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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     float_or_none,
  10     int_or_none,
  11     parse_duration,
  12 )
  13
  14
  15 class CDAIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
  17     _BASE_URL = 'http://www.cda.pl/'
  18     _TESTS = [{
  19         'url': 'http://www.cda.pl/video/5749950c',
  20         'md5': '6f844bf51b15f31fae165365707ae970',
  21         'info_dict': {
  22             'id': '5749950c',
  23             'ext': 'mp4',
  24             'height': 720,
  25             'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
  26             'description': 'md5:269ccd135d550da90d1662651fcb9772',
  27             'thumbnail': 're:^https?://.*\.jpg$',
  28             'average_rating': float,
  29             'duration': 39
  30         }
  31     }, {
  32         'url': 'http://www.cda.pl/video/57413289',
  33         'md5': 'a88828770a8310fc00be6c95faf7f4d5',
  34         'info_dict': {
  35             'id': '57413289',
  36             'ext': 'mp4',
  37             'title': 'Lądowanie na lotnisku na Maderze',
  38             'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a',
  39             'thumbnail': 're:^https?://.*\.jpg$',
  40             'uploader': 'crash404',
  41             'view_count': int,
  42             'average_rating': float,
  43             'duration': 137
  44         }
  45     }, {
  46         'url': 'http://ebd.cda.pl/0x0/5749950c',
  47         'only_matching': True,
  48     }]
  49
  50     def _real_extract(self, url):
  51         video_id = self._match_id(url)
  52         self._set_cookie('cda.pl', 'cda.player', 'html5')
  53         webpage = self._download_webpage(
  54             self._BASE_URL + '/video/' + video_id, video_id)
  55
  56         if 'Ten film jest dostępny dla użytkowników premium' in webpage:
  57             raise ExtractorError('This video is only available for premium users.', expected=True)
  58
  59         formats = []
  60
  61         uploader = self._search_regex(r'''(?x)
  62             <(span|meta)[^>]+itemprop=(["\'])author\2[^>]*>
  63             (?:<\1[^>]*>[^<]*</\1>|(?!</\1>)(?:.|\n))*?
  64             <(span|meta)[^>]+itemprop=(["\'])name\4[^>]*>(?P<uploader>[^<]+)</\3>
  65         ''', webpage, 'uploader', default=None, group='uploader')
  66         view_count = self._search_regex(
  67             r'Odsłony:(?:\s|&nbsp;)*([0-9]+)', webpage,
  68             'view_count', default=None)
  69         average_rating = self._search_regex(
  70             r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
  71             webpage, 'rating', fatal=False, group='rating_value')
  72
  73         info_dict = {
  74             'id': video_id,
  75             'title': self._og_search_title(webpage),
  76             'description': self._og_search_description(webpage),
  77             'uploader': uploader,
  78             'view_count': int_or_none(view_count),
  79             'average_rating': float_or_none(average_rating),
  80             'thumbnail': self._og_search_thumbnail(webpage),
  81             'formats': formats,
  82             'duration': None,
  83         }
  84
  85         def extract_format(page, version):
  86             json_str = self._search_regex(
  87                 r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page,
  88                 '%s player_json' % version, fatal=False, group='player_data')
  89             if not json_str:
  90                 return
  91             player_data = self._parse_json(
  92                 json_str, '%s player_data' % version, fatal=False)
  93             if not player_data:
  94                 return
  95             video = player_data.get('video')
  96             if not video or 'file' not in video:
  97                 self.report_warning('Unable to extract %s version information' % version)
  98                 return
  99             f = {
 100                 'url': video['file'],
 101             }
 102             m = re.search(
 103                 r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
 104                 page)
 105             if m:
 106                 f.update({
 107                     'format_id': m.group('format_id'),
 108                     'height': int(m.group('height')),
 109                 })
 110             info_dict['formats'].append(f)
 111             if not info_dict['duration']:
 112                 info_dict['duration'] = parse_duration(video.get('duration'))
 113
 114         extract_format(webpage, 'default')
 115
 116         for href, resolution in re.findall(
 117                 r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
 118                 webpage):
 119             webpage = self._download_webpage(
 120                 self._BASE_URL + href, video_id,
 121                 'Downloading %s version information' % resolution, fatal=False)
 122             if not webpage:
 123                 # Manually report warning because empty page is returned when
 124                 # invalid version is requested.
 125                 self.report_warning('Unable to download %s version information' % resolution)
 126                 continue
 127             extract_format(webpage, resolution)
 128
 129         self._sort_formats(formats)
 130
 131         return info_dict