_ Git - youtube-dl/blob - youtube_dl/extractor/azmedien.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .kaltura import KalturaIE
   7 from ..utils import (
   8     get_element_by_class,
   9     get_element_by_id,
  10     strip_or_none,
  11     urljoin,
  12 )
  13
  14
  15 class AZMedienBaseIE(InfoExtractor):
  16     def _kaltura_video(self, partner_id, entry_id):
  17         return self.url_result(
  18             'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(),
  19             video_id=entry_id)
  20
  21
  22 class AZMedienIE(AZMedienBaseIE):
  23     IE_DESC = 'AZ Medien videos'
  24     _VALID_URL = r'''(?x)
  25                     https?://
  26                         (?:www\.)?
  27                         (?:
  28                             telezueri\.ch|
  29                             telebaern\.tv|
  30                             telem1\.ch
  31                         )/
  32                         [0-9]+-show-[^/\#]+
  33                         (?:
  34                             /[0-9]+-episode-[^/\#]+
  35                             (?:
  36                                 /[0-9]+-segment-(?:[^/\#]+\#)?|
  37                                 \#
  38                             )|
  39                             \#
  40                         )
  41                         (?P<id>[^\#]+)
  42                     '''
  43
  44     _TESTS = [{
  45         # URL with 'segment'
  46         'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
  47         'info_dict': {
  48             'id': '1_2444peh4',
  49             'ext': 'mov',
  50             'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
  51             'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
  52             'uploader_id': 'TeleZ?ri',
  53             'upload_date': '20161218',
  54             'timestamp': 1482084490,
  55         },
  56         'params': {
  57             'skip_download': True,
  58         },
  59     }, {
  60         # URL with 'segment' and fragment:
  61         'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger',
  62         'only_matching': True
  63     }, {
  64         # URL with 'episode' and fragment:
  65         'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz',
  66         'only_matching': True
  67     }, {
  68         # URL with 'show' and fragment:
  69         'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch',
  70         'only_matching': True
  71     }]
  72
  73     def _real_extract(self, url):
  74         video_id = self._match_id(url)
  75
  76         webpage = self._download_webpage(url, video_id)
  77
  78         partner_id = self._search_regex(
  79             r'<script[^>]+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)',
  80             webpage, 'kaltura partner id')
  81         entry_id = self._html_search_regex(
  82             r'<a[^>]+data-id=(["\'])(?P<id>(?:(?!\1).)+)\1[^>]+data-slug=["\']%s'
  83             % re.escape(video_id), webpage, 'kaltura entry id', group='id')
  84
  85         return self._kaltura_video(partner_id, entry_id)
  86
  87
  88 class AZMedienPlaylistIE(AZMedienBaseIE):
  89     IE_DESC = 'AZ Medien playlists'
  90     _VALID_URL = r'''(?x)
  91                     https?://
  92                         (?:www\.)?
  93                         (?:
  94                             telezueri\.ch|
  95                             telebaern\.tv|
  96                             telem1\.ch
  97                         )/
  98                         (?P<id>[0-9]+-
  99                             (?:
 100                                 show|
 101                                 topic|
 102                                 themen
 103                             )-[^/\#]+
 104                             (?:
 105                                 /[0-9]+-episode-[^/\#]+
 106                             )?
 107                         )$
 108                     '''
 109
 110     _TESTS = [{
 111         # URL with 'episode'
 112         'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016',
 113         'info_dict': {
 114             'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016',
 115             'title': 'News - Donnerstag, 15. Dezember 2016',
 116         },
 117         'playlist_count': 9,
 118     }, {
 119         # URL with 'themen'
 120         'url': 'http://www.telem1.ch/258-themen-tele-m1-classics',
 121         'info_dict': {
 122             'id': '258-themen-tele-m1-classics',
 123             'title': 'Tele M1 Classics',
 124         },
 125         'playlist_mincount': 15,
 126     }, {
 127         # URL with 'topic', contains nested playlists
 128         'url': 'http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen',
 129         'only_matching': True,
 130     }, {
 131         # URL with 'show' only
 132         'url': 'http://www.telezueri.ch/86-show-talktaeglich',
 133         'only_matching': True
 134     }]
 135
 136     def _real_extract(self, url):
 137         show_id = self._match_id(url)
 138         webpage = self._download_webpage(url, show_id)
 139
 140         entries = []
 141
 142         partner_id = self._search_regex(
 143             r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
 144             webpage, 'kaltura partner id', default=None)
 145
 146         if partner_id:
 147             entries = [
 148                 self._kaltura_video(partner_id, m.group('id'))
 149                 for m in re.finditer(
 150                     r'data-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage)]
 151
 152         if not entries:
 153             entries = [
 154                 self.url_result(m.group('url'), ie=AZMedienIE.ie_key())
 155                 for m in re.finditer(
 156                     r'<a[^>]+data-real=(["\'])(?P<url>http.+?)\1', webpage)]
 157
 158         if not entries:
 159             entries = [
 160                 # May contain nested playlists (e.g. [1]) thus no explicit
 161                 # ie_key
 162                 # 1. http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen)
 163                 self.url_result(urljoin(url, m.group('url')))
 164                 for m in re.finditer(
 165                     r'<a[^>]+name=[^>]+href=(["\'])(?P<url>/.+?)\1', webpage)]
 166
 167         title = self._search_regex(
 168             r'episodeShareTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
 169             webpage, 'title',
 170             default=strip_or_none(get_element_by_id(
 171                 'video-title', webpage)), group='title')
 172
 173         return self.playlist_result(entries, show_id, title)
 174
 175
 176 class AZMedienShowPlaylistIE(AZMedienBaseIE):
 177     IE_DESC = 'AZ Medien Show playlists'
 178     _VALID_URL = r'''(?x)
 179                     https?://
 180                         (?:www\.)?
 181                         (?P<id>
 182                         (?:
 183                             telezueri\.ch|
 184                             telebaern\.tv|
 185                             telem1\.ch
 186                         )/
 187                         (?:
 188                             all-episodes|
 189                             alle-episoden
 190                         )
 191                         /[^/]+
 192                         )
 193                     '''
 194
 195     _TEST = {
 196         'url': 'http://www.telezueri.ch/all-episodes/astrotalk',
 197         'info_dict': {
 198             'id': 'telezueri.ch/all-episodes/astrotalk',
 199             'title': 'TeleZüri: AstroTalk - alle episoden',
 200             'description': 'md5:4c0f7e7d741d906004266e295ceb4a26',
 201         },
 202         'playlist_mincount': 13,
 203         'params': {
 204             'skip_download': True,
 205         }
 206     }
 207
 208     def _real_extract(self, url):
 209         playlist_id = self._match_id(url)
 210         webpage = self._download_webpage(url, playlist_id)
 211         episodes = get_element_by_class('search-mobile-box', webpage)
 212         entries = [self.url_result(
 213             urljoin(url, m.group('url'))) for m in re.finditer(
 214                 r'<a[^>]+href=(["\'])(?P<url>.+?)\1', episodes)]
 215         title = self._og_search_title(webpage)
 216         description = self._og_search_description(webpage)
 217         return self.playlist_result(
 218             entries,
 219             playlist_id=playlist_id,
 220             playlist_title=title,
 221             playlist_description=description)