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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .kaltura import KalturaIE
   8 from ..utils import (
   9     get_element_by_class,
  10     get_element_by_id,
  11     strip_or_none,
  12     urljoin,
  13 )
  14
  15
  16 class AZMedienBaseIE(InfoExtractor):
  17     def _kaltura_video(self, partner_id, entry_id):
  18         return self.url_result(
  19             'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(),
  20             video_id=entry_id)
  21
  22
  23 class AZMedienIE(AZMedienBaseIE):
  24     IE_DESC = 'AZ Medien videos'
  25     _VALID_URL = r'''(?x)
  26                     https?://
  27                         (?:www\.)?
  28                         (?:
  29                             telezueri\.ch|
  30                             telebaern\.tv|
  31                             telem1\.ch
  32                         )/
  33                         [0-9]+-show-[^/\#]+
  34                         (?:
  35                             /[0-9]+-episode-[^/\#]+
  36                             (?:
  37                                 /[0-9]+-segment-(?:[^/\#]+\#)?|
  38                                 \#
  39                             )|
  40                             \#
  41                         )
  42                         (?P<id>[^\#]+)
  43                     '''
  44
  45     _TESTS = [{
  46         # URL with 'segment'
  47         'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
  48         'info_dict': {
  49             'id': '1_2444peh4',
  50             'ext': 'mp4',
  51             'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
  52             'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
  53             'uploader_id': 'TeleZ?ri',
  54             'upload_date': '20161218',
  55             'timestamp': 1482084490,
  56         },
  57         'params': {
  58             'skip_download': True,
  59         },
  60     }, {
  61         # URL with 'segment' and fragment:
  62         'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger',
  63         'only_matching': True
  64     }, {
  65         # URL with 'episode' and fragment:
  66         'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz',
  67         'only_matching': True
  68     }, {
  69         # URL with 'show' and fragment:
  70         'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch',
  71         'only_matching': True
  72     }]
  73
  74     def _real_extract(self, url):
  75         video_id = self._match_id(url)
  76
  77         webpage = self._download_webpage(url, video_id)
  78
  79         partner_id = self._search_regex(
  80             r'<script[^>]+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)',
  81             webpage, 'kaltura partner id')
  82         entry_id = self._html_search_regex(
  83             r'<a[^>]+data-id=(["\'])(?P<id>(?:(?!\1).)+)\1[^>]+data-slug=["\']%s'
  84             % re.escape(video_id), webpage, 'kaltura entry id', group='id')
  85
  86         return self._kaltura_video(partner_id, entry_id)
  87
  88
  89 class AZMedienPlaylistIE(AZMedienBaseIE):
  90     IE_DESC = 'AZ Medien playlists'
  91     _VALID_URL = r'''(?x)
  92                     https?://
  93                         (?:www\.)?
  94                         (?:
  95                             telezueri\.ch|
  96                             telebaern\.tv|
  97                             telem1\.ch
  98                         )/
  99                         (?P<id>[0-9]+-
 100                             (?:
 101                                 show|
 102                                 topic|
 103                                 themen
 104                             )-[^/\#]+
 105                             (?:
 106                                 /[0-9]+-episode-[^/\#]+
 107                             )?
 108                         )$
 109                     '''
 110
 111     _TESTS = [{
 112         # URL with 'episode'
 113         'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016',
 114         'info_dict': {
 115             'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016',
 116             'title': 'News - Donnerstag, 15. Dezember 2016',
 117         },
 118         'playlist_count': 9,
 119     }, {
 120         # URL with 'themen'
 121         'url': 'http://www.telem1.ch/258-themen-tele-m1-classics',
 122         'info_dict': {
 123             'id': '258-themen-tele-m1-classics',
 124             'title': 'Tele M1 Classics',
 125         },
 126         'playlist_mincount': 15,
 127     }, {
 128         # URL with 'topic', contains nested playlists
 129         'url': 'http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen',
 130         'only_matching': True,
 131     }, {
 132         # URL with 'show' only
 133         'url': 'http://www.telezueri.ch/86-show-talktaeglich',
 134         'only_matching': True
 135     }]
 136
 137     def _real_extract(self, url):
 138         show_id = self._match_id(url)
 139         webpage = self._download_webpage(url, show_id)
 140
 141         entries = []
 142
 143         partner_id = self._search_regex(
 144             r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
 145             webpage, 'kaltura partner id', default=None)
 146
 147         if partner_id:
 148             entries = [
 149                 self._kaltura_video(partner_id, m.group('id'))
 150                 for m in re.finditer(
 151                     r'data-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage)]
 152
 153         if not entries:
 154             entries = [
 155                 self.url_result(m.group('url'), ie=AZMedienIE.ie_key())
 156                 for m in re.finditer(
 157                     r'<a[^>]+data-real=(["\'])(?P<url>http.+?)\1', webpage)]
 158
 159         if not entries:
 160             entries = [
 161                 # May contain nested playlists (e.g. [1]) thus no explicit
 162                 # ie_key
 163                 # 1. http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen)
 164                 self.url_result(urljoin(url, m.group('url')))
 165                 for m in re.finditer(
 166                     r'<a[^>]+name=[^>]+href=(["\'])(?P<url>/.+?)\1', webpage)]
 167
 168         title = self._search_regex(
 169             r'episodeShareTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
 170             webpage, 'title',
 171             default=strip_or_none(get_element_by_id(
 172                 'video-title', webpage)), group='title')
 173
 174         return self.playlist_result(entries, show_id, title)
 175
 176
 177 class AZMedienShowPlaylistIE(AZMedienBaseIE):
 178     IE_DESC = 'AZ Medien show playlists'
 179     _VALID_URL = r'''(?x)
 180                     https?://
 181                         (?:www\.)?
 182                         (?:
 183                             telezueri\.ch|
 184                             telebaern\.tv|
 185                             telem1\.ch
 186                         )/
 187                         (?:
 188                             all-episodes|
 189                             alle-episoden
 190                         )/
 191                         (?P<id>[^/?#&]+)
 192                     '''
 193
 194     _TEST = {
 195         'url': 'http://www.telezueri.ch/all-episodes/astrotalk',
 196         'info_dict': {
 197             'id': 'astrotalk',
 198             'title': 'TeleZüri: AstroTalk - alle episoden',
 199             'description': 'md5:4c0f7e7d741d906004266e295ceb4a26',
 200         },
 201         'playlist_mincount': 13,
 202     }
 203
 204     def _real_extract(self, url):
 205         playlist_id = self._match_id(url)
 206         webpage = self._download_webpage(url, playlist_id)
 207         episodes = get_element_by_class('search-mobile-box', webpage)
 208         entries = [self.url_result(
 209             urljoin(url, m.group('url'))) for m in re.finditer(
 210                 r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', episodes)]
 211         title = self._og_search_title(webpage, fatal=False)
 212         description = self._og_search_description(webpage)
 213         return self.playlist_result(entries, playlist_id, title, description)