From f0b4ba5e27978d4a03624530c57a6ebd6182bca6 Mon Sep 17 00:00:00 2001 From: Valentin CZERYBA Date: Sat, 1 Jul 2023 21:56:10 +0200 Subject: [PATCH] add url and file --- import_export_canalblog.py | 19 +++++++++++++++++-- lib/WPMenu.py | 39 ++++++++++++++++++++++++++++---------- 2 files changed, 46 insertions(+), 12 deletions(-) diff --git a/import_export_canalblog.py b/import_export_canalblog.py index a404d16..de1c15e 100644 --- a/import_export_canalblog.py +++ b/import_export_canalblog.py @@ -10,6 +10,7 @@ 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 errorRevert(logger, revert, tmp): if revert is True: @@ -202,8 +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') @@ -240,7 +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() @@ -341,4 +348,12 @@ if __name__ == '__main__': 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) \ No newline at end of file diff --git a/lib/WPMenu.py b/lib/WPMenu.py index 287702b..90d9dfc 100644 --- a/lib/WPMenu.py +++ b/lib/WPMenu.py @@ -34,23 +34,32 @@ class WPMenu: def __del__(self): print("{0} : Import finished for {1}".format(self._name, self._wordpress)) - # Public method + # 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): + def fromUrl(self, canalblog): try: - o = urlparse(self._canalblog) + o = urlparse(canalblog) o = o._replace(scheme=self._protocol_canalblog) i = o.geturl().replace(":///", "://") page = self._request.get(i) if page.status_code == 200: - soup = BeautifulSoup(page.text, self._parser) - ul = soup.find_all("ul", id="listsmooth") - for anchor in ul[0].find_all("li"): - li = anchor.find_all("li") - for content in li: - a = content.find("a") + 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)) @@ -58,4 +67,14 @@ class WPMenu: self._logger.error("{0} : Connection error for get 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)) \ No newline at end of file + self._logger.error("{0} : Exception error for get url {1} : {2}".format(self._name, webpage[i], err)) + + + def _menu(self, content): + + soup = BeautifulSoup(page.text, self._parser) + ul = soup.find_all("ul", id="listsmooth") + for anchor in ul[0].find_all("li"): + li = anchor.find_all("li") + for content in li: + a = content.find("a")