X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/0865c28fb29a6481cd837cf8c1ef0cd134c6ef8e..4121346dfbb2b660ded98e98069857c7a50e381f:/youtube_dl/extractor/npo.py diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 9c01eb0..e525ad9 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -1,163 +1,461 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..compat import ( + compat_HTTPError, + compat_str, +) from ..utils import ( + determine_ext, + ExtractorError, fix_xml_ampersands, + int_or_none, + merge_dicts, + orderedSet, parse_duration, qualities, + str_or_none, strip_jsonp, unified_strdate, - url_basename, + unified_timestamp, + url_or_none, + urlencode_postdata, ) class NPOBaseIE(InfoExtractor): def _get_token(self, video_id): - token_page = self._download_webpage( - 'http://ida.omroep.nl/npoplayer/i.js', - video_id, note='Downloading token') - return self._search_regex( - r'npoplayer\.token = "(.+?)"', token_page, 'token') + return self._download_json( + 'http://ida.omroep.nl/app.php/auth', video_id, + note='Downloading token')['token'] class NPOIE(NPOBaseIE): - IE_NAME = 'npo.nl' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/(?!live|radio)[^/]+/[^/]+/(?P[^/?]+)' - - _TESTS = [ - { - 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719', - 'md5': '4b3f9c429157ec4775f2c9cb7b911016', - 'info_dict': { - 'id': 'VPWON_1220719', - 'ext': 'm4v', - 'title': 'Nieuwsuur', - 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', - 'upload_date': '20140622', - }, + IE_NAME = 'npo' + IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl' + _VALID_URL = r'''(?x) + (?: + npo:| + https?:// + (?:www\.)? + (?: + npo\.nl/(?:[^/]+/)*| + (?:ntr|npostart)\.nl/(?:[^/]+/){2,}| + omroepwnl\.nl/video/fragment/[^/]+__| + (?:zapp|npo3)\.nl/(?:[^/]+/){2,} + ) + ) + (?P[^/?#]+) + ''' + + _TESTS = [{ + 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719', + 'md5': '4b3f9c429157ec4775f2c9cb7b911016', + 'info_dict': { + 'id': 'VPWON_1220719', + 'ext': 'm4v', + 'title': 'Nieuwsuur', + 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', + 'upload_date': '20140622', }, - { - 'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800', - 'md5': 'da50a5787dbfc1603c4ad80f31c5120b', - 'info_dict': { - 'id': 'VARA_101191800', - 'ext': 'm4v', - 'title': 'De Mega Mike & Mega Thomas show', - 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4', - 'upload_date': '20090227', - 'duration': 2400, - }, + }, { + 'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800', + 'md5': 'da50a5787dbfc1603c4ad80f31c5120b', + 'info_dict': { + 'id': 'VARA_101191800', + 'ext': 'm4v', + 'title': 'De Mega Mike & Mega Thomas show: The best of.', + 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4', + 'upload_date': '20090227', + 'duration': 2400, }, - { - 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289', - 'md5': 'f8065e4e5a7824068ed3c7e783178f2c', - 'info_dict': { - 'id': 'VPWON_1169289', - 'ext': 'm4v', - 'title': 'Tegenlicht', - 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1', - 'upload_date': '20130225', - 'duration': 3000, - }, + }, { + 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289', + 'md5': 'f8065e4e5a7824068ed3c7e783178f2c', + 'info_dict': { + 'id': 'VPWON_1169289', + 'ext': 'm4v', + 'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika', + 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea', + 'upload_date': '20130225', + 'duration': 3000, }, - { - 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706', - 'info_dict': { - 'id': 'WO_VPRO_043706', - 'ext': 'wmv', - 'title': 'De nieuwe mens - Deel 1', - 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b', - 'duration': 4680, - }, - 'params': { - # mplayer mms download - 'skip_download': True, - } + }, { + 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706', + 'info_dict': { + 'id': 'WO_VPRO_043706', + 'ext': 'm4v', + 'title': 'De nieuwe mens - Deel 1', + 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b', + 'duration': 4680, }, + 'params': { + 'skip_download': True, + } + }, { # non asf in streams - { - 'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771', - 