diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-04-06 21:24:45 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-04-06 21:24:45 +0600 |
commit | ae603b500e569781d9c4db4a4d2e04deff37d994 (patch) | |
tree | f89bf6376a50ade596d8f4b2283a242e428e45ef | |
parent | e40bd5f06ba397f6a3f9f21ab1df01c120d90eb7 (diff) | |
parent | d97aae75724fc301243a00c5a71ac93b235d62fe (diff) |
Merge branch 'newtonelectron-spankbang.com'
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/spankbang.py | 60 |
2 files changed, 61 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 0f7d44616..e6fdf1297 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -471,6 +471,7 @@ from .southpark import ( SouthparkDeIE, ) from .space import SpaceIE +from .spankbang import SpankBangIE from .spankwire import SpankwireIE from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegeltv import SpiegeltvIE diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py new file mode 100644 index 000000000..7f060b15b --- /dev/null +++ b/youtube_dl/extractor/spankbang.py @@ -0,0 +1,60 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class SpankBangIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video' + _TEST = { + 'url': 'http://spankbang.com/3vvn/video/fantasy+solo', + 'md5': '1cc433e1d6aa14bc376535b8679302f7', + 'info_dict': { + 'id': '3vvn', + 'ext': 'mp4', + 'title': 'fantasy solo', + 'description': 'dillion harper masturbates on a bed', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'silly2587', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + stream_key = self._html_search_regex( + r'''var\s+stream_key\s*=\s*['"](.+?)['"]''', + webpage, 'stream key') + + formats = [{ + 'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height), + 'ext': 'mp4', + 'format_id': '%sp' % height, + 'height': int(height), + } for height in re.findall(r'<span[^>]+q_(\d+)p', webpage)] + self._sort_formats(formats) + + title = self._html_search_regex( + r'(?s)<h1>(.+?)</h1>', webpage, 'title') + description = self._search_regex( + r'class="desc"[^>]*>([^<]+)', + webpage, 'description', default=None) + thumbnail = self._og_search_thumbnail(webpage) + uploader = self._search_regex( + r'class="user"[^>]*>([^<]+)', + webpage, 'uploader', fatal=False) + + age_limit = self._rta_search(webpage) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'formats': formats, + 'age_limit': age_limit, + } |