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 ..compat import (
   7     compat_urllib_parse_unquote,
   8     compat_urllib_parse_unquote_plus,
   9 )
  10 from ..utils import (
  11     clean_html,
  12     ExtractorError,
  13 )
  14
  15
  16 class PlayvidIE(InfoExtractor):
  17     _VALID_URL = r'https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
  18     _TESTS = [{
  19         'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
  20         'md5': 'ffa2f6b2119af359f544388d8c01eb6c',
  21         'info_dict': {
  22             'id': 'RnmBNgtrrJu',
  23             'ext': 'mp4',
  24             'title': 'md5:9256d01c6317e3f703848b5906880dc8',
  25             'duration': 82,
  26             'age_limit': 18,
  27         },
  28         'skip': 'Video removed due to ToS',
  29     }, {
  30         'url': 'http://www.playvid.com/watch/hwb0GpNkzgH',
  31         'md5': '39d49df503ad7b8f23a4432cbf046477',
  32         'info_dict': {
  33             'id': 'hwb0GpNkzgH',
  34             'ext': 'mp4',
  35             'title': 'Ellen Euro Cutie Blond Takes a Sexy Survey Get Facial in The Park',
  36             'age_limit': 18,
  37             'thumbnail': 're:^https?://.*\.jpg$',
  38         },
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43         webpage = self._download_webpage(url, video_id)
  44
  45         m_error = re.search(
  46             r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage)
  47         if m_error:
  48             raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
  49
  50         video_title = None
  51         duration = None
  52         video_thumbnail = None
  53         formats = []
  54
  55         # most of the information is stored in the flashvars
  56         flashvars = self._html_search_regex(
  57             r'flashvars="(.+?)"', webpage, 'flashvars')
  58
  59         infos = compat_urllib_parse_unquote(flashvars).split(r'&')
  60         for info in infos:
  61             videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
  62             if videovars_match:
  63                 key = videovars_match.group(1)
  64                 val = videovars_match.group(2)
  65
  66                 if key == 'title':
  67                     video_title = compat_urllib_parse_unquote_plus(val)
  68                 if key == 'duration':
  69                     try:
  70                         duration = int(val)
  71                     except ValueError:
  72                         pass
  73                 if key == 'big_thumb':
  74                     video_thumbnail = val
  75
  76                 videourl_match = re.match(
  77                     r'^video_urls\]\[(?P<resolution>[0-9]+)p', key)
  78                 if videourl_match:
  79                     height = int(videourl_match.group('resolution'))
  80                     formats.append({
  81                         'height': height,
  82                         'url': val,
  83                     })
  84         self._sort_formats(formats)
  85
  86         # Extract title - should be in the flashvars; if not, look elsewhere
  87         if video_title is None:
  88             video_title = self._html_search_regex(
  89                 r'<title>(.*?)</title', webpage, 'title')
  90
  91         return {
  92             'id': video_id,
  93             'formats': formats,
  94             'title': video_title,
  95             'thumbnail': video_thumbnail,
  96             'duration': duration,
  97             'description': None,
  98             'age_limit': 18
  99         }