diff options
| author | Sergey M․ <dstftw@gmail.com> | 2014-04-26 20:22:15 +0700 | 
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2014-04-26 20:22:15 +0700 | 
| commit | 7c360e3a04f09b912f51034c7778eb2297872e86 (patch) | |
| tree | 33225c24166cc1c0354fd0ab045f1d007da1852f | |
| parent | d2176c80116c90ca5cac676fbbba07a55198ff43 (diff) | |
[scivee] Add support for scivee.tv
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/scivee.py | 56 | 
2 files changed, 57 insertions, 0 deletions
| diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9a0983e17..e389acc6a 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -221,6 +221,7 @@ from .rutube import (  )  from .rutv import RUTVIE  from .savefrom import SaveFromIE +from .scivee import SciVeeIE  from .servingsys import ServingSysIE  from .sina import SinaIE  from .slideshare import SlideshareIE diff --git a/youtube_dl/extractor/scivee.py b/youtube_dl/extractor/scivee.py new file mode 100644 index 000000000..609a5ec99 --- /dev/null +++ b/youtube_dl/extractor/scivee.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class SciVeeIE(InfoExtractor): +    _VALID_URL = r'https?://(?:www\.)?scivee\.tv/node/(?P<id>\d+)' + +    _TEST = { +        'url': 'http://www.scivee.tv/node/62352', +        'md5': 'b16699b74c9e6a120f6772a44960304f', +        'info_dict': { +            'id': '62352', +            'ext': 'mp4', +            'title': 'Adam Arkin at the 2014 DOE JGI Genomics of Energy & Environment Meeting', +            'description': 'md5:81f1710638e11a481358fab1b11059d7', +        } +    } + +    def _real_extract(self, url): +        mobj = re.match(self._VALID_URL, url) +        video_id = mobj.group('id') + +        # annotations XML is malformed +        annotations = self._download_webpage( +            'http://www.scivee.tv/assets/annotations/%s' % video_id, video_id, 'Downloading annotations') + +        title = self._html_search_regex(r'<title>([^<]+)</title>', annotations, 'title') +        description = self._html_search_regex(r'<abstract>([^<]+)</abstract>', annotations, 'abstract', fatal=False) +        filesize = int_or_none(self._html_search_regex( +            r'<filesize>([^<]+)</filesize>', annotations, 'filesize', fatal=False)) + +        formats = [ +            { +                'url': 'http://www.scivee.tv/assets/audio/%s' % video_id, +                'ext': 'mp3', +                'format_id': 'audio', +            }, +            { +                'url': 'http://www.scivee.tv/assets/video/%s' % video_id, +                'ext': 'mp4', +                'format_id': 'video', +                'filesize': filesize, +            }, +        ] + +        return { +            'id': video_id, +            'title': title, +            'description': description, +            'thumbnail': 'http://www.scivee.tv/assets/videothumb/%s' % video_id, +            'formats': formats, +        }
\ No newline at end of file | 
