logo

youtube-dl

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

ndr.py (18246B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. import re
  6. from .common import InfoExtractor
  7. from ..compat import compat_urllib_parse_urlparse
  8. from ..utils import (
  9.     determine_ext,
  10.     ExtractorError,
  11.     int_or_none,
  12.     merge_dicts,
  13.     parse_iso8601,
  14.     qualities,
  15.     try_get,
  16.     urljoin,
  17. )
  20. class NDRBaseIE(InfoExtractor):
  21.     def _real_extract(self, url):
  22.         mobj = re.match(self._VALID_URL, url)
  23.         display_id = next(group for group in mobj.groups() if group)
  24.         webpage = self._download_webpage(url, display_id)
  25.         return self._extract_embed(webpage, display_id, url)
  28. class NDRIE(NDRBaseIE):
  29.     IE_NAME = 'ndr'
  30.     IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
  31.     _VALID_URL = r'https?://(?:\w+\.)*ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
  32.     _TESTS = [{
  33.         # httpVideo, same content id
  34.         'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
  35.         'md5': '6515bc255dc5c5f8c85bbc38e035a659',
  36.         'info_dict': {
  37.             'id': 'hafengeburtstag988',
  38.             'display_id': 'Party-Poette-und-Parade',
  39.             'ext': 'mp4',
  40.             'title': 'Party, Pötte und Parade',
  41.             'description': 'md5:ad14f9d2f91d3040b6930c697e5f6b4c',
  42.             'uploader': 'ndrtv',
  43.             'timestamp': 1431255671,
  44.             'upload_date': '20150510',
  45.             'duration': 3498,
  46.         },
  47.         'params': {
  48.             'skip_download': True,
  49.         },
  50.         'expected_warnings': ['Unable to download f4m manifest'],
  51.     }, {
  52.         # httpVideo, different content id
  53.         'url': 'http://www.ndr.de/sport/fussball/40-Osnabrueck-spielt-sich-in-einen-Rausch,osna270.html',
  54.         'md5': '1043ff203eab307f0c51702ec49e9a71',
  55.         'info_dict': {
  56.             'id': 'osna272',
  57.             'display_id': '40-Osnabrueck-spielt-sich-in-einen-Rausch',
  58.             'ext': 'mp4',
  59.             'title': 'Osnabrück - Wehen Wiesbaden: Die Highlights',
  60.             'description': 'md5:32e9b800b3d2d4008103752682d5dc01',
  61.             'uploader': 'ndrtv',
  62.             'timestamp': 1442059200,
  63.             'upload_date': '20150912',
  64.             'duration': 510,
  65.         },
  66.         'params': {
  67.             'skip_download': True,
  68.         },
  69.         'skip': 'No longer available',
  70.     }, {
  71.         # httpAudio, same content id
  72.         'url': 'http://www.ndr.de/info/La-Valette-entgeht-der-Hinrichtung,audio51535.html',
  73.         'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
  74.         'info_dict': {
  75.             'id': 'audio51535',
  76.             'display_id': 'La-Valette-entgeht-der-Hinrichtung',
  77.             'ext': 'mp3',
  78.             'title': 'La Valette entgeht der Hinrichtung',
  79.             'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
  80.             'uploader': 'ndrinfo',
  81.             'timestamp': 1631711863,
  82.             'upload_date': '20210915',
  83.             'duration': 884,
  84.         },
  85.         'params': {
  86.             'skip_download': True,
  87.         },
  88.     }, {
  89.         # with subtitles
  90.         'url': 'https://www.ndr.de/fernsehen/sendungen/extra_3/extra-3-Satiremagazin-mit-Christian-Ehring,sendung1091858.html',
  91.         'info_dict': {
  92.             'id': 'extra18674',
  93.             'display_id': 'extra-3-Satiremagazin-mit-Christian-Ehring',
  94.             'ext': 'mp4',
  95.             'title': 'Extra 3 vom 11.11.2020 mit Christian Ehring',
  96.             'description': 'md5:700f6de264010585012a72f97b0ac0c9',
  97.             'uploader': 'ndrtv',
  98.             'upload_date': '20201207',
  99.             'timestamp': 1614349457,
  100.             'duration': 1749,
  101.             'subtitles': {
  102.                 'de': [{
  103.                     'ext': 'ttml',
  104.                     'url': r're:^https://www\.ndr\.de.+',
  105.                 }],
  106.             },
  107.         },
  108.         'params': {
  109.             'skip_download': True,
  110.         },
  111.         'expected_warnings': ['Unable to download f4m manifest'],
  112.     }, {
