youtube_dl/extractor/quickvid.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urlparse,
   8 )
   9 from ..utils import (
  10     determine_ext,
  11     int_or_none,
  12 )
  13
  14
  15 class QuickVidIE(InfoExtractor):
  16     _VALID_URL = r'https?://(www\.)?quickvid\.org/watch\.php\?v=(?P<id>[a-zA-Z_0-9-]+)'
  17     _TEST = {
  18         'url': 'http://quickvid.org/watch.php?v=sUQT3RCG8dx',
  19         'md5': 'c0c72dd473f260c06c808a05d19acdc5',
  20         'info_dict': {
  21             'id': 'sUQT3RCG8dx',
  22             'ext': 'mp4',
  23             'title': 'Nick Offerman\'s Summer Reading Recap',
  24             'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$',
  25             'view_count': int,
  26         },
  27         'skip': 'Not accessible from Travis CI server',
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         webpage = self._download_webpage(url, video_id)
  33
  34         title = self._html_search_regex(r'<h2>(.*?)</h2>', webpage, 'title')
  35         view_count = int_or_none(self._html_search_regex(
  36             r'(?s)<div id="views">(.*?)</div>',
  37             webpage, 'view count', fatal=False))
  38         video_code = self._search_regex(
  39             r'(?s)<video id="video"[^>]*>(.*?)</video>', webpage, 'video code')
  40         formats = [
  41             {
  42                 'url': compat_urlparse.urljoin(url, src),
  43                 'format_id': determine_ext(src, None),
  44             } for src in re.findall('<source\s+src="([^"]+)"', video_code)
  45         ]
  46         self._sort_formats(formats)
  47
  48         return {
  49             'id': video_id,
  50             'title': title,
  51             'formats': formats,
  52             'thumbnail': self._og_search_thumbnail(webpage),
  53             'view_count': view_count,
  54         }