yt_dlp/extractor/playvid.py

   1 import re
   2 import urllib.parse
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urllib_parse_unquote
   6 from ..utils import ExtractorError, clean_html
   7
   8
   9 class PlayvidIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
  11     _TESTS = [{
  12         'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
  13         'md5': 'ffa2f6b2119af359f544388d8c01eb6c',
  14         'info_dict': {
  15             'id': 'RnmBNgtrrJu',
  16             'ext': 'mp4',
  17             'title': 'md5:9256d01c6317e3f703848b5906880dc8',
  18             'duration': 82,
  19             'age_limit': 18,
  20         },
  21         'skip': 'Video removed due to ToS',
  22     }, {
  23         'url': 'http://www.playvid.com/watch/hwb0GpNkzgH',
  24         'md5': '39d49df503ad7b8f23a4432cbf046477',
  25         'info_dict': {
  26             'id': 'hwb0GpNkzgH',
  27             'ext': 'mp4',
  28             'title': 'Ellen Euro Cutie Blond Takes a Sexy Survey Get Facial in The Park',
  29             'age_limit': 18,
  30             'thumbnail': r're:^https?://.*\.jpg$',
  31         },
  32     }]
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36         webpage = self._download_webpage(url, video_id)
  37
  38         m_error = re.search(
  39             r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage)
  40         if m_error:
  41             raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
  42
  43         video_title = None
  44         duration = None
  45         video_thumbnail = None
  46         formats = []
  47
  48         # most of the information is stored in the flashvars
  49         flashvars = self._html_search_regex(
  50             r'flashvars="(.+?)"', webpage, 'flashvars')
  51
  52         infos = compat_urllib_parse_unquote(flashvars).split(r'&')
  53         for info in infos:
  54             videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
  55             if videovars_match:
  56                 key = videovars_match.group(1)
  57                 val = videovars_match.group(2)
  58
  59                 if key == 'title':
  60                     video_title = urllib.parse.unquote_plus(val)
  61                 if key == 'duration':
  62                     try:
  63                         duration = int(val)
  64                     except ValueError:
  65                         pass
  66                 if key == 'big_thumb':
  67                     video_thumbnail = val
  68
  69                 videourl_match = re.match(
  70                     r'^video_urls\]\[(?P<resolution>[0-9]+)p', key)
  71                 if videourl_match:
  72                     height = int(videourl_match.group('resolution'))
  73                     formats.append({
  74                         'height': height,
  75                         'url': val,
  76                     })
  77
  78         # Extract title - should be in the flashvars; if not, look elsewhere
  79         if video_title is None:
  80             video_title = self._html_extract_title(webpage)
  81
  82         return {
  83             'id': video_id,
  84             'formats': formats,
  85             'title': video_title,
  86             'thumbnail': video_thumbnail,
  87             'duration': duration,
  88             'description': None,
  89             'age_limit': 18
  90         }