simple valid URL regex

1 files changed, 6 insertions, 55 deletions

diff --git a/hypervideo_gui.py b/hypervideo_gui.py
index b3e9a6c..b14fe43 100644
--- a/hypervideo_gui.py
+++ b/hypervideo_gui.py
@@ -4,7 +4,9 @@ import re
 
 from PyQt5.QtWidgets import *
 from PyQt5.QtGui import QIcon
-from PyQt5.QtCore import pyqtSlot
+from PyQt5.QtCore import (
+    pyqtSlot,
+)
 
 import threading
 import hypervideo
@@ -29,59 +31,7 @@ class App(QMainWindow):
     """
     Simple applicaction for download using hypervideo
     """
-    _VALID_URL = r"""(?x)^
-                     (
-                         (?:https?://|//)                                     # http(s):// or protocol-independent URL
-                         (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
-                             (?:www\.)?deturl\.com/www\.youtube\.com/|
-                             (?:www\.)?pwnyoutube\.com/|
-                             (?:www\.)?hooktube\.com/|
-                             (?:www\.)?yourepeat\.com/|
-                             tube\.majestyc\.net/|
-                             # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
-                             (?:(?:www|dev)\.)?invidio\.us/|
-                             (?:(?:www|no)\.)?invidiou\.sh/|
-                             (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
-                             (?:www\.)?invidious\.kabi\.tk/|
-                             (?:www\.)?invidious\.13ad\.de/|
-                             (?:www\.)?invidious\.mastodon\.host/|
-                             (?:www\.)?invidious\.nixnet\.xyz/|
-                             (?:www\.)?invidious\.drycat\.fr/|
-                             (?:www\.)?tube\.poal\.co/|
-                             (?:www\.)?vid\.wxzm\.sx/|
-                             (?:www\.)?yt\.elukerio\.org/|
-                             (?:www\.)?yt\.lelux\.fi/|
-                             (?:www\.)?kgg2m7yk5aybusll\.onion/|
-                             (?:www\.)?qklhadlycap4cnod\.onion/|
-                             (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
-                             (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
-                             (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
-                             (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
-                             (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
-                             youtube\.googleapis\.com/)                       # the various hostnames, with wildcard subdomains
-                         (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
-                         (?:                                                  # the various things that can precede the ID:
-                             (?:(?:v|embed|e)/(?!videoseries))                # v/ or embed/ or e/
-                             |(?:                                             # or the v= param in all its forms
-                                 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)?  # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
-                                 (?:\?|\#!?)                                  # the params delimiter ? or # or #!
-                                 (?:.*?[&;])??                                # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
-                                 v=
-                             )
-                         ))
-                         |(?:
-                             youtu\.be|                                       # just youtu.be/xxxx
-                             vid\.plus|                                       # or vid.plus/xxxx
-                             zwearz\.com/watch|                               # or zwearz.com/watch/xxxx
-                         )/
-                         |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
-                         )
-                     )?                                                       # all until now is optional -> you can pass the naked ID
-                     ([0-9A-Za-z_-]{11})                                      # here is it! the YouTube video ID
-                     (?(1).+)?                                                # if we found the ID, everything can follow
-                     $"""
-
-    __URL = r"""^(?:http(s)?:\/\/)?[\w.-]+(?:\.[\w\.-]+)+[\w\-\._~:/?#[\]@!\$&'\(\)\*\+,;=.]+$"""
+    _VALID_URL = r"""^(?:http(s)?:\/\/)?[\w.-]+(?:\.[\w\.-]+)+[\w\-\._~:/?#[\]@!\$&'\(\)\*\+,;=.]+$"""
 
     def __init__(self):
         super().__init__()
@@ -243,7 +193,7 @@ class App(QMainWindow):
             }
 
         # download the video in daemon thread
-        if re.match(self.__URL, str(self.url_entry())) is None:
+        if re.match(self._VALID_URL, str(self.url_entry())) is None:
             self.statusBar().showMessage('Please add a URL...')  # update status bar
         else:
             self.statusBar().showMessage('Downloading Video...')  # update status bar
@@ -264,6 +214,7 @@ class App(QMainWindow):
                 'format': 'best',
                 'noplaylist': True,   # only download single song, not playlist
             }
+
             with hypervideo.YoutubeDL(self.options) as ydl:
                 meta = ydl.extract_info(url, download=False)
                 formats = meta.get('formats', [meta])