  113.         'url': 'https://www.ndr.de/Fettes-Brot-Ferris-MC-und-Thees-Uhlmann-live-on-stage,festivalsommer116.html',
  114.         'only_matching': True,
  115.     }]
  117.     def _extract_embed(self, webpage, display_id, url):
  118.         embed_url = (
  119.             self._html_search_meta(
  120.                 'embedURL', webpage, 'embed URL',
  121.                 default=None)
  122.             or self._search_regex(
  123.                 r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
  124.                 'embed URL', group='url', default=None)
  125.             or self._search_regex(
  126.                 r'\bvar\s*sophoraID\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
  127.                 'embed URL', group='url', default=''))
  128.         # some more work needed if we only found sophoraID
  129.         if re.match(r'^[a-z]+\d+$', embed_url):
  130.             # get the initial part of the url path,. eg /panorama/archiv/2022/
  131.             parsed_url = compat_urllib_parse_urlparse(url)
  132.             path = self._search_regex(r'(.+/)%s' % display_id, parsed_url.path or '', 'embed URL', default='')
  133.             # find tell-tale image with the actual ID
  134.             ndr_id = self._search_regex(r'%s([a-z]+\d+)(?!\.)\b' % (path, ), webpage, 'embed URL', default=None)
  135.             # or try to use special knowledge!
  136.             NDR_INFO_URL_TPL = 'https://www.ndr.de/info/%s-player.html'
  137.             embed_url = 'ndr:%s' % (ndr_id, ) if ndr_id else NDR_INFO_URL_TPL % (embed_url, )
  138.         if not embed_url:
  139.             raise ExtractorError('Unable to extract embedUrl')
  141.         description = self._search_regex(
  142.             r'<p[^>]+itemprop="description">([^<]+)</p>',
  143.             webpage, 'description', default=None) or self._og_search_description(webpage)
  144.         timestamp = parse_iso8601(
  145.             self._search_regex(
  146.                 (r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="(?P<cont>[^"]+)"',
  147.                  r'\bvar\s*pdt\s*=\s*(?P<q>["\'])(?P<cont>(?:(?!(?P=q)).)+)(?P=q)', ),
  148.                 webpage, 'upload date', group='cont', default=None))
  149.         info = self._search_json_ld(webpage, display_id, default={})
  150.         return merge_dicts({
  151.             '_type': 'url_transparent',
  152.             'url': embed_url,
  153.             'display_id': display_id,
  154.             'description': description,
  155.             'timestamp': timestamp,
  156.         }, info)
  159. class NJoyIE(NDRBaseIE):
  160.     IE_NAME = 'njoy'
  161.     IE_DESC = 'N-JOY'
  162.     _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
  163.     _TESTS = [{
  164.         # httpVideo, same content id
  165.         'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
  166.         'md5': 'cb63be60cd6f9dd75218803146d8dc67',
  167.         'info_dict': {
  168.             'id': 'comedycontest2480',
  169.             'display_id': 'Benaissa-beim-NDR-Comedy-Contest',
  170.             'ext': 'mp4',
  171.             'title': 'Benaissa beim NDR Comedy Contest',
  172.             'description': 'md5:f057a6c4e1c728b10d33b5ffd36ddc39',
  173.             'uploader': 'ndrtv',
  174.             'upload_date': '20141129',
  175.             'duration': 654,
  176.         },
  177.         'params': {
  178.             'skip_download': True,
  179.         },
  180.         'skip': 'No longer available',
  181.     }, {
  182.         # httpVideo, different content id
  183.         'url': 'http://www.n-joy.de/musik/Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-,felixjaehn168.html',
  184.         'md5': '417660fffa90e6df2fda19f1b40a64d8',
  185.         'info_dict': {
  186.             'id': 'livestream283',
  187.             'display_id': 'Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-',
  188.             'ext': 'mp3',
  189.             'title': 'Das frueheste DJ Set des Nordens live mit Felix Jaehn',
  190.             'description': 'md5:681698f527b8601e511e7b79edde7d2c',
  191.             'uploader': 'njoy',
  192.             'upload_date': '20210830',
  193.         },
  194.         'params': {
  195.             'skip_download': True,
  196.         },
  197.     }, {
  198.         'url': 'http://www.n-joy.de/radio/webradio/morningshow209.html',
  199.         'only_matching': True,
  200.     }]
  202.     def _extract_embed(self, webpage, display_id, url=None):
  203.         # find tell-tale URL with the actual ID, or ...
