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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     int_or_none,
  10     js_to_json,
  11     strip_or_none,
  12     try_get,
  13     unescapeHTML,
  14     unified_timestamp,
  15 )
  16
  17
  18 class WatchBoxIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?watchbox\.de/(?P<kind>serien|filme)/(?:[^/]+/)*[^/]+-(?P<id>\d+)'
  20     _TESTS = [{
  21         # film
  22         'url': 'https://www.watchbox.de/filme/free-jimmy-12325.html',
  23         'info_dict': {
  24             'id': '341368',
  25             'ext': 'mp4',
  26             'title': 'Free Jimmy',
  27             'description': 'md5:bcd8bafbbf9dc0ef98063d344d7cc5f6',
  28             'thumbnail': r're:^https?://.*\.jpg$',
  29             'duration': 4890,
  30             'age_limit': 16,
  31             'release_year': 2009,
  32         },
  33         'params': {
  34             'format': 'bestvideo',
  35             'skip_download': True,
  36         },
  37         'expected_warnings': ['Failed to download m3u8 information'],
  38     }, {
  39         # episode
  40         'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-1/date-in-der-hoelle-328286.html',
  41         'info_dict': {
  42             'id': '328286',
  43             'ext': 'mp4',
  44             'title': 'S01 E01 - Date in der Hölle',
  45             'description': 'md5:2f31c74a8186899f33cb5114491dae2b',
  46             'thumbnail': r're:^https?://.*\.jpg$',
  47             'duration': 1291,
  48             'age_limit': 12,
  49             'release_year': 2010,
  50             'series': 'Ugly Americans',
  51             'season_number': 1,
  52             'episode': 'Date in der Hölle',
  53             'episode_number': 1,
  54         },
  55         'params': {
  56             'format': 'bestvideo',
  57             'skip_download': True,
  58         },
  59         'expected_warnings': ['Failed to download m3u8 information'],
  60     }, {
  61         'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-2/der-ring-des-powers-328270',
  62         'only_matching': True,
  63     }]
  64
  65     def _real_extract(self, url):
  66         mobj = re.match(self._VALID_URL, url)
  67         kind, video_id = mobj.group('kind', 'id')
  68
  69         webpage = self._download_webpage(url, video_id)
  70
  71         player_config = self._parse_json(
  72             self._search_regex(
  73                 r'data-player-conf=(["\'])(?P<data>{.+?})\1', webpage,
  74                 'player config', default='{}', group='data'),
  75             video_id, transform_source=unescapeHTML, fatal=False)
  76
  77         if not player_config:
  78             player_config = self._parse_json(
  79                 self._search_regex(
  80                     r'playerConf\s*=\s*({.+?})\s*;', webpage, 'player config',
  81                     default='{}'),
  82                 video_id, transform_source=js_to_json, fatal=False) or {}
  83
  84         source = player_config.get('source') or {}
  85
  86         video_id = compat_str(source.get('videoId') or video_id)
  87
  88         devapi = self._download_json(
  89             'http://api.watchbox.de/devapi/id/%s' % video_id, video_id, query={
  90                 'format': 'json',
  91                 'apikey': 'hbbtv',
  92             }, fatal=False)
  93
  94         item = try_get(devapi, lambda x: x['items'][0], dict) or {}
  95
  96         title = item.get('title') or try_get(
  97             item, lambda x: x['movie']['headline_movie'],
  98             compat_str) or source['title']
  99
 100         formats = []
 101         hls_url = item.get('media_videourl_hls') or source.get('hls')
 102         if hls_url:
 103             formats.extend(self._extract_m3u8_formats(
 104                 hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
 105                 m3u8_id='hls', fatal=False))
 106         dash_url = item.get('media_videourl_wv') or source.get('dash')
 107         if dash_url:
 108             formats.extend(self._extract_mpd_formats(
 109                 dash_url, video_id, mpd_id='dash', fatal=False))
 110         mp4_url = item.get('media_videourl')
 111         if mp4_url:
 112             formats.append({
 113                 'url': mp4_url,
 114                 'format_id': 'mp4',
 115                 'width': int_or_none(item.get('width')),
 116                 'height': int_or_none(item.get('height')),
 117                 'tbr': int_or_none(item.get('bitrate')),
 118             })
 119         self._sort_formats(formats)
 120
 121         description = strip_or_none(item.get('descr'))
 122         thumbnail = item.get('media_content_thumbnail_large') or source.get('poster') or item.get('media_thumbnail')
 123         duration = int_or_none(item.get('media_length') or source.get('length'))
 124         timestamp = unified_timestamp(item.get('pubDate'))
 125         view_count = int_or_none(item.get('media_views'))
 126         age_limit = int_or_none(try_get(item, lambda x: x['movie']['fsk']))
 127         release_year = int_or_none(try_get(item, lambda x: x['movie']['rel_year']))
 128
 129         info = {
 130             'id': video_id,
 131             'title': title,
 132             'description': description,
 133             'thumbnail': thumbnail,
 134             'duration': duration,
 135             'timestamp': timestamp,
 136             'view_count': view_count,
 137             'age_limit': age_limit,
 138             'release_year': release_year,
 139             'formats': formats,
 140         }
 141
 142         if kind.lower() == 'serien':
 143             series = try_get(
 144                 item, lambda x: x['special']['title'],
 145                 compat_str) or source.get('format')
 146             season_number = int_or_none(self._search_regex(
 147                 r'^S(\d{1,2})\s*E\d{1,2}', title, 'season number',
 148                 default=None) or self._search_regex(
 149                     r'/staffel-(\d+)/', url, 'season number', default=None))
 150             episode = source.get('title')
 151             episode_number = int_or_none(self._search_regex(
 152                 r'^S\d{1,2}\s*E(\d{1,2})', title, 'episode number',
 153                 default=None))
 154             info.update({
 155                 'series': series,
 156                 'season_number': season_number,
 157                 'episode': episode,
 158                 'episode_number': episode_number,
 159             })
 160
 161         return info