'md5': 'b3da13de374cbe2d5332a7e910bef97f', - 'info_dict': { - 'id': 'WO_NOS_762771', - 'ext': 'mp4', - 'title': 'Hoe gaat Europa verder na Parijs?', - }, + 'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771', + 'info_dict': { + 'id': 'WO_NOS_762771', + 'ext': 'mp4', + 'title': 'Hoe gaat Europa verder na Parijs?', }, - ] + 'params': { + 'skip_download': True, + } + }, { + 'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content', + 'info_dict': { + 'id': 'VPWON_1233944', + 'ext': 'm4v', + 'title': 'Aap, poot, pies', + 'description': 'md5:c9c8005d1869ae65b858e82c01a91fde', + 'upload_date': '20150508', + 'duration': 599, + }, + 'params': { + 'skip_download': True, + } + }, { + 'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698', + 'info_dict': { + 'id': 'POW_00996502', + 'ext': 'm4v', + 'title': '''"Dit is wel een 'landslide'..."''', + 'description': 'md5:f8d66d537dfb641380226e31ca57b8e8', + 'upload_date': '20150508', + 'duration': 462, + }, + 'params': { + 'skip_download': True, + } + }, { + # audio + 'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437', + 'info_dict': { + 'id': 'RBX_FUNX_6683215', + 'ext': 'mp3', + 'title': 'Jouw Stad Rotterdam', + 'description': 'md5:db251505244f097717ec59fabc372d9f', + }, + 'params': { + 'skip_download': True, + } + }, { + 'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547', + 'only_matching': True, + }, { + 'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118', + 'only_matching': True, + }, { + 'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990', + 'only_matching': True, + }, { + 'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870', + 'only_matching': True, + }, { + # live stream + 'url': 'npo:LI_NL1_4188102', + 'only_matching': True, + }, { + 'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373', + 'only_matching': True, + }, { + 'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927', + 'only_matching': True, + }, { + 'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996', + 'only_matching': True, + }, { + 'url': 'https://npo.nl/KN_1698996', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return (False if any(ie.suitable(url) + for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE)) + else super(NPOIE, cls).suitable(url)) def _real_extract(self, url): video_id = self._match_id(url) - return self._get_info(video_id) + return self._get_info(url, video_id) or self._get_old_info(video_id) + + def _get_info(self, url, video_id): + token = self._download_json( + 'https://www.npostart.nl/api/token', video_id, + 'Downloading token', headers={ + 'Referer': url, + 'X-Requested-With': 'XMLHttpRequest', + })['token'] + + player = self._download_json( + 'https://www.npostart.nl/player/%s' % video_id, video_id, + 'Downloading player JSON', data=urlencode_postdata({ + 'autoplay': 0, + 'share': 1, + 'pageUrl': url, + 'hasAdConsent': 0, + '_token': token, + })) + + player_token = player['token'] + + drm = False + format_urls = set() + formats = [] + for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'): + streams = self._download_json( + 'https://start-player.npo.nl/video/%s/streams' % video_id, + video_id, 'Downloading %s profile JSON' % profile, fatal=False, + query={ + 'profile': profile, + 'quality': 'npo', + 'tokenId': player_token, + 'streamType': 'broadcast', + }) + if not streams: + continue + stream = streams.get('stream') + if not isinstance(stream, dict): + continue + stream_url = url_or_none(stream.get('src')) + if not stream_url or stream_url in format_urls: + continue + format_urls.add(stream_url) + if stream.get('protection') is not None or stream.get('keySystemOptions') is not None: + drm = True + continue + stream_type = stream.get('type') + stream_ext = determine_ext(stream_url) + if stream_type == 'application/dash+xml' or stream_ext == 'mpd': + formats.extend(self._extract_mpd_formats( + stream_url, video_id, mpd_id='dash', fatal=False)) + elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + stream_url, video_id, ext='mp4', + entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) + elif re.search(r'\.isml?