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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import itertools
   6
   7 from .common import InfoExtractor
   8
   9
  10 class VierIE(InfoExtractor):
  11     IE_NAME = 'vier'
  12     _VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))'
  13     _TESTS = [{
  14         'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129',
  15         'info_dict': {
  16             'id': '16129',
  17             'display_id': 'het-wordt-warm-de-moestuin',
  18             'ext': 'mp4',
  19             'title': 'Het wordt warm in De Moestuin',
  20             'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...',
  21         },
  22         'params': {
  23             # m3u8 download
  24             'skip_download': True,
  25         },
  26     }, {
  27         'url': 'http://www.vijf.be/temptationisland/videos/zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas/2561614',
  28         'info_dict': {
  29             'id': '2561614',
  30             'display_id': 'zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas',
  31             'ext': 'mp4',
  32             'title': 'ZO grappig: Temptation Island hosts moeten kiezen tussen onmogelijke dilemma\'s',
  33             'description': 'Het spel is simpel: Annelien Coorevits en Rick Brandsteder krijgen telkens 2 dilemma\'s voorgeschoteld en ze MOETEN een keuze maken.',
  34         },
  35         'params': {
  36             # m3u8 download
  37             'skip_download': True,
  38         },
  39     }, {
  40         'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://www.vier.be/video/v3/embed/16129',
  44         'only_matching': True,
  45     }]
  46
  47     def _real_extract(self, url):
  48         mobj = re.match(self._VALID_URL, url)
  49         embed_id = mobj.group('embed_id')
  50         display_id = mobj.group('display_id') or embed_id
  51         site = mobj.group('site')
  52
  53         webpage = self._download_webpage(url, display_id)
  54
  55         video_id = self._search_regex(
  56             [r'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'],
  57             webpage, 'video id')
  58         application = self._search_regex(
  59             [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'],
  60             webpage, 'application', default=site + '_vod')
  61         filename = self._search_regex(
  62             [r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'],
  63             webpage, 'filename')
  64
  65         playlist_url = 'http://vod.streamcloud.be/%s/_definst_/mp4:%s.mp4/playlist.m3u8' % (application, filename)
  66         formats = self._extract_wowza_formats(playlist_url, display_id, skip_protocols=['dash'])
  67         self._sort_formats(formats)
  68
  69         title = self._og_search_title(webpage, default=display_id)
  70         description = self._og_search_description(webpage, default=None)
  71         thumbnail = self._og_search_thumbnail(webpage, default=None)
  72
  73         return {
  74             'id': video_id,
  75             'display_id': display_id,
  76             'title': title,
  77             'description': description,
  78             'thumbnail': thumbnail,
  79             'formats': formats,
  80         }
  81
  82
  83 class VierVideosIE(InfoExtractor):
  84     IE_NAME = 'vier:videos'
  85     _VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)'
  86     _TESTS = [{
  87         'url': 'http://www.vier.be/demoestuin/videos',
  88         'info_dict': {
  89             'id': 'demoestuin',
  90         },
  91         'playlist_mincount': 153,
  92     }, {
  93         'url': 'http://www.vijf.be/temptationisland/videos',
  94         'info_dict': {
  95             'id': 'temptationisland',
  96         },
  97         'playlist_mincount': 159,
  98     }, {
  99         'url': 'http://www.vier.be/demoestuin/videos?page=6',
 100         'info_dict': {
 101             'id': 'demoestuin-page6',
 102         },
 103         'playlist_mincount': 20,
 104     }, {
 105         'url': 'http://www.vier.be/demoestuin/videos?page=7',
 106         'info_dict': {
 107             'id': 'demoestuin-page7',
 108         },
 109         'playlist_mincount': 13,
 110     }]
 111
 112     def _real_extract(self, url):
 113         mobj = re.match(self._VALID_URL, url)
 114         program = mobj.group('program')
 115         site = mobj.group('site')
 116
 117         page_id = mobj.group('page')
 118         if page_id:
 119             page_id = int(page_id)
 120             start_page = page_id
 121             playlist_id = '%s-page%d' % (program, page_id)
 122         else:
 123             start_page = 0
 124             playlist_id = program
 125
 126         entries = []
 127         for current_page_id in itertools.count(start_page):
 128             current_page = self._download_webpage(
 129                 'http://www.%s.be/%s/videos?page=%d' % (site, program, current_page_id),
 130                 program,
 131                 'Downloading page %d' % (current_page_id + 1))
 132             page_entries = [
 133                 self.url_result('http://www.' + site + '.be' + video_url, 'Vier')
 134                 for video_url in re.findall(
 135                     r'<h[23]><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
 136             entries.extend(page_entries)
 137             if page_id or '>Meer<' not in current_page:
 138                 break
 139
 140         return self.playlist_result(entries, playlist_id)