_ Git - youtube-dl/blob - youtube_dl/extractor/wdr.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import itertools
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_parse_qs,
  10     compat_urlparse,
  11 )
  12 from ..utils import (
  13     unified_strdate,
  14     qualities,
  15 )
  16
  17
  18 class WDRIE(InfoExtractor):
  19     _PLAYER_REGEX = '-(?:video|audio)player(?:_size-[LMS])?'
  20     _VALID_URL = r'(?P<url>https?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX
  21
  22     _TESTS = [
  23         {
  24             'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
  25             'info_dict': {
  26                 'id': 'mdb-362427',
  27                 'ext': 'flv',
  28                 'title': 'Servicezeit',
  29                 'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
  30                 'upload_date': '20140310',
  31                 'is_live': False
  32             },
  33             'params': {
  34                 'skip_download': True,
  35             },
  36             'skip': 'Page Not Found',
  37         },
  38         {
  39             'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
  40             'info_dict': {
  41                 'id': 'mdb-363194',
  42                 'ext': 'flv',
  43                 'title': 'Marga Spiegel ist tot',
  44                 'description': 'md5:2309992a6716c347891c045be50992e4',
  45                 'upload_date': '20140311',
  46                 'is_live': False
  47             },
  48             'params': {
  49                 'skip_download': True,
  50             },
  51             'skip': 'Page Not Found',
  52         },
  53         {
  54             'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
  55             'md5': '83e9e8fefad36f357278759870805898',
  56             'info_dict': {
  57                 'id': 'mdb-194332',
  58                 'ext': 'mp3',
  59                 'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
  60                 'description': 'md5:2309992a6716c347891c045be50992e4',
  61                 'upload_date': '20091129',
  62                 'is_live': False
  63             },
  64         },
  65         {
  66             'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
  67             'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
  68             'info_dict': {
  69                 'id': 'mdb-478135',
  70                 'ext': 'mp3',
  71                 'title': 'Flavia Coelho: Amar é Amar',
  72                 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
  73                 'upload_date': '20140717',
  74                 'is_live': False
  75             },
  76             'skip': 'Page Not Found',
  77         },
  78         {
  79             'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
  80             'playlist_mincount': 146,
  81             'info_dict': {
  82                 'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100',
  83             }
  84         },
  85         {
  86             'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html',
  87             'info_dict': {
  88                 'id': 'mdb-103364',
  89                 'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  90                 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
  91                 'ext': 'flv',
  92                 'upload_date': '20150101',
  93                 'is_live': True
  94             },
  95             'params': {
  96                 'skip_download': True,
  97             },
  98         }
  99     ]
 100
 101     def _real_extract(self, url):
 102         mobj = re.match(self._VALID_URL, url)
 103         page_url = mobj.group('url')
 104         page_id = mobj.group('id')
 105
 106         webpage = self._download_webpage(url, page_id)
 107
 108         if mobj.group('player') is None:
 109             entries = [
 110                 self.url_result(page_url + href, 'WDR')
 111                 for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
 112             ]
 113
 114             if entries:  # Playlist page
 115                 return self.playlist_result(entries, page_id)
 116
 117             # Overview page
 118             entries = []
 119             for page_num in itertools.count(2):
 120                 hrefs = re.findall(
 121                     r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
 122                     webpage)
 123                 entries.extend(
 124                     self.url_result(page_url + href, 'WDR')
 125                     for href in hrefs)
 126                 next_url_m = re.search(
 127                     r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
 128                 if not next_url_m:
 129                     break
 130                 next_url = page_url + next_url_m.group(1)
 131                 webpage = self._download_webpage(
 132                     next_url, page_id,
 133                     note='Downloading playlist page %d' % page_num)
 134             return self.playlist_result(entries, page_id)
 135
 136         flashvars = compat_parse_qs(
 137             self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
 138
 139         page_id = flashvars['trackerClipId'][0]
 140         video_url = flashvars['dslSrc'][0]
 141         title = flashvars['trackerClipTitle'][0]
 142         thumbnail = flashvars['startPicture'][0] if 'startPicture' in flashvars else None
 143         is_live = flashvars.get('isLive', ['0'])[0] == '1'
 144
 145         if is_live:
 146             title = self._live_title(title)
 147
 148         if 'trackerClipAirTime' in flashvars:
 149             upload_date = flashvars['trackerClipAirTime'][0]
 150         else:
 151             upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
 152
 153         if upload_date:
 154             upload_date = unified_strdate(upload_date)
 155
 156         formats = []
