logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

wdr.py (14311B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. import re
  6. from .common import InfoExtractor
  7. from ..compat import (
  8.     compat_str,
  9.     compat_urlparse,
  10. )
  11. from ..utils import (
  12.     determine_ext,
  13.     dict_get,
  14.     ExtractorError,
  15.     js_to_json,
  16.     strip_jsonp,
  17.     try_get,
  18.     unified_strdate,
  19.     update_url_query,
  20.     urlhandle_detect_ext,
  21.     url_or_none,
  22. )
  25. class WDRIE(InfoExtractor):
  26.     __API_URL_TPL = '//deviceids-medp.wdr.de/ondemand/%s/%s'
  27.     _VALID_URL = (r'(?:https?:' + __API_URL_TPL) % (r'\d+', r'(?=\d+\.js)|wdr:)(?P<id>\d{6,})')
  28.     _GEO_COUNTRIES = ['DE']
  29.     _TESTS = [{
  30.         'url': 'http://deviceids-medp.wdr.de/ondemand/155/1557833.js',
  31.         'info_dict': {
  32.             'id': 'mdb-1557833',
  33.             'ext': 'mp4',
  34.             'title': 'Biathlon-Staffel verpasst Podest bei Olympia-Generalprobe',
  35.             'upload_date': '20180112',
  36.         },
  37.     },
  38.     ]
  40.     def _asset_url(self, wdr_id):
  41.         id_len = max(len(wdr_id), 5)
  42.         return ''.join(('https:', self.__API_URL_TPL % (wdr_id[:id_len - 4], wdr_id, ), '.js'))
  44.     def _real_extract(self, url):
  45.         video_id = self._match_id(url)
  47.         if url.startswith('wdr:'):
  48.             video_id = url[4:]
  49.             url = self._asset_url(video_id)
  51.         metadata = self._download_json(
  52.             url, video_id, transform_source=strip_jsonp)
  54.         is_live = metadata.get('mediaType') == 'live'
  56.         tracker_data = metadata['trackerData']
  57.         title = tracker_data['trackerClipTitle']
  59.         media_resource = metadata['mediaResource']
  61.         formats = []
  63.         # check if the metadata contains a direct URL to a file
  64.         for kind, media in media_resource.items():
  65.             if not isinstance(media, dict):
  66.                 continue
  67.             if kind not in ('dflt', 'alt'):
  68.                 continue
  70.             for tag_name, medium_url in media.items():
  71.                 if tag_name not in ('videoURL', 'audioURL'):
  72.                     continue
  74.                 ext = determine_ext(medium_url)
  75.                 if ext == 'm3u8':
  76.                     formats.extend(self._extract_m3u8_formats(
  77.                         medium_url, video_id, 'mp4', 'm3u8_native',
  78.                         m3u8_id='hls'))
  79.                 elif ext == 'f4m':
  80.                     manifest_url = update_url_query(
  81.                         medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
  82.                     formats.extend(self._extract_f4m_formats(
  83.                         manifest_url, video_id, f4m_id='hds', fatal=False))
  84.                 elif ext == 'smil':
  85.                     formats.extend(self._extract_smil_formats(
  86.                         medium_url, 'stream', fatal=False))
  87.                 else:
  88.                     a_format = {
  89.                         'url': medium_url
  90.                     }
  91.                     if ext == 'unknown_video':
  92.                         urlh = self._request_webpage(
  93.                             medium_url, video_id, note='Determining extension')
  94.                         ext = urlhandle_detect_ext(urlh)
  95.                         a_format['ext'] = ext
  96.                     formats.append(a_format)
  98.         self._sort_formats(formats)
  100.         subtitles = {}
  101.         caption_url = media_resource.get('captionURL')
  102.         if caption_url:
  103.             subtitles['de'] = [{
  104.                 'url': caption_url,
  105.                 'ext': 'ttml',
  106.             }]
  107.         captions_hash = media_resource.get('captionsHash')
  108.         if isinstance(captions_hash, dict):
  109.             for ext, format_url in captions_hash.items():
  110.                 format_url = url_or_none(format_url)
  111.                 if not format_url:
  112.                     continue
  113.                 subtitles.setdefault('de', []).append({
  114.                     'url': format_url,
  115.                     'ext': determine_ext(format_url, None) or ext,
  116.                 })
  118.         return {
  119.             'id': tracker_data.get('trackerClipId', video_id),
  120.             'title': self._live_title(title) if is_live else title,
  121.             'alt_title': tracker_data.get('trackerClipSubcategory'),
  122.             'formats': formats,
  123.             'subtitles': subtitles,
  124.             'upload_date': unified_strdate(tracker_data.get('trackerClipAirTime')),
  125.             'is_live': is_live,
  126.         }
  129. class WDRPageIE(WDRIE):
  130.     _MAUS_REGEX = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/)*?(?P<maus_id>[^/?#.]+)(?:/?|/index\.php5|\.php5)$'
  131.     _PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html'
  132.     _VALID_URL = r'https?://(?:www\d?\.)?(?:(?:kinder\.)?wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _MAUS_REGEX
  134.     _TESTS = [
  135.         {
