yt_dlp/extractor/vier.py

   1 import re
   2 import itertools
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     urlencode_postdata,
   7     int_or_none,
   8     unified_strdate,
   9 )
  10
  11
  12 class VierIE(InfoExtractor):
  13     IE_NAME = 'vier'
  14     IE_DESC = 'vier.be and vijf.be'
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         (?:www\.)?(?P<site>vier|vijf)\.be/
  18                         (?:
  19                             (?:
  20                                 [^/]+/videos|
  21                                 video(?:/[^/]+)*
  22                             )/
  23                             (?P<display_id>[^/]+)(?:/(?P<id>\d+))?|
  24                             (?:
  25                                 video/v3/embed|
  26                                 embed/video/public
  27                             )/(?P<embed_id>\d+)
  28                         )
  29                     '''
  30     _NETRC_MACHINE = 'vier'
  31     _TESTS = [{
  32         'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129',
  33         'md5': 'e4ae2054a6b040ef1e289e20d111b46e',
  34         'info_dict': {
  35             'id': '16129',
  36             'display_id': 'het-wordt-warm-de-moestuin',
  37             'ext': 'mp4',
  38             'title': 'Het wordt warm in De Moestuin',
  39             'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...',
  40             'upload_date': '20121025',
  41             'series': 'Plan B',
  42             'tags': ['De Moestuin', 'Moestuin', 'meisjes', 'Tomaat', 'Wim', 'Droom'],
  43         },
  44     }, {
  45         'url': 'http://www.vijf.be/temptationisland/videos/zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas/2561614',
  46         'info_dict': {
  47             'id': '2561614',
  48             'display_id': 'zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas',
  49             'ext': 'mp4',
  50             'title': 'md5:84f45fe48b8c1fa296a7f6d208d080a7',
  51             'description': 'md5:0356d4981e58b8cbee19355cbd51a8fe',
  52             'upload_date': '20170228',
  53             'series': 'Temptation Island',
  54             'tags': list,
  55         },
  56         'params': {
  57             'skip_download': True,
  58         },
  59     }, {
  60         'url': 'http://www.vier.be/janigaat/videos/jani-gaat-naar-tokio-aflevering-4/2674839',
  61         'info_dict': {
  62             'id': '2674839',
  63             'display_id': 'jani-gaat-naar-tokio-aflevering-4',
  64             'ext': 'mp4',
  65             'title': 'Jani gaat naar Tokio - Aflevering 4',
  66             'description': 'md5:aa8d611541db6ae9e863125704511f88',
  67             'upload_date': '20170501',
  68             'series': 'Jani gaat',
  69             'episode_number': 4,
  70             'tags': ['Jani Gaat', 'Volledige Aflevering'],
  71         },
  72         'params': {
  73             'skip_download': True,
  74         },
  75         'skip': 'Requires account credentials',
  76     }, {
  77         # Requires account credentials but bypassed extraction via v3/embed page
  78         # without metadata
  79         'url': 'http://www.vier.be/janigaat/videos/jani-gaat-naar-tokio-aflevering-4/2674839',
  80         'info_dict': {
  81             'id': '2674839',
  82             'display_id': 'jani-gaat-naar-tokio-aflevering-4',
  83             'ext': 'mp4',
  84             'title': 'jani-gaat-naar-tokio-aflevering-4',
  85         },
  86         'params': {
  87             'skip_download': True,
  88         },
  89         'expected_warnings': ['Log in to extract metadata'],
  90     }, {
  91         # Without video id in URL
  92         'url': 'http://www.vier.be/planb/videos/dit-najaar-plan-b',
  93         'only_matching': True,
  94     }, {
  95         'url': 'http://www.vier.be/video/v3/embed/16129',
  96         'only_matching': True,
  97     }, {
  98         'url': 'https://www.vijf.be/embed/video/public/4093',
  99         'only_matching': True,
 100     }, {
 101         'url': 'https://www.vier.be/video/blockbusters/in-juli-en-augustus-summer-classics',
 102         'only_matching': True,
 103     }, {
 104         'url': 'https://www.vier.be/video/achter-de-rug/2017/achter-de-rug-seizoen-1-aflevering-6',
 105         'only_matching': True,
 106     }]
 107
 108     def _real_initialize(self):
 109         self._logged_in = False
 110
 111     def _login(self, site):
 112         username, password = self._get_login_info()
 113         if username is None or password is None:
 114             return
 115
 116         login_page = self._download_webpage(
 117             'http://www.%s.be/user/login' % site,
 118             None, note='Logging in', errnote='Unable to log in',
 119             data=urlencode_postdata({
 120                 'form_id': 'user_login',
 121                 'name': username,
 122                 'pass': password,
 123             }),
 124             headers={'Content-Type': 'application/x-www-form-urlencoded'})
 125
 126         login_error = self._html_search_regex(
 127             r'(?s)<div class="messages error">\s*<div>\s*<h2.+?</h2>(.+?)<',
 128             login_page, 'login error', default=None)
 129         if login_error:
 130             self.report_warning('Unable to log in: %s' % login_error)
 131         else:
 132             self._logged_in = True
 133
 134     def _real_extract(self, url):
 135         mobj = self._match_valid_url(url)
