github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

Made the YouTubeIE regex verbose/commented

Browse source
This commit is contained in:
Filippo Valsorda 2012-08-20 00:58:10 +02:00
parent 9bb8dc8e42
commit 202e76cfb0
1 changed files with 23 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
youtube_dl/InfoExtractors.py
View file

@ -95,7 +95,24 @@ def _real_extract(self, url):
class YoutubeIE(InfoExtractor): class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com.""" """Information extractor for youtube.com."""
_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' _VALID_URL = r"""^
(
(?:https?://)? # http(s):// (optional)
(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/) # the various hostnames, with wildcard subdomains
(?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms
(?:watch(?:_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)
v=
)
)? # optional -> youtube.com/xxxx is OK
)? # all until now is optional -> you can pass the naked ID
([0-9A-Za-z_-]+) # here is it! the YouTube video ID
(?(1).+)? # if we found the ID, everything can follow
$"""
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
@ -134,6 +151,10 @@ class YoutubeIE(InfoExtractor):
} }
IE_NAME = u'youtube' IE_NAME = u'youtube'
def suitable(self, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url, re.VERBOSE) is not None
def report_lang(self): def report_lang(self):
"""Report attempt to set language.""" """Report attempt to set language."""
self._downloader.to_screen(u'[youtube] Setting language') self._downloader.to_screen(u'[youtube] Setting language')
@ -268,7 +289,7 @@ def _real_extract(self, url):
url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/') url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/')
# Extract video id from URL # Extract video id from URL
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url) self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return return