diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/sunporno.py | 68 | 
2 files changed, 69 insertions, 0 deletions
| diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a306035f1..459899861 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -323,6 +323,7 @@ from .stanfordoc import StanfordOpenClassroomIE  from .steam import SteamIE  from .streamcloud import StreamcloudIE  from .streamcz import StreamCZIE +from .sunporno import SunPornoIE  from .swrmediathek import SWRMediathekIE  from .syfy import SyfyIE  from .sztvhu import SztvHuIE diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py new file mode 100644 index 000000000..c7a46eb71 --- /dev/null +++ b/youtube_dl/extractor/sunporno.py @@ -0,0 +1,68 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( +    parse_duration, +    int_or_none, +    qualities, +    determine_ext, +) + + +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', +            'thumbnail': 're:^https?://.*\.jpg$', +            '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) + +        title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title') +        description = self._html_search_meta('description', webpage, 'description') +        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)) +        comment_count = int_or_none(self._html_search_regex( +            r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False)) + +        formats = [] +        quality = qualities(['mp4', 'flv']) +        for video_url in re.findall(r'<source src="([^"]+)"', webpage): +            video_ext = determine_ext(video_url) +            formats.append({ +                'url': video_url, +                'format_id': video_ext, +                'quality': quality(video_ext), +            }) +        self._sort_formats(formats) + +        return { +            'id': video_id, +            'title': title, +            'description': description, +            'thumbnail': thumbnail, +            'duration': duration, +            'view_count': view_count, +            'comment_count': comment_count, +            'formats': formats, +        } | 
