etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-04 23:35:04 +00:00
Code Issues Projects Releases Wiki Activity

[sunporno] Fix metadata extraction (Closes #10316)

Browse source
This commit is contained in:
Sergey M․ 2016-08-13 14:09:35 +07:00
parent f0d3669437
commit 794e5dcd7e
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 5 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
youtube_dl/extractor/sunporno.py
View file

@ -15,10 +15,10 @@ class SunPornoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://www.sunporno.com/videos/807778/', 'url': 'http://www.sunporno.com/videos/807778/',
'md5': '6457d3c165fd6de062b99ef6c2ff4c86', 'md5': '507887e29033502f29dba69affeebfc9',
'info_dict': { 'info_dict': {
'id': '807778', 'id': '807778',
'ext': 'flv', 'ext': 'mp4',
'title': 'md5:0a400058e8105d39e35c35e7c5184164', 'title': 'md5:0a400058e8105d39e35c35e7c5184164',
'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
@ -40,7 +40,8 @@ def _real_extract(self, url):
r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'itemprop="duration">\s*(\d+:\d+)\s*<', (r'itemprop="duration"[^>]*>\s*(\d+:\d+)\s*<',
r'>Duration:\s*<span[^>]+>\s*(\d+:\d+)\s*<'),
webpage, 'duration', fatal=False)) webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex( view_count = int_or_none(self._html_search_regex(
@ -48,7 +49,7 @@ def _real_extract(self, url):
webpage, 'view count', fatal=False)) webpage, 'view count', fatal=False))
comment_count = int_or_none(self._html_search_regex( comment_count = int_or_none(self._html_search_regex(
r'(\d+)</b> Comments?', r'(\d+)</b> Comments?',
webpage, 'comment count', fatal=False)) webpage, 'comment count', fatal=False, default=None))
formats = [] formats = []
quality = qualities(['mp4', 'flv']) quality = qualities(['mp4', 'flv'])