  136.             'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html',
  137.             # HDS download, MD5 is unstable
  138.             'info_dict': {
  139.                 'id': 'mdb-1058683',
  140.                 'ext': 'flv',
  141.                 'display_id': 'doku-am-freitag/video-geheimnis-aachener-dom-100',
  142.                 'title': 'Geheimnis Aachener Dom',
  143.                 'alt_title': 'Doku am Freitag',
  144.                 'upload_date': '20160304',
  145.                 'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318',
  146.                 'is_live': False,
  147.                 'subtitles': {'de': [{
  148.                     'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml',
  149.                     'ext': 'ttml',
  150.                 }]},
  151.             },
  152.             'skip': 'HTTP Error 404: Not Found',
  153.         },
  154.         {
  155.             'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html',
  156.             'md5': 'f4c1f96d01cf285240f53ea4309663d8',
  157.             'info_dict': {
  158.                 'id': 'mdb-1072000',
  159.                 'ext': 'mp3',
  160.                 'display_id': 'wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100',
  161.                 'title': 'Schriftstellerin Juli Zeh',
  162.                 'alt_title': 'WDR 3 Gespräch am Samstag',
  163.                 'upload_date': '20160312',
  164.                 'description': 'md5:e127d320bc2b1f149be697ce044a3dd7',
  165.                 'is_live': False,
  166.                 'subtitles': {}
  167.             },
  168.             'skip': 'HTTP Error 404: Not Found',
  169.         },
  170.         {
  171.             'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
  172.             'info_dict': {
  173.                 'id': 'mdb-2296252',
  174.                 'ext': 'mp4',
  175.                 'title': r're:^WDR Fernsehen im Livestream (?:\(nur in Deutschland erreichbar\) )?[0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  176.                 'alt_title': 'WDR Fernsehen Live',
  177.                 'upload_date': '20201112',
  178.                 'is_live': True,
  179.             },
  180.             'params': {
  181.                 'skip_download': True,  # m3u8 download
  182.             },
  183.         },
  184.         {
  185.             'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
  186.             'playlist_mincount': 6,
  187.             'info_dict': {
  188.                 'id': 'aktuelle-stunde-120',
  189.             },
  190.         },
  191.         {
  192.             'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
  193.             'info_dict': {
  194.                 'id': 'mdb-2627637',
  195.                 'ext': 'mp4',
  196.                 'upload_date': 're:^[0-9]{8}$',
  197.                 'title': 're:^Die Sendung (?:mit der Maus )?vom [0-9.]{10}$',
  198.             },
  199.             'skip': 'The id changes from week to week because of the new episode'
  200.         },
  201.         {
  202.             'url': 'http://www.wdrmaus.de/filme/sachgeschichten/achterbahn.php5',
  203.             'md5': '803138901f6368ee497b4d195bb164f2',
  204.             'info_dict': {
  205.                 'id': 'mdb-186083',
  206.                 'ext': 'mp4',
  207.                 'upload_date': '20130919',
  208.                 'title': 'Sachgeschichte - Achterbahn ',
  209.             },
  210.             'skip': 'HTTP Error 404: Not Found',
  211.         },
  212.         {
  213.             'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html',
  214.             # Live stream, MD5 unstable
  215.             'info_dict': {
  216.                 'id': 'mdb-869971',
  217.                 'ext': 'mp4',
  218.                 'title': r're:^COSMO Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  219.                 'upload_date': '20160101',
  220.             },
  221.             'params': {
  222.                 'skip_download': True,  # m3u8 download
  223.             }
  224.         },
  225.         {
  226.             'url': 'http://www.sportschau.de/handballem2018/handball-nationalmannschaft-em-stolperstein-vorrunde-100.html',
  227.             'info_dict': {
  228.                 'id': 'mdb-1556012',
  229.                 'ext': 'mp4',
  230.                 'title': 'DHB-Vizepräsident Bob Hanning - "Die Weltspitze ist extrem breit"',
  231.                 'upload_date': '20180111',
  232.             },
  233.             'params': {
  234.                 'skip_download': True,
  235.             },
  236.             'skip': 'HTTP Error 404: Not Found',
  237.         },
  238.         {
  239.             'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html',
  240.             'only_matching': True,
  241.         },
  242.         {
  243.             'url': 'https://kinder.wdr.de/tv/die-sendung-mit-dem-elefanten/av/video-folge---astronaut-100.html',
  244.             'only_matching': True,
  245.         },
  246.     ]
  248.     def _real_extract(self, url):
  249.         mobj = re.match(self._VALID_URL, url)
  250.         display_id = dict_get(mobj.groupdict(), ('display_id', 'maus_id'), 'wdrmaus')
  251.         webpage = self._download_webpage(url, display_id)
  253.         entries = []