  204.         video_id = self._search_regex(
  205.             (r'''\bsrc\s*=\s*["']?(?:/\w+)+/([a-z]+\d+)(?!\.)\b''',
  206.              r'<iframe[^>]+id="pp_([\da-z]+)"', ),
  207.             webpage, 'NDR id', default=None)
  209.         description = (
  210.             self._html_search_meta('description', webpage)
  211.             or self._search_regex(
  212.                 r'<div[^>]+class="subline"[^>]*>[^<]+</div>\s*<p>([^<]+)</p>',
  213.                 webpage, 'description', fatal=False))
  214.         return {
  215.             '_type': 'url_transparent',
  216.             'ie_key': 'NDREmbedBase',
  217.             'url': 'ndr:%s' % video_id,
  218.             'display_id': display_id,
  219.             'description': description,
  220.             'title': display_id.replace('-', ' ').strip(),
  221.         }
  224. class NDREmbedBaseIE(InfoExtractor):
  225.     IE_NAME = 'ndr:embed:base'
  226.     _VALID_URL = r'(?:ndr:(?P<id_s>[\da-z]+)|https?://www\.ndr\.de/(?P<id>[\da-z]+)-ppjson\.json)'
  227.     _TESTS = [{
  228.         'url': 'ndr:soundcheck3366',
  229.         'only_matching': True,
  230.     }, {
  231.         'url': 'http://www.ndr.de/soundcheck3366-ppjson.json',
  232.         'only_matching': True,
  233.     }]
  235.     def _real_extract(self, url):
  236.         mobj = re.match(self._VALID_URL, url)
  237.         video_id = mobj.group('id') or mobj.group('id_s')
  239.         ppjson = self._download_json(
  240.             'http://www.ndr.de/%s-ppjson.json' % video_id, video_id)
  242.         playlist = ppjson['playlist']
  244.         formats = []
  245.         quality_key = qualities(('xs', 's', 'm', 'l', 'xl'))
  247.         for format_id, f in playlist.items():
  248.             src = f.get('src')
  249.             if not src:
  250.                 continue
  251.             ext = determine_ext(src, None)
  252.             if ext == 'f4m':
  253.                 formats.extend(self._extract_f4m_formats(
  254.                     src + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id,
  255.                     f4m_id='hds', fatal=False))
  256.             elif ext == 'm3u8':
  257.                 formats.extend(self._extract_m3u8_formats(
  258.                     src, video_id, 'mp4', m3u8_id='hls',
  259.                     entry_protocol='m3u8_native', fatal=False))
  260.             else:
  261.                 quality = f.get('quality')
  262.                 ff = {
  263.                     'url': src,
  264.                     'format_id': quality or format_id,
  265.                     'quality': quality_key(quality),
  266.                 }
  267.                 type_ = f.get('type')
  268.                 if type_ and type_.split('/')[0] == 'audio':
  269.                     ff['vcodec'] = 'none'
  270.                     ff['ext'] = ext or 'mp3'
  271.                 formats.append(ff)
  272.         self._sort_formats(formats)
  274.         config = playlist['config']
  276.         live = playlist.get('config', {}).get('streamType') in ['httpVideoLive', 'httpAudioLive']
  277.         title = config['title']
  278.         if live:
  279.             title = self._live_title(title)
  280.         uploader = ppjson.get('config', {}).get('branding')
  281.         upload_date = ppjson.get('config', {}).get('publicationDate')
  282.         duration = int_or_none(config.get('duration'))
  284.         thumbnails = []
  285.         poster = try_get(config, lambda x: x['poster'], dict) or {}
  286.         for thumbnail_id, thumbnail in poster.items():
  287.             thumbnail_url = urljoin(url, thumbnail.get('src'))
  288.             if not thumbnail_url:
  289.                 continue
  290.             thumbnails.append({
  291.                 'id': thumbnail.get('quality') or thumbnail_id,
  292.                 'url': thumbnail_url,
  293.                 'preference': quality_key(thumbnail.get('quality')),