/Manifest', stream_url): + formats.extend(self._extract_ism_formats( + stream_url, video_id, ism_id='mss', fatal=False)) + else: + formats.append({ + 'url': stream_url, + }) + + if not formats: + if drm: + raise ExtractorError('This video is DRM protected.', expected=True) + return + + self._sort_formats(formats) - def _get_info(self, video_id): + info = { + 'id': video_id, + 'title': video_id, + 'formats': formats, + } + + embed_url = url_or_none(player.get('embedUrl')) + if embed_url: + webpage = self._download_webpage( + embed_url, video_id, 'Downloading embed page', fatal=False) + if webpage: + video = self._parse_json( + self._search_regex( + r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video', + default='{}'), video_id) + if video: + title = video.get('episodeTitle') + subtitles = {} + subtitles_list = video.get('subtitles') + if isinstance(subtitles_list, list): + for cc in subtitles_list: + cc_url = url_or_none(cc.get('src')) + if not cc_url: + continue + lang = str_or_none(cc.get('language')) or 'nl' + subtitles.setdefault(lang, []).append({ + 'url': cc_url, + }) + return merge_dicts({ + 'title': title, + 'description': video.get('description'), + 'thumbnail': url_or_none( + video.get('still_image_url') or video.get('orig_image_url')), + 'duration': int_or_none(video.get('duration')), + 'timestamp': unified_timestamp(video.get('broadcastDate')), + 'creator': video.get('channel'), + 'series': video.get('title'), + 'episode': title, + 'episode_number': int_or_none(video.get('episodeNumber')), + 'subtitles': subtitles, + }, info) + + return info + + def _get_old_info(self, video_id): metadata = self._download_json( - 'http://e.omroep.nl/metadata/aflevering/%s' % video_id, + 'http://e.omroep.nl/metadata/%s' % video_id, video_id, # We have to remove the javascript callback transform_source=strip_jsonp, ) + error = metadata.get('error') + if error: + raise ExtractorError(error, expected=True) + + # For some videos actual video id (prid) is different (e.g. for + # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698 + # video id is POMS_WNL_853698 but prid is POW_00996502) + video_id = metadata.get('prid') or video_id + + # titel is too generic in some cases so utilize aflevering_titel as well + # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html) + title = metadata['titel'] + sub_title = metadata.get('aflevering_titel') + if sub_title and sub_title != title: + title += ': %s' % sub_title + token = self._get_token(video_id) formats = [] + urls = set() + + def is_legal_url(format_url): + return format_url and format_url not in urls and re.match( + r'^(?:https?:)?//', format_url) + + QUALITY_LABELS = ('Laag', 'Normaal', 'Hoog') + QUALITY_FORMATS = ('adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std') + + quality_from_label = qualities(QUALITY_LABELS) + quality_from_format_id = qualities(QUALITY_FORMATS) + items = self._download_json( + 'http://ida.omroep.nl/app.php/%s' % video_id, video_id, + 'Downloading formats JSON', query={ + 'adaptive': 'yes', + 'token': token, + })['items'][0] + for num, item in enumerate(items): + item_url = item.get('url') + if not is_legal_url(item_url): + continue + urls.add(item_url) + format_id = self._search_regex( + r'video/ida/([^/]+)', item_url, 'format id', + default=None) + + item_label = item.get('label') + + def add_format_url(format_url): + width = int_or_none(self._search_regex( + r'(\d+)[xX]\d+', format_url, 'width', default=None)) + height = int_or_none(self._search_regex( + r'\d+[xX](\d+)', format_url, 'height', default=None)) + if item_label in QUALITY_LABELS: + quality = quality_from_label(item_label) + f_id = item_label + elif item_label in QUALITY_FORMATS: + quality = quality_from_format_id(format_id) + f_id = format_id + else: + quality, f_id = [None] * 2 + formats.append({ + 'url': format_url, + 'format_id': f_id, + 'width': width, + 'height': height, + 'quality': quality, + }) - pubopties = metadata.get('pubopties') - if pubopties: - quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std']) - for format_id in pubopties: - format_info = self._download_json( - 'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' - % (video_id, format_id, token), - video_id, 'Downloading %s JSON' % format_id) - if format_info.get('error_code', 0) or format_info.get('errorcode', 0): + # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706 + if item.get('contentType') in ('url', 'audio'): + add_format_url(item_url) + continue + + try: + stream_info = self._download_json( + item_url + '&type=json', video_id, + 'Downloading %s stream JSON' + % item_label or item.get('format') or format_id or num) + except ExtractorError as ee: + if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404: + error = (self._parse_json( + ee.cause.read().decode(), video_id, + fatal=False) or {}).get('errorstring') + if error: + raise ExtractorError(error, expected=True) + raise + # Stream URL instead of JSON, example: npo:LI_NL1_4188102 + if isinstance(stream_info, compat_str): + if not stream_info.startswith('http'): continue - streams = format_info.get('streams') - if streams: - video_info = self._download_json( - streams[0] + '&type=json', - video_id, 'Downloading %s stream JSON' % format_id) - else: - video_info = format_info - video_url = video_info.get('url') - if not video_url: + video_url = stream_info + # JSON + else: + video_url = stream_info.get('url') + if not video_url or 'vodnotavailable.' in video_url or video_url in urls: + continue + urls.add(video_url) + if determine_ext(video_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + video_url, video_id, ext='mp4', + entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) + else: + add_format_url(video_url) + + is_live = metadata.get('medium') == 'live' + + if not is_live: + for num, stream in enumerate(metadata.get('streams', [])): + stream_url = stream.get('url') + if not is_legal_url(stream_url): continue - if format_id == 'adaptive': - formats.extend(self._extract_m3u8_formats(video_url, video_id)) - else: + urls.add(stream_url) + # smooth streaming is not supported + stream_type = stream.get('type', '').lower() + if stream_type in ['ss', 'ms']: + continue + if stream_type == 'hds': + f4m_formats = self._extract_f4m_formats( + stream_url, video_id, fatal=False) + # f4m downloader downloads only piece of live stream + for f4m_format in f4m_formats: + f4m_format['preference'] = -1 + formats.extend(f4m_formats) + elif stream_type == 'hls': + formats.extend(self._extract_m3u8_formats( + stream_url, video_id, ext='mp4', fatal=False)) + # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706 + elif '.asf' in stream_url: + asx = self._download_xml( + stream_url, video_id, + 'Downloading stream %d ASX playlist' % num, + transform_source=fix_xml_ampersands, fatal=False) + if not asx: + continue + ref = asx.find('./ENTRY/Ref') + if ref is None: + continue + video_url = ref.get('href') + if not video_url or video_url in urls: + continue + urls.add(video_url) formats.append({ 'url': video_url, - 'format_id': format_id, - 'quality': quality(format_id), + 'ext': stream.get('formaat', 'asf'), + 'quality': stream.get('kwaliteit'), + 'preference': -10, }) - - streams = metadata.get('streams') - if streams: - for i, stream in enumerate(streams): - stream_url = stream.get('url') - if not stream_url: - continue - if '.asf' not in stream_url: + else: formats.append({ 'url': stream_url, 'quality': stream.get('kwaliteit'), }) - continue - asx = self._download_xml( - stream_url, video_id, - 'Downloading stream %d ASX playlist' % i, - transform_source=fix_xml_ampersands) - ref = asx.find('./ENTRY/Ref') - if ref is None: - continue - video_url = ref.get('href') - if not video_url: - continue - formats.append({ - 'url': video_url, - 'ext': stream.get('formaat', 'asf'), - 'quality': stream.get('kwaliteit'), - }) self._sort_formats(formats) @@ -165,101 +463,66 @@ class NPOIE(NPOBaseIE): if metadata.get('tt888') == 'ja': subtitles['nl'] = [{ 'ext': 'vtt', - 'url': 'http://e.omroep.nl/tt888/%s' % video_id, + 'url': 'http://tt888.omroep.nl/tt888/%s' % video_id, }] return { 'id': video_id, - 'title': metadata['titel'], - 'description': metadata['info'], + 'title': self._live_title(title) if is_live else title, + 'description': metadata.get('info'), 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'], 'upload_date': unified_strdate(metadata.get('gidsdatum')), 'duration': parse_duration(metadata.get('tijdsduur')), 'formats': formats, 'subtitles': subtitles, + 'is_live': is_live, } class NPOLiveIE(NPOBaseIE): IE_NAME = 'npo.nl:live' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P.+)' + _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P[^/?#&]+))?' - _TEST = { + _TESTS = [{ 'url': 'http://www.npo.nl/live/npo-1', 'info_dict': { - 'id': 'LI_NEDERLAND1_136692', + 'id': 'LI_NL1_4188102', 'display_id': 'npo-1', 'ext': 'mp4', - 'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'description': 'Livestream', + 'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'is_live': True, }, 'params': { 'skip_download': True, } - } + }, { + 'url': 'http://www.npo.nl/live', + 'only_matching': True, + }, { + 'url': 'https://www.npostart.nl/live/npo-1', + 'only_matching': True, + }] def _real_extract(self, url): - display_id = self._match_id(url) + display_id = self._match_id(url) or 'npo-1' webpage = self._download_webpage(url, display_id) live_id = self._search_regex( - r'data-prid="([^"]+)"', webpage, 'live id') - - metadata = self._download_json( - 'http://e.omroep.nl/metadata/%s' % live_id, - display_id, transform_source=strip_jsonp) - - token = self._get_token(display_id) - - formats = [] - - streams = metadata.get('streams') - if streams: - for stream in streams: - stream_type = stream.get('type').lower() - if stream_type == 'ss': - continue - stream_info = self._download_json( - 'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp' - % (stream.get('url'), token), - display_id, 'Downloading %s JSON' % stream_type) - if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0): - continue - stream_url = self._download_json( - stream_info['stream'], display_id, - 'Downloading %s URL' % stream_type, - transform_source=strip_jsonp) - if stream_type == 'hds': - f4m_formats = self._extract_f4m_formats(stream_url, display_id) - # f4m downloader downloads only piece of live stream - for f4m_format in f4m_formats: - f4m_format['preference'] = -1 - formats.extend(f4m_formats) - elif stream_type == 'hls': - formats.extend(self._extract_m3u8_formats(stream_url, display_id, 'mp4')) - else: - formats.append({ - 'url': stream_url, - }) - - self._sort_formats(formats) + [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id') return { + '_type': 'url_transparent', + 'url': 'npo:%s' % live_id, + 'ie_key': NPOIE.ie_key(), 'id': live_id, 'display_id': display_id, - 'title': self._live_title(metadata['titel']), - 'description': metadata['info'], - 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'], - 'formats': formats, - 'is_live': True, } class NPORadioIE(InfoExtractor): IE_NAME = 'npo.nl:radio' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P[^/]+)/?$' + _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P[^/]+)' _TEST = { 'url': 'http://www.npo.nl/radio/radio-1', @@ -274,6 +537,10 @@ class NPORadioIE(InfoExtractor): } } + @classmethod + def suitable(cls, url): + return False if NPORadioFragmentIE.suitable(url) else super(NPORadioIE, cls).suitable(url) + @staticmethod def _html_get_attribute_regex(attribute): return r'{0}\s*=\s*\'([^\']+)\''.format(attribute) @@ -335,9 +602,84 @@ class NPORadioFragmentIE(InfoExtractor): } -class TegenlichtVproIE(NPOIE): - IE_NAME = 'tegenlicht.vpro.nl' - _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?' +class NPODataMidEmbedIE(InfoExtractor): + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex( + r'data-mid=(["\'])(?P(?:(?!\1).)+)\1', webpage, 'video_id', group='id') + return { + '_type': 'url_transparent', + 'ie_key': 'NPO', + 'url': 'npo:%s' % video_id, + 'display_id': display_id + } + + +class SchoolTVIE(NPODataMidEmbedIE): + IE_NAME = 'schooltv' + _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P[^/?#&]+)' + + _TEST = { + 'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/', + 'info_dict': { + 'id': 'WO_NTR_429477', + 'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam', + 'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?', + 'ext': 'mp4', + 'description': 'md5:abfa0ff690adb73fd0297fd033aaa631' + }, + 'params': { + # Skip because of m3u8 download + 'skip_download': True + } + } + + +class HetKlokhuisIE(NPODataMidEmbedIE): + IE_NAME = 'hetklokhuis' + _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P[^/?#&]+)' + + _TEST = { + 'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven', + 'info_dict': { + 'id': 'VPWON_1260528', + 'display_id': 'Zwaartekrachtsgolven', + 'ext': 'm4v', + 'title': 'Het Klokhuis: Zwaartekrachtsgolven', + 'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48', + 'upload_date': '20170223', + }, + 'params': { + 'skip_download': True + } + } + + +class NPOPlaylistBaseIE(NPOIE): + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id) + for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage)) + ] + + playlist_title = self._html_search_regex( + self._PLAYLIST_TITLE_RE, webpage, 'playlist title', + default=None) or self._og_search_title(webpage) + + return self.playlist_result(entries, playlist_id, playlist_title) + + +class VPROIE(NPOPlaylistBaseIE): + IE_NAME = 'vpro' + _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P[^/]+)\.html' + _PLAYLIST_TITLE_RE = (r']+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)', + r']+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)') + _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"' _TESTS = [ { @@ -346,17 +688,80 @@ class TegenlichtVproIE(NPOIE): 'info_dict': { 'id': 'VPWON_1169289', 'ext': 'm4v', - 'title': 'Tegenlicht', - 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1', + 'title': 'De toekomst komt uit Afrika', + 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea', 'upload_date': '20130225', }, + 'skip': 'Video gone', }, + { + 'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html', + 'info_dict': { + 'id': 'sergio-herman', + 'title': 'sergio herman: fucking perfect', + }, + 'playlist_count': 2, + }, + { + # playlist with youtube embed + 'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html', + 'info_dict': { + 'id': 'education-education', + 'title': 'education education', + }, + 'playlist_count': 2, + }, + { + 'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html', + 'info_dict': { + 'id': 'de-tegenprestatie', + 'title': 'De Tegenprestatie', + }, + 'playlist_count': 2, + }, { + 'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html', + 'info_dict': { + 'id': 'VARA_101375237', + 'ext': 'm4v', + 'title': 'MH17: Het verdriet van Nederland', + 'description': 'md5:09e1a37c1fdb144621e22479691a9f18', + 'upload_date': '20150716', + }, + 'params': { + # Skip because of m3u8 download + 'skip_download': True + }, + } ] - def _real_extract(self, url): - name = url_basename(url) - webpage = self._download_webpage(url, name) - urn = self._html_search_meta('mediaurn', webpage) - info_page = self._download_json( - 'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name) - return self._get_info(info_page['mid']) + +class WNLIE(NPOPlaylistBaseIE): + IE_NAME = 'wnl' + _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P[^/]+)__\d+' + _PLAYLIST_TITLE_RE = r'(?s)]+class="subject"[^>]*>(.+?)' + _PLAYLIST_ENTRY_RE = r']+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+' + + _TESTS = [{ + 'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515', + 'info_dict': { + 'id': 'vandaag-de-dag-6-mei', + 'title': 'Vandaag de Dag 6 mei', + }, + 'playlist_count': 4, + }] + + +class AndereTijdenIE(NPOPlaylistBaseIE): + IE_NAME = 'anderetijden' + _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P[^/?#&]+)' + _PLAYLIST_TITLE_RE = r'(?s)]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)' + _PLAYLIST_ENTRY_RE = r']+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']' + + _TESTS = [{ + 'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem', + 'info_dict': { + 'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem', + 'title': 'Duitse soldaten over de Slag bij Arnhem', + }, + 'playlist_count': 3, + }]