diff options
author | hojel <hojelei@gmail.com> | 2014-05-12 03:58:07 -0700 |
---|---|---|
committer | hojel <hojelei@gmail.com> | 2014-05-12 03:58:07 -0700 |
commit | 33c7ff861ec6288a6e437deb73a277067ac9e267 (patch) | |
tree | 3e289d46527c5ca12dfd6b2d34abb4267d28da1b /youtube_dl | |
parent | e399853d0c5784257ffcb6fba147d0b47d3f9bb6 (diff) |
[hentaistigma] Add new extractor
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/hentaistigma.py | 43 |
2 files changed, 44 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9529077c7..228f62b40 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -109,6 +109,7 @@ from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE from .hark import HarkIE from .helsinki import HelsinkiIE +from .hentaistigma import HentaiStigmaIE from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE from .huffpost import HuffPostIE diff --git a/youtube_dl/extractor/hentaistigma.py b/youtube_dl/extractor/hentaistigma.py new file mode 100644 index 000000000..4f2d30599 --- /dev/null +++ b/youtube_dl/extractor/hentaistigma.py @@ -0,0 +1,43 @@ +import re + +from .common import InfoExtractor + +class HentaiStigmaIE(InfoExtractor): + _VALID_URL = r'^https?://hentai\.animestigma\.com/(?P<videoid>[^/]+)' + _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, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + 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 + 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} + + return [info] |