diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-09-01 00:45:51 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-09-01 00:45:51 +0700 |
commit | 43fd39241367f1a15475bd06073de6ebc0b8fd03 (patch) | |
tree | 16f43af3d2d3f0eb2abcadd90d89febdf4e592de /youtube_dl/extractor/sunporno.py | |
parent | f30a38be8b3c32500e168f93f68fc1f36a62b29d (diff) | |
parent | 7eb21356f98315b15fc05d9e616951511253076f (diff) |
Merge branch 'sunporno' of https://github.com/peugeot/youtube-dl into peugeot-sunporno
Diffstat (limited to 'youtube_dl/extractor/sunporno.py')
-rw-r--r-- | youtube_dl/extractor/sunporno.py | 57 |
1 files changed, 57 insertions, 0 deletions
diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py new file mode 100644 index 000000000..2a193dee3 --- /dev/null +++ b/youtube_dl/extractor/sunporno.py @@ -0,0 +1,57 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, +) + + +class SunPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.sunporno.com/videos/807778/', + 'md5': '6457d3c165fd6de062b99ef6c2ff4c86', + 'info_dict': { + 'id': '807778', + 'ext': 'flv', + 'title': 'md5:0a400058e8105d39e35c35e7c5184164', + 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', + 'duration': 302, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'videoSource\s*=\s*\'<source\s*src="([^"]*)"', webpage, 'video URL') + + title = self._html_search_regex(r'<title>([^<]*)</title>', webpage, 'title') + + description = self._html_search_regex( + r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False) + + thumbnail = self._html_search_regex( + r'poster="([^"]*)"', webpage, 'thumbnail', fatal=False) + + duration = parse_duration(self._search_regex( + r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False)) + + view_count = int_or_none(self._html_search_regex( + r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + } |