X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/453698570f26bebd37b39df8537d993b57d77b8b..7b54e7278c1ff62e888689ec470f488682311356:/youtube_dl/extractor/lnkgo.py diff --git a/youtube_dl/extractor/lnkgo.py b/youtube_dl/extractor/lnkgo.py index a8e3578..3e71852 100644 --- a/youtube_dl/extractor/lnkgo.py +++ b/youtube_dl/extractor/lnkgo.py @@ -5,25 +5,27 @@ import re from .common import InfoExtractor from ..utils import ( + clean_html, + compat_str, int_or_none, - js_to_json, - unified_strdate, + parse_iso8601, ) class LnkGoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?lnkgo\.alfa\.lt/visi\-video/(?P[^/]+)/ziurek\-(?P[A-Za-z0-9\-]+)' + _VALID_URL = r'https?://(?:www\.)?lnk(?:go)?\.(?:alfa\.)?lt/(?:visi-video/[^/]+|video)/(?P[A-Za-z0-9-]+)(?:/(?P\d+))?' _TESTS = [{ - 'url': 'http://lnkgo.alfa.lt/visi-video/yra-kaip-yra/ziurek-yra-kaip-yra-162', + 'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai', 'info_dict': { - 'id': '46712', + 'id': '10809', 'ext': 'mp4', - 'title': 'Yra kaip yra', - 'upload_date': '20150107', - 'description': 'md5:d82a5e36b775b7048617f263a0e3475e', - 'age_limit': 7, - 'duration': 3019, - 'thumbnail': 're:^https?://.*\.jpg$' + 'title': "Put'ka: Trys Klausimai", + 'upload_date': '20161216', + 'description': 'Seniai matytas Put’ka užduoda tris klausimėlius. Pabandykime surasti atsakymus.', + 'age_limit': 18, + 'duration': 117, + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1481904000, }, 'params': { 'skip_download': True, # HLS download @@ -31,94 +33,56 @@ class LnkGoIE(InfoExtractor): }, { 'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2', 'info_dict': { - 'id': '47289', + 'id': '10467', 'ext': 'mp4', 'title': 'Nėrdas: Kompiuterio Valymas', 'upload_date': '20150113', 'description': 'md5:7352d113a242a808676ff17e69db6a69', 'age_limit': 18, 'duration': 346, - 'thumbnail': 're:^https?://.*\.jpg$' + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1421164800, }, 'params': { 'skip_download': True, # HLS download }, + }, { + 'url': 'https://lnk.lt/video/neigalieji-tv-bokste/37413', + 'only_matching': True, }] _AGE_LIMITS = { 'N-7': 7, 'N-14': 14, 'S': 18, } + _M3U8_TEMPL = 'https://vod.lnk.lt/lnk_vod/lnk/lnk/%s:%s/playlist.m3u8%s' def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') - - webpage = self._download_webpage( - url, display_id, 'Downloading player webpage') - - video_id = self._search_regex( - r'data-ep="([^"]+)"', webpage, 'video ID') - title = self._og_search_title(webpage) - description = self._og_search_description(webpage) - - thumbnail_w = int_or_none( - self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False)) - thumbnail_h = int_or_none( - self._og_search_property('image:height', webpage, 'thumbnail height', fatal=False)) - thumbnail = { - 'url': self._og_search_thumbnail(webpage), - } - if thumbnail_w and thumbnail_h: - thumbnail.update({ - 'width': thumbnail_w, - 'height': thumbnail_h, - }) - - upload_date = unified_strdate(self._search_regex( - r'class="meta-item\sair-time">.*?([^<]+)', webpage, 'upload date', fatal=False)) - duration = int_or_none(self._search_regex( - r'VideoDuration = "([^"]+)"', webpage, 'duration', fatal=False)) - - pg_rating = self._search_regex( - r'pgrating="([^"]+)"', webpage, 'PG rating', fatal=False, default='') - age_limit = self._AGE_LIMITS.get(pg_rating.upper(), 0) + display_id, video_id = re.match(self._VALID_URL, url).groups() - sources_js = self._search_regex( - r'(?s)sources:\s(\[.*?\]),', webpage, 'sources') - sources = self._parse_json( - sources_js, video_id, transform_source=js_to_json) - - formats = [] - for source in sources: - if source.get('provider') == 'rtmp': - m = re.search(r'^(?Prtmp://[^/]+/(?P[^/]+))/(?P.+)$', source['file']) - if not m: - continue - formats.append({ - 'format_id': 'rtmp', - 'ext': 'flv', - 'url': m.group('url'), - 'play_path': m.group('play_path'), - 'page_url': url, - }) - elif source.get('file').endswith('.m3u8'): - formats.append({ - 'format_id': 'hls', - 'ext': source.get('type', 'mp4'), - 'url': source['file'], - }) + video_info = self._download_json( + 'https://lnk.lt/api/main/video-page/%s/%s/false' % (display_id, video_id or '0'), + display_id)['videoConfig']['videoInfo'] + video_id = compat_str(video_info['id']) + title = video_info['title'] + prefix = 'smil' if video_info.get('isQualityChangeAvailable') else 'mp4' + formats = self._extract_m3u8_formats( + self._M3U8_TEMPL % (prefix, video_info['videoUrl'], video_info.get('secureTokenParams') or ''), + video_id, 'mp4', 'm3u8_native') self._sort_formats(formats) + poster_image = video_info.get('posterImage') + return { 'id': video_id, 'display_id': display_id, 'title': title, 'formats': formats, - 'thumbnails': [thumbnail], - 'duration': duration, - 'description': description, - 'age_limit': age_limit, - 'upload_date': upload_date, + 'thumbnail': 'https://lnk.lt/all-images/' + poster_image if poster_image else None, + 'duration': int_or_none(video_info.get('duration')), + 'description': clean_html(video_info.get('htmlDescription')), + 'age_limit': self._AGE_LIMITS.get(video_info.get('pgRating'), 0), + 'timestamp': parse_iso8601(video_info.get('airDate')), + 'view_count': int_or_none(video_info.get('viewsCount')), }