Merge pull request 'webpage-file' (#20) from webpage-file into master

Reviewed-on: #20

import_export_canalblog.py

@@ -5,7 +5,7 @@ from urllib.parse import urlparse
 from concurrent import futures
 from concurrent.futures import as_completed, wait, ALL_COMPLETED
 
-import argparse, logging, threading
+import argparse, logging, threading, os, glob
 from lib.WPImport import WPimport
 from lib.WPExport import WPExport
 from lib.WPRemove import WPRemove
@@ -40,21 +40,21 @@ def remove(index, number, args, basic, logger, ssl_wordpress):
     del removeWp
 
 
-def download(name_thread, max_thread, url, logger, parser, directory, html, img, ssl_canalblog):
+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)    
-    webpage = exportWp.getUrlPage(name_thread, max_thread)
+    if not revert:
+        exportWp.getUrlPage(name_thread, max_thread)
     for i in ["article", "page"]:
         for j in ["publications", "principal"]:
             if html is False:
-                exportWp.downloadHTML(webpage[j][i])
+                exportWp.downloadHTML(j, i)
 
             if img is False:
-                exportWp.downloadImg(webpage[j][i])
+                exportWp.downloadImg(j, i)
+    del exportWp
 
 
-
+def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, basic, serial, ssl_wordpress, ssl_canalblog, create, update, image, revert, tmp):
-
-def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, basic, serial, ssl_wordpress, ssl_canalblog, create, update, image):
     canalblog = canalblog.split(",")
     wordpress = wordpress.split(",")
     name = "Thread-{0}".format(int(name_thread) + 1)
@@ -70,14 +70,15 @@ def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, bas
             except Exception as err:
                 logger.error("{0} : parsing error : {1}".format(name, err))
                 exit(1)
-            exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, ssl_canalblog=ssl_canalblog)
+            exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, ssl_canalblog=ssl_canalblog, tmp=tmp)
-            webpage = exportWp.getUrlPage(name_thread, max_thread)
+            if not revert:
+                exportWp.getUrlPage(name_thread, max_thread)
             del exportWp
             for j in wordpress:
-                importWp = WPimport(name=name, basic=basic, wordpress=j, logger=logger, parser=parser, ssl_wordpress=ssl_wordpress, no_create=create, no_update=update, no_image=image)
+                importWp = WPimport(name=name, basic=basic, wordpress=j, logger=logger, parser=parser, ssl_wordpress=ssl_wordpress, no_create=create, no_update=update, no_image=image, tmp=tmp)
                 for k in ["article", "page"]:
                     for l in ["publications", "principal"]:
-                        importWp.fromUrl(webpage[l][k])
+                        importWp.fromUrl(l, k)
 
                 del importWp
     else:
@@ -93,9 +94,10 @@ def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, bas
                 logger.error("parsing error : {0}".format(err))
                 exit(1)
             exportWp = WPExport(name=name, url=url, logger=logger, parser=parser, ssl_canalblog=ssl_canalblog)
-            webpage = exportWp.getUrlPage(name_thread, max_thread)
+            if not revert:
+                exportWp.getUrlPage(name_thread, max_thread)
             del exportWp
-            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 = 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, tmp=tmp)
 
             for k in ["article", "page"]:
                 for l in ["publications", "principal"]:
@@ -117,7 +119,7 @@ def importDirectory(name_thread, max_thread, directory, logger, parser, wordpres
 
     else:
         if len(directory) != len(wordpress):
-            logger.error("{0} : Error : Number directory is differant than wordpress".format(name))
+            logger.error("{0} : Error : Number directory is different than wordpress".format(name))
             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)
@@ -134,6 +136,8 @@ if __name__ == '__main__':
     parser.add_argument("--parser", help="Parser content", default="html.parser")
     parser.add_argument("--parallel", help="Define number thread (default : 1)", default=1)
     parser.add_argument("--no-ssl", help="No ssl for canalblog and/or wordpress (example wordpress,canalblog)", dest="ssl", default="")
+    parser.add_argument("--revert", help="Restart a work from stopping work", action="store_true")
+    parser.add_argument("--tmp", help="directory tmp", default="/tmp/import_export_canablog")
 
     subparsers = parser.add_subparsers(dest="command")
 
