From b95aab8482881e8b1f7fba856da816a2dbc50d0f Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sat, 24 Jan 2015 11:42:20 +0100 Subject: [PATCH] [youtube:truncated_url] Add x-yt-cl URLs (#4773) --- youtube_dl/extractor/youtube.py | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index eb55d24ce..b7b91f354 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1682,11 +1682,17 @@ class YoutubeTruncatedURLIE(InfoExtractor): IE_NAME = 'youtube:truncated_url' IE_DESC = False # Do not list _VALID_URL = r'''(?x) - (?:https?://)?[^/]+/watch\?(?: + (?:https?://)? + (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ + (?:watch\?(?: feature=[a-z_]+| - annotation_id=annotation_[^&]+ - )?$| - (?:https?://)?(?:www\.)?youtube\.com/attribution_link\?a=[^&]+$ + annotation_id=annotation_[^&]+| + x-yt-cl=[0-9]+| + )? + | + attribution_link\?a=[^&]+ + ) + $ ''' _TESTS = [{ @@ -1695,6 +1701,12 @@ class YoutubeTruncatedURLIE(InfoExtractor): }, { 'url': 'http://www.youtube.com/watch?', 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', + 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?feature=foo', + 'only_matching': True, }] def _real_extract(self, url): @@ -1710,7 +1722,7 @@ class YoutubeTruncatedURLIE(InfoExtractor): class YoutubeTruncatedIDIE(InfoExtractor): IE_NAME = 'youtube:truncated_id' IE_DESC = False # Do not list - _VALID_URL = r'https?://(?:www\.)youtube\.com/watch\?v=(?P[0-9A-Za-z_-]{1,10})$' + _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P[0-9A-Za-z_-]{1,10})$' _TESTS = [{ 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',