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 from ..utils import (
   9     urlencode_postdata,
  10     int_or_none,
  11     unified_strdate,
  12 )
  13
  14
  15 class VierIE(InfoExtractor):
  16     IE_NAME = 'vier'
  17     IE_DESC = 'vier.be and vijf.be'
  18     _VALID_URL = r'''(?x)
  19                     https?://
  20                         (?:www\.)?(?P<site>vier|vijf)\.be/
  21                         (?:
  22                             (?:
  23                                 [^/]+/videos|
  24                                 video(?:/[^/]+)*
  25                             )/
  26                             (?P<display_id>[^/]+)(?:/(?P<id>\d+))?|
  27                             (?:
  28                                 video/v3/embed|
  29                                 embed/video/public
  30                             )/(?P<embed_id>\d+)
  31                         )
  32                     '''
  33     _NETRC_MACHINE = 'vier'
  34     _TESTS = [{
  35         'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129',
  36         'md5': 'e4ae2054a6b040ef1e289e20d111b46e',
  37         'info_dict': {
  38             'id': '16129',
  39             'display_id': 'het-wordt-warm-de-moestuin',
  40             'ext': 'mp4',
  41             'title': 'Het wordt warm in De Moestuin',
  42             'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...',
  43             'upload_date': '20121025',
  44             'series': 'Plan B',
  45             'tags': ['De Moestuin', 'Moestuin', 'meisjes', 'Tomaat', 'Wim', 'Droom'],
  46         },
  47     }, {
  48         'url': 'http://www.vijf.be/temptationisland/videos/zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas/2561614',
  49         'info_dict': {
  50             'id': '2561614',
  51             'display_id': 'zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas',
  52             'ext': 'mp4',
  53             'title': 'md5:84f45fe48b8c1fa296a7f6d208d080a7',
  54             'description': 'md5:0356d4981e58b8cbee19355cbd51a8fe',
  55             'upload_date': '20170228',
  56             'series': 'Temptation Island',
  57             'tags': list,
  58         },
  59         'params': {
  60             'skip_download': True,
  61         },
  62     }, {
  63         'url': 'http://www.vier.be/janigaat/videos/jani-gaat-naar-tokio-aflevering-4/2674839',
  64         'info_dict': {
  65             'id': '2674839',
  66             'display_id': 'jani-gaat-naar-tokio-aflevering-4',
  67             'ext': 'mp4',
  68             'title': 'Jani gaat naar Tokio - Aflevering 4',
  69             'description': 'md5:aa8d611541db6ae9e863125704511f88',
  70             'upload_date': '20170501',
  71             'series': 'Jani gaat',
  72             'episode_number': 4,
  73             'tags': ['Jani Gaat', 'Volledige Aflevering'],
  74         },
  75         'params': {
  76             'skip_download': True,
  77         },
  78         'skip': 'Requires account credentials',
  79     }, {
  80         # Requires account credentials but bypassed extraction via v3/embed page
  81         # without metadata
  82         'url': 'http://www.vier.be/janigaat/videos/jani-gaat-naar-tokio-aflevering-4/2674839',
  83         'info_dict': {
  84             'id': '2674839',
  85             'display_id': 'jani-gaat-naar-tokio-aflevering-4',
  86             'ext': 'mp4',
  87             'title': 'jani-gaat-naar-tokio-aflevering-4',
  88         },
  89         'params': {
  90             'skip_download': True,
  91         },
  92         'expected_warnings': ['Log in to extract metadata'],
  93     }, {
  94         # Without video id in URL
  95         'url': 'http://www.vier.be/planb/videos/dit-najaar-plan-b',
  96         'only_matching': True,
  97     }, {
  98         'url': 'http://www.vier.be/video/v3/embed/16129',
  99         'only_matching': True,
 100     }, {
 101         'url': 'https://www.vijf.be/embed/video/public/4093',
 102         'only_matching': True,
 103     }, {
 104         'url': 'https://www.vier.be/video/blockbusters/in-juli-en-augustus-summer-classics',
 105         'only_matching': True,
 106     }, {
 107         'url': 'https://www.vier.be/video/achter-de-rug/2017/achter-de-rug-seizoen-1-aflevering-6',
 108         'only_matching': True,
 109     }]
 110
 111     def _real_initialize(self):
 112         self._logged_in = False
 113
 114     def _login(self, site):
 115         username, password = self._get_login_info()
 116         if username is None or password is None:
 117             return
 118
 119         login_page = self._download_webpage(
 120             'http://www.%s.be/user/login' % site,
 121             None, note='Logging in', errnote='Unable to log in',
 122             data=urlencode_postdata({
 123                 'form_id': 'user_login',
 124                 'name': username,
 125                 'pass': password,
 126             }),
 127             headers={'Content-Type': 'application/x-www-form-urlencoded'})
 128
 129         login_error = self._html_search_regex(
 130             r'(?s)<div class="messages error">\s*<div>\s*<h2.+?</h2>(.+?)<',
 131             login_page, 'login error', default=None)
 132         if login_error:
 133             self.report_warning('Unable to log in: %s' % login_error)
 134         else:
 135             self._logged_in = True
 136
 137     def _real_extract(self, url):
 138         mobj = re.match(self._VALID_URL, url)
