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\.)?vier\.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.vier.be/planb/videos/mieren-herders-van-de-bladluizen',
  28         'only_matching': True,
  29     }, {
  30         'url': 'http://www.vier.be/video/v3/embed/16129',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         mobj = re.match(self._VALID_URL, url)
  36         embed_id = mobj.group('embed_id')
  37         display_id = mobj.group('display_id') or embed_id
  38
  39         webpage = self._download_webpage(url, display_id)
  40
  41         video_id = self._search_regex(
  42             [r'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'],
  43             webpage, 'video id')
  44         application = self._search_regex(
  45             [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'],
  46             webpage, 'application', default='vier_vod')
  47         filename = self._search_regex(
  48             [r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'],
  49             webpage, 'filename')
  50
  51         playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename)
  52         formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4')
  53         self._sort_formats(formats)
  54
  55         title = self._og_search_title(webpage, default=display_id)
  56         description = self._og_search_description(webpage, default=None)
  57         thumbnail = self._og_search_thumbnail(webpage, default=None)
  58
  59         return {
  60             'id': video_id,
  61             'display_id': display_id,
  62             'title': title,
  63             'description': description,
  64             'thumbnail': thumbnail,
  65             'formats': formats,
  66         }
  67
  68
  69 class VierVideosIE(InfoExtractor):
  70     IE_NAME = 'vier:videos'
  71     _VALID_URL = r'https?://(?:www\.)?vier\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)'
  72     _TESTS = [{
  73         'url': 'http://www.vier.be/demoestuin/videos',
  74         'info_dict': {
  75             'id': 'demoestuin',
  76         },
  77         'playlist_mincount': 153,
  78     }, {
  79         'url': 'http://www.vier.be/demoestuin/videos?page=6',
  80         'info_dict': {
  81             'id': 'demoestuin-page6',
  82         },
  83         'playlist_mincount': 20,
  84     }, {
  85         'url': 'http://www.vier.be/demoestuin/videos?page=7',
  86         'info_dict': {
  87             'id': 'demoestuin-page7',
  88         },
  89         'playlist_mincount': 13,
  90     }]
  91
  92     def _real_extract(self, url):
  93         mobj = re.match(self._VALID_URL, url)
  94         program = mobj.group('program')
  95
  96         page_id = mobj.group('page')
  97         if page_id:
  98             page_id = int(page_id)
  99             start_page = page_id
 100             playlist_id = '%s-page%d' % (program, page_id)
 101         else:
 102             start_page = 0
 103             playlist_id = program
 104
 105         entries = []
 106         for current_page_id in itertools.count(start_page):
 107             current_page = self._download_webpage(
 108                 'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id),
 109                 program,
 110                 'Downloading page %d' % (current_page_id + 1))
 111             page_entries = [
 112                 self.url_result('http://www.vier.be' + video_url, 'Vier')
 113                 for video_url in re.findall(
 114                     r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
 115             entries.extend(page_entries)
 116             if page_id or '>Meer<' not in current_page:
 117                 break
 118
 119         return self.playlist_result(entries, playlist_id)