diff options
| -rw-r--r-- | youtube_dl/extractor/hentaistigma.py | 51 |
1 files changed, 25 insertions, 26 deletions
diff --git a/youtube_dl/extractor/hentaistigma.py b/youtube_dl/extractor/hentaistigma.py index 4f2d30599..63d87b74c 100644 --- a/youtube_dl/extractor/hentaistigma.py +++ b/youtube_dl/extractor/hentaistigma.py @@ -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') - - info = {'id': video_id, - 'url': video_url, - 'title': video_title, - 'format': 'mp4', - 'age_limit': 18} + video_url = self._html_search_regex( + r'clip:\s*{\s*url: "([^"]*)"', wrap_webpage, 'video url') - return [info] + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'age_limit': 18, + } |