 136         embed_id = mobj.group('embed_id')
 137         display_id = mobj.group('display_id') or embed_id
 138         video_id = mobj.group('id') or embed_id
 139         site = mobj.group('site')
 140
 141         if not self._logged_in:
 142             self._login(site)
 143
 144         webpage = self._download_webpage(url, display_id)
 145
 146         if r'id="user-login"' in webpage:
 147             self.report_warning(
 148                 'Log in to extract metadata', video_id=display_id)
 149             webpage = self._download_webpage(
 150                 'http://www.%s.be/video/v3/embed/%s' % (site, video_id),
 151                 display_id)
 152
 153         video_id = self._search_regex(
 154             [r'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'],
 155             webpage, 'video id', default=video_id or display_id)
 156
 157         playlist_url = self._search_regex(
 158             r'data-file=(["\'])(?P<url>(?:https?:)?//[^/]+/.+?\.m3u8.*?)\1',
 159             webpage, 'm3u8 url', default=None, group='url')
 160
 161         if not playlist_url:
 162             application = self._search_regex(
 163                 [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'],
 164                 webpage, 'application', default=site + '_vod')
 165             filename = self._search_regex(
 166                 [r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'],
 167                 webpage, 'filename')
 168             playlist_url = 'http://vod.streamcloud.be/%s/_definst_/mp4:%s.mp4/playlist.m3u8' % (application, filename)
 169
 170         formats = self._extract_wowza_formats(
 171             playlist_url, display_id, skip_protocols=['dash'])
 172         self._sort_formats(formats)
 173
 174         title = self._og_search_title(webpage, default=display_id)
 175         description = self._html_search_regex(
 176             r'(?s)<div\b[^>]+\bclass=(["\'])[^>]*?\bfield-type-text-with-summary\b[^>]*?\1[^>]*>.*?<p>(?P<value>.+?)</p>',
 177             webpage, 'description', default=None, group='value')
 178         thumbnail = self._og_search_thumbnail(webpage, default=None)
 179         upload_date = unified_strdate(self._html_search_regex(
 180             r'(?s)<div\b[^>]+\bclass=(["\'])[^>]*?\bfield-name-post-date\b[^>]*?\1[^>]*>.*?(?P<value>\d{2}/\d{2}/\d{4})',
 181             webpage, 'upload date', default=None, group='value'))
 182
 183         series = self._search_regex(
 184             r'data-program=(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
 185             'series', default=None, group='value')
 186         episode_number = int_or_none(self._search_regex(
 187             r'(?i)aflevering (\d+)', title, 'episode number', default=None))
 188         tags = re.findall(r'<a\b[^>]+\bhref=["\']/tags/[^>]+>([^<]+)<', webpage)
 189
 190         return {
 191             'id': video_id,
 192             'display_id': display_id,
 193             'title': title,
 194             'description': description,
 195             'thumbnail': thumbnail,
 196             'upload_date': upload_date,
 197             'series': series,
 198             'episode_number': episode_number,
 199             'tags': tags,
 200             'formats': formats,
 201         }
 202
 203
 204 class VierVideosIE(InfoExtractor):
 205     IE_NAME = 'vier:videos'
 206     _VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)'
 207     _TESTS = [{
 208         'url': 'http://www.vier.be/demoestuin/videos',
 209         'info_dict': {
 210             'id': 'demoestuin',
 211         },
 212         'playlist_mincount': 153,
 213     }, {
 214         'url': 'http://www.vijf.be/temptationisland/videos',
 215         'info_dict': {
 216             'id': 'temptationisland',
 217         },
 218         'playlist_mincount': 159,
 219     }, {
 220         'url': 'http://www.vier.be/demoestuin/videos?page=6',
 221         'info_dict': {
 222             'id': 'demoestuin-page6',
 223         },
 224         'playlist_mincount': 20,
 225     }, {
 226         'url': 'http://www.vier.be/demoestuin/videos?page=7',
 227         'info_dict': {
 228             'id': 'demoestuin-page7',
 229         },
 230         'playlist_mincount': 13,
 231     }]
 232
 233     def _real_extract(self, url):
 234         mobj = self._match_valid_url(url)
 235         program = mobj.group('program')
 236         site = mobj.group('site')
 237
 238         page_id = mobj.group('page')
 239         if page_id:
 240             page_id = int(page_id)
 241             start_page = page_id
 242             playlist_id = '%s-page%d' % (program, page_id)
 243         else:
 244             start_page = 0
 245             playlist_id = program
 246
 247         entries = []
 248         for current_page_id in itertools.count(start_page):
 249             current_page = self._download_webpage(
 250                 'http://www.%s.be/%s/videos?page=%d' % (site, program, current_page_id),
 251                 program,
 252                 'Downloading page %d' % (current_page_id + 1))
 253             page_entries = [
 254                 self.url_result('http://www.' + site + '.be' + video_url, 'Vier')
 255                 for video_url in re.findall(
 256                     r'<h[23]><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
 257             entries.extend(page_entries)
 258             if page_id or '>Meer<' not in current_page:
 259                 break
 260
 261         return self.playlist_result(entries, playlist_id)