mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 12:01:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

[extremetube] Modernize

Browse source
This commit is contained in:
Philipp Hagemeister 2014-04-19 19:42:51 +02:00
parent 52fadd5fb2
commit 3c50b99ab4
1 changed files with 18 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
youtube_dl/extractor/extremetube.py
View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import os
import re
@ -8,16 +10,18 @@
compat_urllib_parse,
)
class ExtremeTubeIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
_TESTS = [{
u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
u'file': u'652431.mp4',
u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0',
u'info_dict': {
u"title": u"Music Video 14 british euro brit european cumshots swallow",
u"uploader": u"unknown",
u"age_limit": 18,
'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
'info_dict': {
'id': '652431',
'ext': 'mp4',
'title': 'Music Video 14 british euro brit european cumshots swallow',
'uploader': 'unknown',
'age_limit': 18,
}
}, {
'url': 'http://www.extremetube.com/gay/video/abcde-1234',
@ -33,11 +37,14 @@ def _real_extract(self, url):
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, u'title')
uploader = self._html_search_regex(r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False)
video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, u'video_url'))
video_title = self._html_search_regex(
r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, 'title')
uploader = self._html_search_regex(
r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
fatal=False)
video_url = compat_urllib_parse.unquote(self._html_search_regex(
r'video_url=(.+?)&amp;', webpage, 'video_url'))
path = compat_urllib_parse_urlparse(video_url).path
extension = os.path.splitext(path)[1][1:]
format = path.split('/')[5].split('_')[:2]
format = "-".join(format)
@ -46,7 +53,6 @@ def _real_extract(self, url):
'title': video_title,
'uploader': uploader,
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
'age_limit': 18,