X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/b8d8e13c1f9e4d3cdd7d41c5c9d711a36dd5f9c3..a5a28b1eabe0533f26d23c4157c97144215b22b7:/youtube_dl/extractor/dplay.py diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index 32028bc..b734467 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -6,42 +6,34 @@ import re import time from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import ( + compat_HTTPError, + compat_str, + compat_urlparse, +) from ..utils import ( - USER_AGENTS, + determine_ext, + ExtractorError, + float_or_none, int_or_none, + remove_end, + try_get, + unified_strdate, + unified_timestamp, update_url_query, + USER_AGENTS, ) class DPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?Pit\.dplay\.com|www\.dplay\.(?:dk|se|no))/[^/]+/(?P[^/?#]+)' + _VALID_URL = r'https?://(?Pwww\.(?Pdplay\.(?Pdk|se|no)))/(?:video(?:er|s)/)?(?P[^/]+/[^/?#]+)' _TESTS = [{ - # geo restricted, via direct unsigned hls URL - 'url': 'http://it.dplay.com/take-me-out/stagione-1-episodio-25/', - 'info_dict': { - 'id': '1255600', - 'display_id': 'stagione-1-episodio-25', - 'ext': 'mp4', - 'title': 'Episodio 25', - 'description': 'md5:cae5f40ad988811b197d2d27a53227eb', - 'duration': 2761, - 'timestamp': 1454701800, - 'upload_date': '20160205', - 'creator': 'RTIT', - 'series': 'Take me out', - 'season_number': 1, - 'episode_number': 25, - 'age_limit': 0, - }, - 'expected_warnings': ['Unable to download f4m manifest'], - }, { # non geo restricted, via secure api, unsigned download hls URL 'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/', 'info_dict': { 'id': '3172', - 'display_id': 'season-1-svensken-lar-sig-njuta-av-livet', + 'display_id': 'nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet', 'ext': 'mp4', 'title': 'Svensken lär sig njuta av livet', 'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8', @@ -59,7 +51,7 @@ class DPlayIE(InfoExtractor): 'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/', 'info_dict': { 'id': '70816', - 'display_id': 'season-6-episode-12', + 'display_id': 'mig-og-min-mor/season-6-episode-12', 'ext': 'mp4', 'title': 'Episode 12', 'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90', @@ -76,6 +68,33 @@ class DPlayIE(InfoExtractor): # geo restricted, via direct unsigned hls URL 'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/', 'only_matching': True, + }, { + # disco-api + 'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7', + 'info_dict': { + 'id': '40206', + 'display_id': 'i-kongens-klr/sesong-1-episode-7', + 'ext': 'mp4', + 'title': 'Episode 7', + 'description': 'md5:e3e1411b2b9aebeea36a6ec5d50c60cf', + 'duration': 2611.16, + 'timestamp': 1516726800, + 'upload_date': '20180123', + 'series': 'I kongens klær', + 'season_number': 1, + 'episode_number': 7, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + }, + }, { + + 'url': 'https://www.dplay.dk/videoer/singleliv/season-5-episode-3', + 'only_matching': True, + }, { + 'url': 'https://www.dplay.se/videos/sofias-anglar/sofias-anglar-1001', + 'only_matching': True, }] def _real_extract(self, url): @@ -83,10 +102,81 @@ class DPlayIE(InfoExtractor): display_id = mobj.group('id') domain = mobj.group('domain') + self._initialize_geo_bypass([mobj.group('country').upper()]) + webpage = self._download_webpage(url, display_id) video_id = self._search_regex( - r'data-video-id=["\'](\d+)', webpage, 'video id') + r'data-video-id=["\'](\d+)', webpage, 'video id', default=None) + + if not video_id: + host = mobj.group('host') + disco_base = 'https://disco-api.%s' % host + self._download_json( + '%s/token' % disco_base, display_id, 'Downloading token', + query={ + 'realm': host.replace('.', ''), + }) + video = self._download_json( + '%s/content/videos/%s' % (disco_base, display_id), display_id, + headers={ + 'Referer': url, + 'x-disco-client': 'WEB:UNKNOWN:dplay-client:0.0.1', + }, query={ + 'include': 'show' + }) + video_id = video['data']['id'] + info = video['data']['attributes'] + title = info['name'] + formats = [] + for format_id, format_dict in self._download_json( + '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id), + display_id)['data']['attributes']['streaming'].items(): + if not isinstance(format_dict, dict): + continue + format_url = format_dict.get('url') + if