@@ -188,7 +192,6 @@ if __name__ == '__main__':
                       help="File")
 
     
-
     args = parser.parse_args()
 
     logger = logging.getLogger('import export canalblog')
@@ -223,6 +226,8 @@ if __name__ == '__main__':
         fileHandler.setFormatter(formatter)
         logger.addHandler(fileHandler)
 
+    os.makedirs(args.tmp, exist_ok=True)
+
     if args.command == "import" or args.command == "remove":
         password = args.password
         if len(args.password) == 0:
@@ -255,8 +260,17 @@ 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:
+                        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)
+                    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))
                     ]
 
@@ -294,7 +308,7 @@ if __name__ == '__main__':
                 try:
                     with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
                         wait_for = [
-                        ex.submit(download, i, int(args.parallel), url, logger, args.parser, args.directory, args.html, args.img, ssl_canalblog)
+                        ex.submit(download, i, int(args.parallel), url, logger, args.parser, args.directory, args.html, args.img, ssl_canalblog, args.revert, args.tmp)
                         for i in range(0, int(args.parallel))
                         ]
                 except Exception as err:

lib/WPExport.py

@@ -1,12 +1,12 @@
 #!/usr/bin/python3
 from bs4 import BeautifulSoup
 from urllib.parse import urlparse
-import requests, os, argparse, logging
+import requests, os, argparse, logging, json
 from requests.adapters import HTTPAdapter
 from requests.packages.urllib3.util.retry import Retry
 
 class WPExport:
-    def __init__(self, name = "Thread-0", url = "", logger = None, parser = "html.parser", directory = "backup", ssl_canalblog=True):
+    def __init__(self, name = "Thread-0", url = "", logger = None, parser = "html.parser", directory = "backup", ssl_canalblog=True, tmp="/tmp/import_export_canablog"):
         self._url = url
         self._logger = logger
         self._parser = parser
@@ -22,7 +22,7 @@ class WPExport:
                 status_forcelist=[429, 500, 502, 503, 504], backoff_factor=2)
 
         self._request.mount('{0}://'.format(self._protocol), HTTPAdapter(max_retries=retries))
-
+        self._tmp = tmp
 
     # Destructor 
     def __del__(self):
@@ -57,13 +57,13 @@ class WPExport:
 
     # Download HTML
 
-    def downloadHTML(self, webpage):
+    def downloadHTML(self, first, second):
-        self._downloadPage(webpage, self._dir)
+        self._downloadPage(webpage[first][second], self._dir)
 
     # Download Image
     
-    def downloadImg(self, webpage):
+    def downloadImg(self, first, second):
-        page_src = self._getImg(webpage)
+        page_src = self._getImg(webpage[first][second])
         o = urlparse(self._url)
         self._downloadPage(page_src, "{0}/{1}/{2}".format(self._dir, o.path, "img"))
 
@@ -161,7 +161,14 @@ class WPExport:
             except Exception as err:
                 self._logger.error("{0} : Exception error : {1}".format(self._name, err))
                 exit(1)
-        return webpage
+        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))
+
+
+
         
 
 

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):
+    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"):
         self._name = name
         self._basic = basic
         self._wordpress = wordpress
@@ -16,6 +16,7 @@ class WPimport:
         self._parser = parser
         self._headers_json = {'Content-Type': 'application/json; charset=utf-8', 'Accept':'application/json'}
         self._protocol = "https"
+        self._directory = "backup"
         if ssl_wordpress is False:
             self._protocol = "http"
         self._request = requests.Session()
@@ -27,6 +28,7 @@ class WPimport:
         self._no_create = no_create
         self._no_update = no_update
         self._no_image = no_image
+        self._tmp = tmp
     
