress = "http"
+        if ssl_canalblog is False:
+            self._protocol_canalblog = "http"
+        self._request_canalblog = requests.Session()
+        self._request_wordpress = requests.Session()
+
+        retries = Retry(connect=10, read=10, redirect=5,
+                status_forcelist=[429, 500, 502, 503, 504], backoff_factor=2)
+
+        self._request_canalblog.mount('{0}://'.format(self._protocol_canalblog), HTTPAdapter(max_retries=retries))
+        self._request_wordpress.mount('{0}://'.format(self._protocol_wordpress), HTTPAdapter(max_retries=retries))
+
+    
+    # Destructor 
+    def __del__(self):
+        print("{0} : Import finished for {1}".format(self._name, self._wordpress))
+
+    # Public method
+
+    ## From file 
+
+    def fromFile(self, files):
+        if os.path.exists(files):
+            with open(files, 'r') as f:
+                self._logger.info("{0} : File is being processed : {1}".format(self._name, files))
+                content = f.read()
+                self._menu(content)
+        else:
+            self._logger.error("{0} : File isn't exist : {1}".format(self._name, files))
+
+
+
+    ## Get from URL
+
+    def fromUrl(self, canalblog):
+        self._canalblog = canalblog
+        try:
+            o = urlparse(canalblog)
+            o = o._replace(scheme=self._protocol_canalblog)
+            i = o.geturl().replace(":///", "://")
+            page = self._request_canalblog.get(i)
+            if page.status_code == 200:
+                self._logger.info("{0} : Page web is being processed : {1}".format(self._name, i))
+                self._menu(page.content)
+            else:
+                self._logger.error("{0} : index didn't get due status code : {1}".format(self._name, page.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, page.content))
+        except ConnectionError as err:
+            self._logger.error("{0} : Connection error for get url {1} : {2}".format(self._name, canalblog, err))
+            exit(1)        
+        except Exception as err:
+            self._logger.error("{0} : Exception error for get url {1} : {2}".format(self._name, canalblog, err))
+
+    def _getId(self, title, parent):
+        menu = {"id":"", "type":"", "title": "", "parent":"", "children": []}
+        exist = False
+        for i in ["categories", "tags"]:
+            if exist is False:
+                try:
+                    params = {"search":title, "per_page":"100"}
+                    page = self._request_wordpress.get("{2}://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i, self._protocol_wordpress), auth=self._basic, params=params)
+                    if page.status_code == 200:
+                        result = page.json()
+                        if len(result) > 0:
+                            menu = {"id":result[0]["id"], "type":i, "title": title, "parent":parent, "children": []}
+                            exist = True
+                    else:
+                        self._logger.error("{0} : {2} didn't get due status code : {1}".format(self._name, page.status_code, i))
+                        self._logger.debug("{0} : {1}".format(self._name, page.content))
+                except ConnectionError as err:
+                    self._logger.error("{0} : Connection error for get url {1} : {2}".format(self._name, "{2}://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i, self._protocol_wordpress), err))
+                    exit(1)        
+                except Exception as err:
+                    self._logger.error("{0} : Exception error for get url {1} : {2}".format(self._name, "{2}://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i, self._protocol_wordpress), err))
+        return menu
+    
+    def _menu(self, content):
+
+        soup = BeautifulSoup(content, self._parser)
+        ul = soup.find("ul", id="listsmooth")
+        menu = list()
+        children = list()
+        for anchor in ul.find_all("li"):
+
+            parent = anchor.find("a").get_text().replace(" \xa0", "")
+            href = anchor.find("a").get("href")
+            if href == "{0}://{1}/".format(self._protocol_canalblog, self._canalblog):
+                parent = "home"
+            itemMenu = {"id":"", "type":"", "title": parent, "children":list()}
+            
+            
+            #menu = self._child(parent, parent)
+            if href == "#":
+                li = anchor.find("ul").find_all("li")
+                for child in li:
+                    a = child.find("a")
+                    self._logger.info("{0} Parent {1} : Child {2}".format(self._name, parent, a.get_text()))
+                    children.append({"title": a.get_text(), "parent": parent})
+            menu.append(itemMenu)
+
+        
+        for i in range(0, len(children)-1):
+            self._logger.info("{0} : Child {1}".format(self._name, children[i]))
+            for j in range(0, len(menu)-1):
+                if menu[j]["title"] == children[i]["title"]:
+                    self._logger.info("{0} : Parent  {1}".format(self._name, menu[j]))
+                    del menu[j]
+            for j in range(0, len(menu)-1):
+                if menu[j]["title"] == children[i]["parent"]:
+                    menu[j]["children"].append({"id":"", "title":children[i]["title"], "parent": children[i]["parent"]})
+
+        for i in menu:
+            self._logger.info("{0} : Menu {1} {2}".format(self._name, i["title"], len(i["children"])))