not format_url: + continue + ext = determine_ext(format_url) + if format_id == 'dash' or ext == 'mpd': + formats.extend(self._extract_mpd_formats( + format_url, display_id, mpd_id='dash', fatal=False)) + elif format_id == 'hls' or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, display_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id, + }) + self._sort_formats(formats) + + series = None + try: + included = video.get('included') + if isinstance(included, list): + show = next(e for e in included if e.get('type') == 'show') + series = try_get( + show, lambda x: x['attributes']['name'], compat_str) + except StopIteration: + pass + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': info.get('description'), + 'duration': float_or_none( + info.get('videoDuration'), scale=1000), + 'timestamp': unified_timestamp(info.get('publishStart')), + 'series': series, + 'season_number': int_or_none(info.get('seasonNumber')), + 'episode_number': int_or_none(info.get('episodeNumber')), + 'age_limit': int_or_none(info.get('minimum_age')), + 'formats': formats, + } info = self._download_json( 'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id), @@ -168,3 +258,106 @@ class DPlayIE(InfoExtractor): 'formats': formats, 'subtitles': subtitles, } + + +class DPlayItIE(InfoExtractor): + _VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P[^/?#]+)' + _GEO_COUNTRIES = ['IT'] + _TEST = { + 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/', + 'md5': '2b808ffb00fc47b884a172ca5d13053c', + 'info_dict': { + 'id': '6918', + 'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij', + 'ext': 'mp4', + 'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij', + 'description': 'md5:3c7a4303aef85868f867a26f5cc14813', + 'thumbnail': r're:^https?://.*\.jpe?g', + 'upload_date': '20160524', + 'series': 'Biografie imbarazzanti', + 'season_number': 1, + 'episode': 'Luigi Di Maio: la psicosi di Stanislawskij', + 'episode_number': 1, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + title = remove_end(self._og_search_title(webpage), ' | Dplay') + + video_id = None + + info = self._search_regex( + r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")', + webpage, 'playback JSON', default=None) + if info: + for _ in range(2): + info = self._parse_json(info, display_id, fatal=False) + if not info: + break + else: + video_id = try_get(info, lambda x: x['data']['id']) + + if not info: + info_url = self._search_regex( + r'url\s*[:=]\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)', + webpage, 'info url') + + video_id = info_url.rpartition('/')[-1] + + try: + info = self._download_json( + info_url, display_id, headers={ + 'Authorization': 'Bearer %s' % self._get_cookies(url).get( + 'dplayit_token').value, + 'Referer': url, + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403): + info = self._parse_json(e.cause.read().decode('utf-8'), display_id) + error = info['errors'][0] + if error.get('code') == 'access.denied.geoblocked': + self.raise_geo_restricted( + msg=error.get('detail'), countries=self._GEO_COUNTRIES) + raise ExtractorError(info['errors'][0]['detail'], expected=True) + raise + + hls_url = info['data']['attributes']['streaming']['hls']['url'] + + formats = self._extract_m3u8_formats( + hls_url, display_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + series = self._html_search_regex( + r'(?s)]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)', + webpage, 'series', fatal=False) + episode = self._search_regex( + r']+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*
\s*([^<]+)', + webpage, 'episode', fatal=False) + + mobj = re.search( + r'(?s)]+class=["\']dates["\'][^>]*>.+?\bS\.(?P\d+)\s+E\.(?P\d+)\s*-\s*(?P\d{2}/\d{2}/\d{4})', + webpage) + if mobj: + season_number = int(mobj.group('season_number')) + episode_number = int(mobj.group('episode_number')) + upload_date = unified_strdate(mobj.group('upload_date')) + else: + season_number = episode_number = upload_date = None + + return { + 'id': compat_str(video_id or display_id), + 'display_id': display_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'series': series, + 'season_number': season_number, + 'episode': episode, + 'episode_number': episode_number, + 'upload_date': upload_date, + 'formats': formats, + }