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     _TEST = {
  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     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         webpage = self._download_webpage(url, video_id)
  33
  34         m_error = re.search(
  35             r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage)
  36         if m_error:
  37             raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
  38
  39         video_title = None
  40         duration = None
  41         video_thumbnail = None
  42         formats = []
  43
  44         # most of the information is stored in the flashvars
  45         flashvars = self._html_search_regex(
  46             r'flashvars="(.+?)"', webpage, 'flashvars')
  47
  48         infos = compat_urllib_parse_unquote(flashvars).split(r'&')
  49         for info in infos:
  50             videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
  51             if videovars_match:
  52                 key = videovars_match.group(1)
  53                 val = videovars_match.group(2)
  54
  55                 if key == 'title':
  56                     video_title = compat_urllib_parse_unquote_plus(val)
  57                 if key == 'duration':
  58                     try:
  59                         duration = int(val)
  60                     except ValueError:
  61                         pass
  62                 if key == 'big_thumb':
  63                     video_thumbnail = val
  64
  65                 videourl_match = re.match(
  66                     r'^video_urls\]\[(?P<resolution>[0-9]+)p', key)
  67                 if videourl_match:
  68                     height = int(videourl_match.group('resolution'))
  69                     formats.append({
  70                         'height': height,
  71                         'url': val,
  72                     })
  73         self._sort_formats(formats)
  74
  75         # Extract title - should be in the flashvars; if not, look elsewhere
  76         if video_title is None:
  77             video_title = self._html_search_regex(
  78                 r'<title>(.*?)</title', webpage, 'title')
  79
  80         return {
  81             'id': video_id,
  82             'formats': formats,
  83             'title': video_title,
  84             'thumbnail': video_thumbnail,
  85             'duration': duration,
  86             'description': None,
  87             'age_limit': 18
  88         }