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     strip_or_none,
  10 )
  11
  12
  13 class AZMedienBaseIE(InfoExtractor):
  14     def _kaltura_video(self, partner_id, entry_id):
  15         return self.url_result(
  16             'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(),
  17             video_id=entry_id)
  18
  19
  20 class AZMedienIE(AZMedienBaseIE):
  21     IE_DESC = 'AZ Medien videos'
  22     _VALID_URL = r'''(?x)
  23                     https?://
  24                         (?:www\.)?
  25                         (?:
  26                             telezueri\.ch|
  27                             telebaern\.tv|
  28                             telem1\.ch
  29                         )/
  30                         [0-9]+-show-[^/\#]+
  31                         (?:
  32                             /[0-9]+-episode-[^/\#]+
  33                             (?:
  34                                 /[0-9]+-segment-(?:[^/\#]+\#)?|
  35                                 \#
  36                             )|
  37                             \#
  38                         )
  39                         (?P<id>[^\#]+)
  40                     '''
  41
  42     _TESTS = [{
  43         # URL with 'segment'
  44         'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
  45         'info_dict': {
  46             'id': '1_2444peh4',
  47             'ext': 'mov',
  48             'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
  49             'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
  50             'uploader_id': 'TeleZ?ri',
  51             'upload_date': '20161218',
  52             'timestamp': 1482084490,
  53         },
  54         'params': {
  55             'skip_download': True,
  56         },
  57     }, {
  58         # URL with 'segment' and fragment:
  59         'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger',
  60         'only_matching': True
  61     }, {
  62         # URL with 'episode' and fragment:
  63         'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz',
  64         'only_matching': True
  65     }, {
  66         # URL with 'show' and fragment:
  67         'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch',
  68         'only_matching': True
  69     }]
  70
  71     def _real_extract(self, url):
  72         video_id = self._match_id(url)
  73
  74         webpage = self._download_webpage(url, video_id)
  75
  76         partner_id = self._search_regex(
  77             r'<script[^>]+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)',
  78             webpage, 'kaltura partner id')
  79         entry_id = self._html_search_regex(
  80             r'<a[^>]+data-id=(["\'])(?P<id>(?:(?!\1).)+)\1[^>]+data-slug=["\']%s'
  81             % re.escape(video_id), webpage, 'kaltura entry id', group='id')
  82
  83         return self._kaltura_video(partner_id, entry_id)
  84
  85
  86 class AZMedienShowIE(AZMedienBaseIE):
  87     IE_DESC = 'AZ Medien shows'
  88     _VALID_URL = r'''(?x)
  89                     https?://
  90                         (?:www\.)?
  91                         (?:
  92                             telezueri\.ch|
  93                             telebaern\.tv|
  94                             telem1\.ch
  95                         )/
  96                         (?P<id>[0-9]+-show-[^/\#]+
  97                             (?:
  98                                 /[0-9]+-episode-[^/\#]+
  99                             )?
 100                         )$
 101                     '''
 102
 103     _TESTS = [{
 104         # URL with 'episode'
 105         'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016',
 106         'info_dict': {
 107             'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016',
 108             'title': 'News - Donnerstag, 15. Dezember 2016',
 109         },
 110         'playlist_count': 9,
 111     }, {
 112         # URL with 'show' only
 113         'url': 'http://www.telezueri.ch/86-show-talktaeglich',
 114         'only_matching': True
 115     }]
 116
 117     def _real_extract(self, url):
 118         show_id = self._match_id(url)
 119         webpage = self._download_webpage(url, show_id)
 120
 121         entries = []
 122
 123         partner_id = self._search_regex(
 124             r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
 125             webpage, 'kaltura partner id', default=None)
 126
 127         if partner_id:
 128             entries = [
 129                 self._kaltura_video(partner_id, m.group('id'))
 130                 for m in re.finditer(
 131                     r'data-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage)]
 132
 133         if not entries:
 134             entries = [
 135                 self.url_result(m.group('url'), ie=AZMedienIE.ie_key())
 136                 for m in re.finditer(
 137                     r'<a[^>]+data-real=(["\'])(?P<url>http.+?)\1', webpage)]
 138
 139         title = self._search_regex(
 140             r'episodeShareTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
 141             webpage, 'title',
 142             default=strip_or_none(get_element_by_class(
 143                 'title-block-cell', webpage)), group='title')
 144
 145         return self.playlist_result(entries, show_id, title)