     # Destructor 
     def __del__(self):
@@ -37,7 +39,12 @@ class WPimport:
     def setUrl(self, wordpress):
         self._wordpress = wordpress
 
-    def fromUrl(self, webpage):
+    def fromUrl(self, first, second):
+        try:
+            with open("{0}/{1}.json".format(self._tmp, self._name)) as file:
+                webpage_content = json.loads(file.read())
+                self._logger.debug("{0} : size of webpage : {1}".format(self._name, len(webpage_content)))
+                webpage = webpage_content[first][second]
                 for i in range(0, len(webpage)):
                     try:
                         r = self._request.get(webpage[i])
@@ -49,26 +56,39 @@ class WPimport:
                                 self._addOrUpdatePost(soup)
                             else:
                                 self._addOrUpdateFeaturedMedia(soup)
+                            del webpage_content[first][second][i]
+                            webpage_content = json.dumps(webpage_content)
+                            open("{0}/{1}.json".format(self._tmp, self._name), "wt").write(webpage_content)
                         else:
                             self._logger.error("{0} : Connection error for get url {1} with status code : {2}".format(self._name, webpage[i], r.status_code))
                             self._logger.debug("{0} : {1}".format(self._name, r.content))
                     except ConnectionError as err:
                         self._logger.error("{0} : Connection error for get url {1} : {2}".format(self._name, webpage[i], err))
                         exit(1)
+                    except IOError as err:
+                        self._logger.error("{0} : Connection error for IO url {1} : {2}".format(self._name, webpage[i], err))
+                        exit(1)
                     except Exception as err:
                         self._logger.error("{0} : Exception error for get url {1} : {2}".format(self._name, webpage[i], err))
+        except Exception as ex:
+            self._logger.error("{0} : Read file json from tmp : {1}".format(self._name, ex))
 
 
     def fromDirectory(self, directory="", number_thread=1, max_thread=1):
+        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)
+            self.fromFile(files=files, number_thread=number_thread, max_thread=max_thread)
         else:
             self._logger.error("{0} : No files for {1}".format(self._name, directory))
     
             
+
+
+        
+
     def fromFile(self, files=[], number_thread=1, max_thread=1):
         divFiles = int(len(files) / max_thread)
         currentRangeFiles = int(divFiles * (number_thread+1))
@@ -445,23 +465,38 @@ class WPimport:
                 if len(img) > 0:
                     href_a = i.get("href")
                     href_img = img[0].get("src")
+                    href_a_o = urlparse(href_a)
+                    href_img_o = urlparse(href_img)
                     new_img["old_src"]=href_img
                     new_img["old_href"]=href_a
                     try:
+                        if len(href_img_o.netloc) > 0:
+                            img_ok = False
                             page_img = self._request.get(href_img)
                 
                             if page_img.status_code == 404:
                                 href_img = href_a
                                 try:
                                     page_img = self._request.get(href_a)
+                                    if page_img.status_code == 200:
+                                        img_ok = True
                                 except ConnectionError as err:
                                     self._logger.error("{0} : Connection error for get image : {1}".format(self._name, err))
                                     exit(1)
                                 except Exception as err:
                                     self._logger.error("{0} : Exception error for get image : {1}".format(self._name, err))
                                     exit(1)
+                            
+                        else:
+                            if os.path.exists("{0}/..{1}".format(self._directory, href_img)):
+                                page_img = open("{0}/..{1}".format(self._directory, href_img), "r")
+                                img_ok = True
+                            else:
+                                if os.path.exists("{0}/..{1}".format(self._directory, href_a)):
+                                    page_img = open("{0}/..{1}".format(self._directory, href_a), "r")
+                                    img_ok = True
                         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:
+                        if img_ok is True:
                             media=self._addOrUpdateMedia(href_img, page_img)
                             new_img["id"]=media["id"]
                             new_img["new_src"]=media["rendered"]