  294.             })
  296.         subtitles = {}
  297.         tracks = config.get('tracks')
  298.         if tracks and isinstance(tracks, list):
  299.             for track in tracks:
  300.                 if not isinstance(track, dict):
  301.                     continue
  302.                 track_url = urljoin(url, track.get('src'))
  303.                 if not track_url:
  304.                     continue
  305.                 subtitles.setdefault(track.get('srclang') or 'de', []).append({
  306.                     'url': track_url,
  307.                     'ext': 'ttml',
  308.                 })
  310.         return {
  311.             'id': video_id,
  312.             'title': title,
  313.             'is_live': live,
  314.             'uploader': uploader if uploader != '-' else None,
  315.             'upload_date': upload_date[0:8] if upload_date else None,
  316.             'duration': duration,
  317.             'thumbnails': thumbnails,
  318.             'formats': formats,
  319.             'subtitles': subtitles,
  320.         }
  323. class NDREmbedIE(NDREmbedBaseIE):
  324.     IE_NAME = 'ndr:embed'
  325.     _VALID_URL = r'https?://(?:\w+\.)*ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:(?:ard)?player|externalPlayer)\.html'
  326.     _TESTS = [{
  327.         'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
  328.         'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
  329.         'info_dict': {
  330.             'id': 'ndraktuell28488',
  331.             'ext': 'mp4',
  332.             'title': 'Norddeutschland begrüßt Flüchtlinge',
  333.             'is_live': False,
  334.             'uploader': 'ndrtv',
  335.             'upload_date': '20150907',
  336.             'duration': 132,
  337.         },
  338.         'skip': 'No longer available',
  339.     }, {
  340.         'url': 'http://www.ndr.de/ndr2/events/soundcheck/soundcheck3366-player.html',
  341.         'md5': '002085c44bae38802d94ae5802a36e78',
  342.         'info_dict': {
  343.             'id': 'soundcheck3366',
  344.             'ext': 'mp4',
  345.             'title': 'Ella Henderson braucht Vergleiche nicht zu scheuen',
  346.             'is_live': False,
  347.             'uploader': 'ndr2',
  348.             'upload_date': '20150912',
  349.             'duration': 3554,
  350.         },
  351.         'params': {
  352.             'skip_download': True,
  353.         },
  354.         'skip': 'No longer available',
  355.     }, {
  356.         'url': 'http://www.ndr.de/info/audio51535-player.html',
  357.         'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
  358.         'info_dict': {
  359.             'id': 'audio51535',
  360.             'ext': 'mp3',
  361.             'title': 'La Valette entgeht der Hinrichtung',
  362.             'is_live': False,
  363.             'uploader': 'ndrinfo',
  364.             'upload_date': '20210915',
  365.             'duration': 884,
  366.         },
  367.         'params': {
  368.             'skip_download': True,
  369.         },
  370.     }, {
  371.         'url': 'http://www.ndr.de/fernsehen/sendungen/visite/visite11010-externalPlayer.html',
  372.         'md5': 'ae57f80511c1e1f2fd0d0d3d31aeae7c',
  373.         'info_dict': {
  374.             'id': 'visite11010',
  375.             'ext': 'mp4',
  376.             'title': 'Visite - die ganze Sendung',
  377.             'is_live': False,
  378.             'uploader': 'ndrtv',
  379.             'upload_date': '20150902',
  380.             'duration': 3525,
  381.         },
  382.         'params': {
  383.             'skip_download': True,
  384.         },
  385.         'skip': 'No longer available',
  386.     }, {
  387.         # httpVideoLive
  388.         'url': 'http://www.ndr.de/fernsehen/livestream/livestream217-externalPlayer.html',
  389.         'info_dict': {
  390.             'id': 'livestream217',