  255.         # Article with several videos
  257.         # for wdr.de the data-extension is in a tag with the class "mediaLink"
  258.         # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
  259.         # for wdrmaus, in a tag with the class "videoButton" (previously a link
  260.         # to the page in a multiline "videoLink"-tag)
  261.         for mobj in re.finditer(
  262.             r'''(?sx)class=
  263.                     (?:
  264.                         (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+|
  265.                         (["\'])videoLink\b.*?\2[\s]*>\n[^\n]*
  266.                     )data-extension=(["\'])(?P<data>(?:(?!\3).)+)\3
  267.                     ''', webpage):
  268.             media_link_obj = self._parse_json(
  269.                 mobj.group('data'), display_id, transform_source=js_to_json,
  270.                 fatal=False)
  271.             if not media_link_obj:
  272.                 continue
  273.             jsonp_url = try_get(
  274.                 media_link_obj, lambda x: x['mediaObj']['url'], compat_str)
  275.             if jsonp_url:
  276.                 # metadata, or player JS with ['ref'] giving WDR id, or just media, perhaps
  277.                 clip_id = media_link_obj['mediaObj'].get('ref')
  278.                 if jsonp_url.endswith('.assetjsonp'):
  279.                     asset = self._download_json(
  280.                         jsonp_url, display_id, fatal=False, transform_source=strip_jsonp)
  281.                     clip_id = try_get(asset, lambda x: x['trackerData']['trackerClipId'], compat_str)
  282.                 if clip_id:
  283.                     jsonp_url = self._asset_url(clip_id[4:])
  284.                 entries.append(self.url_result(jsonp_url, ie=WDRIE.ie_key()))
  286.         # Playlist (e.g. https://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html)
  287.         if not entries:
  288.             entries = [
  289.                 self.url_result(
  290.                     compat_urlparse.urljoin(url, mobj.group('href')),
  291.                     ie=WDRPageIE.ie_key())
  292.                 for mobj in re.finditer(
  293.                     r'<a[^>]+\bhref=(["\'])(?P<href>(?:(?!\1).)+)\1[^>]+\bdata-extension=',
  294.                     webpage) if re.match(self._PAGE_REGEX, mobj.group('href'))
  295.             ]
  297.         return self.playlist_result(entries, playlist_id=display_id)
  300. class WDRElefantIE(InfoExtractor):
  301.     _VALID_URL = r'https?://(?:www\.)wdrmaus\.de/elefantenseite/#(?P<id>.+)'
  302.     _TEST = {
  303.         'url': 'http://www.wdrmaus.de/elefantenseite/#elefantenkino_wippe',
  304.         # adaptive stream: unstable file MD5
  305.         'info_dict': {
  306.             'title': 'Wippe',
  307.             'id': 'mdb-1198320',
  308.             'ext': 'mp4',
  309.             'age_limit': None,
  310.             'upload_date': '20071003'
  311.         },
  312.     }
  314.     def _real_extract(self, url):
  315.         display_id = self._match_id(url)
  317.         # Table of Contents seems to always be at this address, so fetch it directly.
  318.         # The website fetches configurationJS.php5, which links to tableOfContentsJS.php5.
  319.         table_of_contents = self._download_json(
  320.             'https://www.wdrmaus.de/elefantenseite/data/tableOfContentsJS.php5',
  321.             display_id)
  322.         if display_id not in table_of_contents:
  323.             raise ExtractorError(
  324.                 'No entry in site\'s table of contents for this URL. '
  325.                 'Is the fragment part of the URL (after the #) correct?',
  326.                 expected=True)
  327.         xml_metadata_path = table_of_contents[display_id]['xmlPath']
  328.         xml_metadata = self._download_xml(
  329.             'https://www.wdrmaus.de/elefantenseite/' + xml_metadata_path,
  330.             display_id)
  331.         zmdb_url_element = xml_metadata.find('./movie/zmdb_url')
  332.         if zmdb_url_element is None:
  333.             raise ExtractorError(
  334.                 '%s is not a video' % display_id, expected=True)
  335.         return self.url_result(zmdb_url_element.text, ie=WDRIE.ie_key())
  338. class WDRMobileIE(InfoExtractor):
  339.     _VALID_URL = r'''(?x)
  340.         https?://mobile-ondemand\.wdr\.de/
  341.         .*?/fsk(?P<age_limit>[0-9]+)
  342.         /[0-9]+/[0-9]+/
  343.         (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
  344.     IE_NAME = 'wdr:mobile'
  345.     _WORKING = False  # no such domain
  346.     _TEST = {
  347.         'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
  348.         'info_dict': {
  349.             'title': '4283021',
  350.             'id': '421735',
  351.             'ext': 'mp4',
  352.             'age_limit': 0,
  353.         },
  354.         'skip': 'Problems with loading data.'
  355.     }
  357.     def _real_extract(self, url):
  358.         mobj = re.match(self._VALID_URL, url)
  359.         return {
  360.             'id': mobj.group('id'),
  361.             'title': mobj.group('title'),
  362.             'age_limit': int(mobj.group('age_limit')),
  363.             'url': url,
  364.             'http_headers': {
  365.                 'User-Agent': 'mobile',
  366.             },
  367.         }