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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import codecs
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10     float_or_none,
  11     int_or_none,
  12     parse_duration,
  13 )
  14
  15
  16 class CDAIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
  18     _BASE_URL = 'http://www.cda.pl/'
  19     _TESTS = [{
  20         'url': 'http://www.cda.pl/video/5749950c',
  21         'md5': '6f844bf51b15f31fae165365707ae970',
  22         'info_dict': {
  23             'id': '5749950c',
  24             'ext': 'mp4',
  25             'height': 720,
  26             'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
  27             'description': 'md5:269ccd135d550da90d1662651fcb9772',
  28             'thumbnail': r're:^https?://.*\.jpg$',
  29             'average_rating': float,
  30             'duration': 39
  31         }
  32     }, {
  33         'url': 'http://www.cda.pl/video/57413289',
  34         'md5': 'a88828770a8310fc00be6c95faf7f4d5',
  35         'info_dict': {
  36             'id': '57413289',
  37             'ext': 'mp4',
  38             'title': 'Lądowanie na lotnisku na Maderze',
  39             'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a',
  40             'thumbnail': r're:^https?://.*\.jpg$',
  41             'uploader': 'crash404',
  42             'view_count': int,
  43             'average_rating': float,
  44             'duration': 137
  45         }
  46     }, {
  47         'url': 'http://ebd.cda.pl/0x0/5749950c',
  48         'only_matching': True,
  49     }]
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53         self._set_cookie('cda.pl', 'cda.player', 'html5')
  54         webpage = self._download_webpage(
  55             self._BASE_URL + '/video/' + video_id, video_id)
  56
  57         if 'Ten film jest dostępny dla użytkowników premium' in webpage:
  58             raise ExtractorError('This video is only available for premium users.', expected=True)
  59
  60         formats = []
  61
  62         uploader = self._search_regex(r'''(?x)
  63             <(span|meta)[^>]+itemprop=(["\'])author\2[^>]*>
  64             (?:<\1[^>]*>[^<]*</\1>|(?!</\1>)(?:.|\n))*?
  65             <(span|meta)[^>]+itemprop=(["\'])name\4[^>]*>(?P<uploader>[^<]+)</\3>
  66         ''', webpage, 'uploader', default=None, group='uploader')
  67         view_count = self._search_regex(
  68             r'Odsłony:(?:\s|&nbsp;)*([0-9]+)', webpage,
  69             'view_count', default=None)
  70         average_rating = self._search_regex(
  71             r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
  72             webpage, 'rating', fatal=False, group='rating_value')
  73
  74         info_dict = {
  75             'id': video_id,
  76             'title': self._og_search_title(webpage),
  77             'description': self._og_search_description(webpage),
  78             'uploader': uploader,
  79             'view_count': int_or_none(view_count),
  80             'average_rating': float_or_none(average_rating),
  81             'thumbnail': self._og_search_thumbnail(webpage),
  82             'formats': formats,
  83             'duration': None,
  84         }
  85
  86         def extract_format(page, version):
  87             json_str = self._search_regex(
  88                 r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page,
  89                 '%s player_json' % version, fatal=False, group='player_data')
  90             if not json_str:
  91                 return
  92             player_data = self._parse_json(
  93                 json_str, '%s player_data' % version, fatal=False)
  94             if not player_data:
  95                 return
  96             video = player_data.get('video')
  97             if not video or 'file' not in video:
  98                 self.report_warning('Unable to extract %s version information' % version)
  99                 return
 100             if video['file'].startswith('uggc'):
 101                 video['file'] = codecs.decode(video['file'], 'rot_13')
 102                 if video['file'].endswith('adc.mp4'):
 103                     video['file'] = video['file'].replace('adc.mp4', '.mp4')
 104             f = {
 105                 'url': video['file'],
 106             }
 107             m = re.search(
 108                 r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
 109                 page)
 110             if m:
 111                 f.update({
 112                     'format_id': m.group('format_id'),
 113                     'height': int(m.group('height')),
 114                 })
 115             info_dict['formats'].append(f)
 116             if not info_dict['duration']:
 117                 info_dict['duration'] = parse_duration(video.get('duration'))
 118
 119         extract_format(webpage, 'default')
 120
 121         for href, resolution in re.findall(
 122                 r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
 123                 webpage):
 124             webpage = self._download_webpage(
 125                 self._BASE_URL + href, video_id,
 126                 'Downloading %s version information' % resolution, fatal=False)
 127             if not webpage:
 128                 # Manually report warning because empty page is returned when
 129                 # invalid version is requested.
 130                 self.report_warning('Unable to download %s version information' % resolution)
 131                 continue
 132             extract_format(webpage, resolution)
 133
 134         self._sort_formats(formats)
 135
 136         return info_dict