Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/playvid.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     clean_html,
   9     compat_urllib_parse,
  10 )
  11
  12
  13 class PlayvidIE(InfoExtractor):
  14     _VALID_URL = r'^https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
  15     _TEST = {
  16         'url': 'http://www.playvid.com/watch/agbDDi7WZTV',
  17         'md5': '44930f8afa616efdf9482daf4fe53e1e',
  18         'info_dict': {
  19             'id': 'agbDDi7WZTV',
  20             'ext': 'mp4',
  21             'title': 'Michelle Lewin in Miami Beach',
  22             'duration': 240,
  23             'age_limit': 18,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         m_error = re.search(
  34             r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage)
  35         if m_error:
  36             raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
  37
  38         video_title = None
  39         duration = None
  40         video_thumbnail = None
  41         formats = []
  42
  43         # most of the information is stored in the flashvars
  44         flashvars = self._html_search_regex(
  45             r'flashvars="(.+?)"', webpage, 'flashvars')
  46
  47         infos = compat_urllib_parse.unquote(flashvars).split(r'&')
  48         for info in infos:
  49             videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
  50             if videovars_match:
  51                 key = videovars_match.group(1)
  52                 val = videovars_match.group(2)
  53
  54                 if key == 'title':
  55                     video_title = compat_urllib_parse.unquote_plus(val)
  56                 if key == 'duration':
  57                     try:
  58                         duration = int(val)
  59                     except ValueError:
  60                         pass
  61                 if key == 'big_thumb':
  62                     video_thumbnail = val
  63
  64                 videourl_match = re.match(
  65                     r'^video_urls\]\[(?P<resolution>[0-9]+)p', key)
  66                 if videourl_match:
  67                     height = int(videourl_match.group('resolution'))
  68                     formats.append({
  69                         'height': height,
  70                         'url': val,
  71                     })
  72         self._sort_formats(formats)
  73
  74         # Extract title - should be in the flashvars; if not, look elsewhere
  75         if video_title is None:
  76             video_title = self._html_search_regex(
  77                 r'<title>(.*?)</title', webpage, 'title')
  78
  79         return {
  80             'id': video_id,
  81             'formats': formats,
  82             'title': video_title,
  83             'thumbnail': video_thumbnail,
  84             'duration': duration,
  85             'description': None,
  86             'age_limit': 18
  87         }