  391.             'ext': 'mp4',
  392.             'title': r're:^NDR Fernsehen Niedersachsen \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
  393.             'is_live': True,
  394.             'upload_date': '20210409',
  395.             'uploader': 'ndrtv',
  396.         },
  397.         'params': {
  398.             'skip_download': True,
  399.         },
  400.     }, {
  401.         'url': 'http://www.ndr.de/ndrkultur/audio255020-player.html',
  402.         'only_matching': True,
  403.     }, {
  404.         'url': 'http://www.ndr.de/fernsehen/sendungen/nordtour/nordtour7124-player.html',
  405.         'only_matching': True,
  406.     }, {
  407.         'url': 'http://www.ndr.de/kultur/film/videos/videoimport10424-player.html',
  408.         'only_matching': True,
  409.     }, {
  410.         'url': 'http://www.ndr.de/fernsehen/sendungen/hamburg_journal/hamj43006-player.html',
  411.         'only_matching': True,
  412.     }, {
  413.         'url': 'http://www.ndr.de/fernsehen/sendungen/weltbilder/weltbilder4518-player.html',
  414.         'only_matching': True,
  415.     }, {
  416.         'url': 'http://www.ndr.de/fernsehen/doku952-player.html',
  417.         'only_matching': True,
  418.     }]
  421. class NJoyEmbedIE(NDREmbedBaseIE):
  422.     IE_NAME = 'njoy:embed'
  423.     _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
  424.     _TESTS = [{
  425.         # httpVideo
  426.         'url': 'http://www.n-joy.de/events/reeperbahnfestival/doku948-player_image-bc168e87-5263-4d6d-bd27-bb643005a6de_theme-n-joy.html',
  427.         'md5': '8483cbfe2320bd4d28a349d62d88bd74',
  428.         'info_dict': {
  429.             'id': 'doku948',
  430.             'ext': 'mp4',
  431.             'title': 'Zehn Jahre Reeperbahn Festival - die Doku',
  432.             'is_live': False,
  433.             'upload_date': '20200826',
  434.             'duration': 1011,
  435.         },
  436.         'expected_warnings': ['Unable to download f4m manifest'],
  437.     }, {
  438.         # httpAudio
  439.         'url': 'http://www.n-joy.de/news_wissen/stefanrichter100-player_image-d5e938b1-f21a-4b9a-86b8-aaba8bca3a13_theme-n-joy.html',
  440.         'md5': 'd989f80f28ac954430f7b8a48197188a',
  441.         'info_dict': {
  442.             'id': 'stefanrichter100',
  443.             'ext': 'mp3',
  444.             'title': 'Interview mit einem Augenzeugen',
  445.             'is_live': False,
  446.             'uploader': 'njoy',
  447.             'upload_date': '20150909',
  448.             'duration': 140,
  449.         },
  450.         'params': {
  451.             'skip_download': True,
  452.         },
  453.         'skip': 'No longer available',
  454.     }, {
  455.         # httpAudioLive, no explicit ext
  456.         'url': 'http://www.n-joy.de/news_wissen/webradioweltweit100-player_image-3fec0484-2244-4565-8fb8-ed25fd28b173_theme-n-joy.html',
  457.         'info_dict': {
  458.             'id': 'webradioweltweit100',
  459.             'ext': 'mp3',
  460.             'title': r're:^N-JOY Weltweit \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
  461.             'is_live': True,
  462.             'uploader': 'njoy',
  463.             'upload_date': '20210830',
  464.         },
  465.         'params': {
  466.             'skip_download': True,
  467.         },
  468.     }, {
  469.         'url': 'http://www.n-joy.de/musik/dockville882-player_image-3905259e-0803-4764-ac72-8b7de077d80a_theme-n-joy.html',
  470.         'only_matching': True,
  471.     }, {
  472.         'url': 'http://www.n-joy.de/radio/sendungen/morningshow/urlaubsfotos190-player_image-066a5df1-5c95-49ec-a323-941d848718db_theme-n-joy.html',
  473.         'only_matching': True,
  474.     }, {
  475.         'url': 'http://www.n-joy.de/entertainment/comedy/krudetv290-player_image-ab261bfe-51bf-4bf3-87ba-c5122ee35b3d_theme-n-joy.html',
  476.         'only_matching': True,
  477.     }]