depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-22 16:57:40 +00:00
Code Issues Releases Wiki Activity

[hentaistigma] Simplified (#2902)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-05-13 10:10:59 +02:00
parent 24e6ec8ac8
commit 56a94d8cbb
1 changed files with 25 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

51
youtube_dl/extractor/hentaistigma.py
View file

@ -1,43 +1,42 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class HentaiStigmaIE(InfoExtractor):
_VALID_URL = r'^https?://hentai\.animestigma\.com/(?P<videoid>[^/]+)'
_VALID_URL = r'^https?://hentai\.animestigma\.com/(?P<id>[^/]+)'
_TEST = {
u'url': u'http://hentai.animestigma.com/inyouchuu-etsu-bonus/',
u'file': u'inyouchuu-etsu-bonus.mp4',
u'md5': u'4e3d07422a68a4cc363d8f57c8bf0d23',
u'info_dict': {
u"title": u"Inyouchuu Etsu Bonus",
u"age_limit": 18,
'url': 'http://hentai.animestigma.com/inyouchuu-etsu-bonus/',
'md5': '4e3d07422a68a4cc363d8f57c8bf0d23',
'info_dict': {
'id': 'inyouchuu-etsu-bonus',
'ext': 'mp4',
"title": "Inyouchuu Etsu Bonus",
"age_limit": 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = mobj.group('videoid')
# Get webpage content
webpage = self._download_webpage(url, video_id)
# Get the video title
video_title = self._html_search_regex(r'<h2 class="posttitle"><a[^>]*>([^<]+)</a>',
webpage, u'title').strip()
# Get the wrapper url
wrap_url = self._html_search_regex(r'<iframe src="([^"]+mp4)"', webpage, u'wrapper url')
# Get wrapper content
title = self._html_search_regex(
r'<h2 class="posttitle"><a[^>]*>([^<]+)</a>',
webpage, 'title')
wrap_url = self._html_search_regex(
r'<iframe src="([^"]+mp4)"', webpage, 'wrapper url')
wrap_webpage = self._download_webpage(wrap_url, video_id)
video_url = self._html_search_regex(r'clip:\s*{\s*url: "([^"]*)"', wrap_webpage, u'video url')
video_url = self._html_search_regex(
r'clip:\s*{\s*url: "([^"]*)"', wrap_webpage, 'video url')
info = {'id': video_id,
'url': video_url,
'title': video_title,
'format': 'mp4',
'age_limit': 18}
return [info]
return {
'id': video_id,
'url': video_url,
'title': title,
'age_limit': 18,
}