 157         preference = qualities(['S', 'M', 'L', 'XL'])
 158
 159         if video_url.endswith('.f4m'):
 160             formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', page_id, f4m_id='hds', fatal=False))
 161         elif video_url.endswith('.smil'):
 162             formats.extend(self._extract_smil_formats(video_url, page_id, False, {
 163                 'hdcore': '3.3.0',
 164                 'plugin': 'aasp-3.3.0.99.43',
 165             }))
 166         else:
 167             formats.append({
 168                 'url': video_url,
 169                 'http_headers': {
 170                     'User-Agent': 'mobile',
 171                 },
 172             })
 173
 174         m3u8_url = self._search_regex(r'rel="adaptiv"[^>]+href="([^"]+)"', webpage, 'm3u8 url', default=None)
 175         if m3u8_url:
 176             formats.extend(self._extract_m3u8_formats(m3u8_url, page_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
 177
 178         direct_urls = re.findall(r'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage)
 179         if direct_urls:
 180             for quality, video_url in direct_urls:
 181                 formats.append({
 182                     'url': video_url,
 183                     'preference': preference(quality),
 184                     'http_headers': {
 185                         'User-Agent': 'mobile',
 186                     },
 187                 })
 188
 189         self._sort_formats(formats)
 190
 191         description = self._html_search_meta('Description', webpage, 'description')
 192
 193         return {
 194             'id': page_id,
 195             'formats': formats,
 196             'title': title,
 197             'description': description,
 198             'thumbnail': thumbnail,
 199             'upload_date': upload_date,
 200             'is_live': is_live
 201         }
 202
 203
 204 class WDRMobileIE(InfoExtractor):
 205     _VALID_URL = r'''(?x)
 206         https?://mobile-ondemand\.wdr\.de/
 207         .*?/fsk(?P<age_limit>[0-9]+)
 208         /[0-9]+/[0-9]+/
 209         (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
 210     IE_NAME = 'wdr:mobile'
 211     _TEST = {
 212         'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
 213         'info_dict': {
 214             'title': '4283021',
 215             'id': '421735',
 216             'ext': 'mp4',
 217             'age_limit': 0,
 218         },
 219         'skip': 'Problems with loading data.'
 220     }
 221
 222     def _real_extract(self, url):
 223         mobj = re.match(self._VALID_URL, url)
 224         return {
 225             'id': mobj.group('id'),
 226             'title': mobj.group('title'),
 227             'age_limit': int(mobj.group('age_limit')),
 228             'url': url,
 229             'http_headers': {
 230                 'User-Agent': 'mobile',
 231             },
 232         }
 233
 234
 235 class WDRMausIE(InfoExtractor):
 236     _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
 237     IE_DESC = 'Sendung mit der Maus'
 238     _TESTS = [{
 239         'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
 240         'info_dict': {
 241             'id': 'aktuelle-sendung',
 242             'ext': 'mp4',
 243             'thumbnail': 're:^http://.+\.jpg',
 244             'upload_date': 're:^[0-9]{8}$',
 245             'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
 246         }
 247     }, {
 248         'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
 249         'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
 250         'info_dict': {
 251             'id': '40_jahre_maus',
 252             'ext': 'mp4',
 253             'thumbnail': 're:^http://.+\.jpg',
 254             'upload_date': '20131007',
 255             'title': '12.03.2011 - 40 Jahre Maus',
 256         }
 257     }]
 258
 259     def _real_extract(self, url):
 260         video_id = self._match_id(url)
 261
 262         webpage = self._download_webpage(url, video_id)
 263         param_code = self._html_search_regex(
 264             r'<a href="\?startVideo=1&amp;([^"]+)"', webpage, 'parameters')
 265
 266         title_date = self._search_regex(
 267             r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
 268             webpage, 'air date')
 269         title_str = self._html_search_regex(
 270             r'<h1>(.*?)</h1>', webpage, 'title')
 271         title = '%s - %s' % (title_date, title_str)
 272         upload_date = unified_strdate(
 273             self._html_search_meta('dc.date', webpage))
 274
 275         fields = compat_parse_qs(param_code)
 276         video_url = fields['firstVideo'][0]
 277         thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
 278
 279         formats = [{
 280             'format_id': 'rtmp',
 281             'url': video_url,
 282         }]
 283
 284         jscode = self._download_webpage(
 285             'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
 286             video_id, fatal=False,
 287             note='Downloading URL translation table',
 288             errnote='Could not download URL translation table')
 289         if jscode:
 290             for m in re.finditer(
 291                     r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
 292                     jscode):
 293                 if video_url.startswith(m.group('stream')):
 294                     http_url = video_url.replace(
 295                         m.group('stream'), m.group('dl'))
 296                     formats.append({
 297                         'format_id': 'http',
 298                         'url': http_url,
 299                     })
 300                     break
 301
 302         self._sort_formats(formats)
 303
 304         return {
 305             'id': video_id,
 306             'title': title,
 307             'formats': formats,
 308             'thumbnail': thumbnail,
 309             'upload_date': upload_date,
 310         }