 139         embed_id = mobj.group('embed_id')
 140         display_id = mobj.group('display_id') or embed_id
 141         video_id = mobj.group('id') or embed_id
 142         site = mobj.group('site')
 143
 144         if not self._logged_in:
 145             self._login(site)
 146
 147         webpage = self._download_webpage(url, display_id)
 148
 149         if r'id="user-login"' in webpage:
 150             self.report_warning(
 151                 'Log in to extract metadata', video_id=display_id)
 152             webpage = self._download_webpage(
 153                 'http://www.%s.be/video/v3/embed/%s' % (site, video_id),
 154                 display_id)
 155
 156         video_id = self._search_regex(
 157             [r'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'],
 158             webpage, 'video id', default=video_id or display_id)
 159
 160         playlist_url = self._search_regex(
 161             r'data-file=(["\'])(?P<url>(?:https?:)?//[^/]+/.+?\.m3u8.*?)\1',
 162             webpage, 'm3u8 url', default=None, group='url')
 163
 164         if not playlist_url:
 165             application = self._search_regex(
 166                 [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'],
 167                 webpage, 'application', default=site + '_vod')
 168             filename = self._search_regex(
 169                 [r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'],
 170                 webpage, 'filename')
 171             playlist_url = 'http://vod.streamcloud.be/%s/_definst_/mp4:%s.mp4/playlist.m3u8' % (application, filename)
 172
 173         formats = self._extract_wowza_formats(
 174             playlist_url, display_id, skip_protocols=['dash'])
 175         self._sort_formats(formats)
 176
 177         title = self._og_search_title(webpage, default=display_id)
 178         description = self._html_search_regex(
 179             r'(?s)<div\b[^>]+\bclass=(["\'])[^>]*?\bfield-type-text-with-summary\b[^>]*?\1[^>]*>.*?<p>(?P<value>.+?)</p>',
 180             webpage, 'description', default=None, group='value')
 181         thumbnail = self._og_search_thumbnail(webpage, default=None)
 182         upload_date = unified_strdate(self._html_search_regex(
 183             r'(?s)<div\b[^>]+\bclass=(["\'])[^>]*?\bfield-name-post-date\b[^>]*?\1[^>]*>.*?(?P<value>\d{2}/\d{2}/\d{4})',
 184             webpage, 'upload date', default=None, group='value'))
 185
 186         series = self._search_regex(
 187             r'data-program=(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
 188             'series', default=None, group='value')
 189         episode_number = int_or_none(self._search_regex(
 190             r'(?i)aflevering (\d+)', title, 'episode number', default=None))
 191         tags = re.findall(r'<a\b[^>]+\bhref=["\']/tags/[^>]+>([^<]+)<', webpage)
 192
 193         return {
 194             'id': video_id,
 195             'display_id': display_id,
 196             'title': title,
 197             'description': description,
 198             'thumbnail': thumbnail,
 199             'upload_date': upload_date,
 200             'series': series,
 201             'episode_number': episode_number,
 202             'tags': tags,
 203             'formats': formats,
 204         }
 205
 206
 207 class VierVideosIE(InfoExtractor):
 208     IE_NAME = 'vier:videos'
 209     _VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)'
 210     _TESTS = [{
 211         'url': 'http://www.vier.be/demoestuin/videos',
 212         'info_dict': {
 213             'id': 'demoestuin',
 214         },
 215         'playlist_mincount': 153,
 216     }, {
 217         'url': 'http://www.vijf.be/temptationisland/videos',
 218         'info_dict': {
 219             'id': 'temptationisland',
 220         },
 221         'playlist_mincount': 159,
 222     }, {
 223         'url': 'http://www.vier.be/demoestuin/videos?page=6',
 224         'info_dict': {
 225             'id': 'demoestuin-page6',
 226         },
 227         'playlist_mincount': 20,
 228     }, {
 229         'url': 'http://www.vier.be/demoestuin/videos?page=7',
 230         'info_dict': {
 231             'id': 'demoestuin-page7',
 232         },
 233         'playlist_mincount': 13,
 234     }]
 235
 236     def _real_extract(self, url):
 237         mobj = re.match(self._VALID_URL, url)
 238         program = mobj.group('program')
 239         site = mobj.group('site')
 240
 241         page_id = mobj.group('page')
 242         if page_id:
 243             page_id = int(page_id)
 244             start_page = page_id
 245             playlist_id = '%s-page%d' % (program, page_id)
 246         else:
 247             start_page = 0
 248             playlist_id = program
 249
 250         entries = []
 251         for current_page_id in itertools.count(start_page):
 252             current_page = self._download_webpage(
 253                 'http://www.%s.be/%s/videos?page=%d' % (site, program, current_page_id),
 254                 program,
 255                 'Downloading page %d' % (current_page_id + 1))
 256             page_entries = [
 257                 self.url_result('http://www.' + site + '.be' + video_url, 'Vier')
 258                 for video_url in re.findall(
 259                     r'<h[23]><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
 260             entries.extend(page_entries)
 261             if page_id or '>Meer<' not in current_page:
 262                 break
 263
 264         return self.playlist_result(entries, playlist_id)