diff options
| -rwxr-xr-x | youtube_dl/YoutubeDL.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/brightcove.py | 12 | ||||
| -rw-r--r-- | youtube_dl/extractor/cinemassacre.py | 119 | ||||
| -rw-r--r-- | youtube_dl/extractor/extractors.py | 7 | ||||
| -rw-r--r-- | youtube_dl/extractor/imdb.py | 37 | ||||
| -rw-r--r-- | youtube_dl/extractor/mgtv.py | 43 | ||||
| -rw-r--r-- | youtube_dl/extractor/nrk.py | 430 | ||||
| -rw-r--r-- | youtube_dl/extractor/openload.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/sina.py | 124 | ||||
| -rw-r--r-- | youtube_dl/extractor/twitch.py | 27 | ||||
| -rw-r--r-- | youtube_dl/extractor/ustudio.py | 66 | ||||
| -rw-r--r-- | youtube_dl/utils.py | 4 |
12 files changed, 403 insertions, 469 deletions
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 34eeb77c5..03a6a1890 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -720,6 +720,7 @@ class YoutubeDL(object): result_type = ie_result.get('_type', 'video') if result_type in ('url', 'url_transparent'): + ie_result['url'] = sanitize_url(ie_result['url']) extract_flat = self.params.get('extract_flat', False) if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or extract_flat is True): diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index f0781fc27..fc7fc5b16 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -307,9 +307,10 @@ class BrightcoveLegacyIE(InfoExtractor): playlist_title=playlist_info['mediaCollectionDTO']['displayName']) def _extract_video_info(self, video_info): + video_id = compat_str(video_info['id']) publisher_id = video_info.get('publisherId') info = { - 'id': compat_str(video_info['id']), + 'id': video_id, 'title': video_info['displayName'].strip(), 'description': video_info.get('shortDescription'), 'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'), @@ -331,7 +332,8 @@ class BrightcoveLegacyIE(InfoExtractor): url_comp = compat_urllib_parse_urlparse(url) if url_comp.path.endswith('.m3u8'): formats.extend( - self._extract_m3u8_formats(url, info['id'], 'mp4')) + self._extract_m3u8_formats( + url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) continue elif 'akamaihd.net' in url_comp.netloc: # This type of renditions are served through @@ -365,7 +367,7 @@ class BrightcoveLegacyIE(InfoExtractor): a_format.update({ 'format_id': 'hls%s' % ('-%s' % tbr if tbr else ''), 'ext': 'mp4', - 'protocol': 'm3u8', + 'protocol': 'm3u8_native', }) formats.append(a_format) @@ -395,7 +397,7 @@ class BrightcoveLegacyIE(InfoExtractor): return ad_info if 'url' not in info and not info.get('formats'): - raise ExtractorError('Unable to extract video url for %s' % info['id']) + raise ExtractorError('Unable to extract video url for %s' % video_id) return info @@ -527,7 +529,7 @@ class BrightcoveNewIE(InfoExtractor): if not src: continue formats.extend(self._extract_m3u8_formats( - src, video_id, 'mp4', m3u8_id='hls', fatal=False)) + src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) elif source_type == 'application/dash+xml': if not src: continue diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py deleted file mode 100644 index 042c4f2f1..000000000 --- a/youtube_dl/extractor/cinemassacre.py +++ /dev/null @@ -1,119 +0,0 @@ -# encoding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ExtractorError -from .screenwavemedia import ScreenwaveMediaIE - - -class CinemassacreIE(InfoExtractor): - _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)' - _TESTS = [ - { - 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', - 'md5': 'fde81fbafaee331785f58cd6c0d46190', - 'info_dict': { - 'id': 'Cinemassacre-19911', - 'ext': 'mp4', - 'upload_date': '20121110', - 'title': '“Angry Video Game Nerd: The Movie” – Trailer', - 'description': 'md5:fb87405fcb42a331742a0dce2708560b', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, - { - 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', - 'md5': 'd72f10cd39eac4215048f62ab477a511', - 'info_dict': { - 'id': 'Cinemassacre-521be8ef82b16', - 'ext': 'mp4', - 'upload_date': '20131002', - 'title': 'The Mummy’s Hand (1940)', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, - { - # Youtube embedded video - 'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/', - 'md5': 'ec9838a5520ef5409b3e4e42fcb0a3b9', - 'info_dict': { - 'id': 'OEVzPCY2T-g', - 'ext': 'webm', - 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles', - 'upload_date': '20061207', - 'uploader': 'Cinemassacre', - 'uploader_id': 'JamesNintendoNerd', - 'description': 'md5:784734696c2b8b7f4b8625cc799e07f6', - } - }, - { - # Youtube embedded video - 'url': 'http://cinemassacre.com/2006/09/01/mckids/', - 'md5': '7393c4e0f54602ad110c793eb7a6513a', - 'info_dict': { - 'id': 'FnxsNhuikpo', - 'ext': 'webm', - 'upload_date': '20060901', - 'uploader': 'Cinemassacre Extra', - 'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53', - 'uploader_id': 'Cinemassacre', - 'title': 'AVGN: McKids', - } - }, - { - 'url': 'http://cinemassacre.com/2015/05/25/mario-kart-64-nintendo-64-james-mike-mondays/', - 'md5': '1376908e49572389e7b06251a53cdd08', - 'info_dict': { - 'id': 'Cinemassacre-555779690c440', - 'ext': 'mp4', - 'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!', - 'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays', - 'upload_date': '20150525', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - } - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') - video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d') - - webpage = self._download_webpage(url, display_id) - - playerdata_url = self._search_regex( - [ - ScreenwaveMediaIE.EMBED_PATTERN, - r'<iframe[^>]+src="(?P<url>(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"', - ], - webpage, 'player data URL', default=None, group='url') - if not playerdata_url: - raise ExtractorError('Unable to find player data') - - video_title = self._html_search_regex( - r'<title>(?P<title>.+?)\|', webpage, 'title') - video_description = self._html_search_regex( - r'<div class="entry-content">(?P<description>.+?)</div>', - webpage, 'description', flags=re.DOTALL, fatal=False) - video_thumbnail = self._og_search_thumbnail(webpage) - - return { - '_type': 'url_transparent', - 'display_id': display_id, - 'title': video_title, - 'description': video_description, - 'upload_date': video_date, - 'thumbnail': video_thumbnail, - 'url': playerdata_url, - } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a0bb3d4c2..b6f4ccc5d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -124,7 +124,6 @@ from .chirbit import ( ChirbitProfileIE, ) from .cinchcast import CinchcastIE -from .cinemassacre import CinemassacreIE from .cliprs import ClipRsIE from .clipfish import ClipfishIE from .cliphunter import CliphunterIE @@ -834,7 +833,6 @@ from .twitch import ( TwitchVodIE, TwitchProfileIE, TwitchPastBroadcastsIE, - TwitchBookmarksIE, TwitchStreamIE, ) from .twitter import ( @@ -852,7 +850,10 @@ from .unistra import UnistraIE from .urort import UrortIE from .usatoday import USATodayIE from .ustream import UstreamIE, UstreamChannelIE -from .ustudio import UstudioIE +from .ustudio import ( + UstudioIE, + UstudioEmbedIE, +) from .varzesh3 import Varzesh3IE from .vbox7 import Vbox7IE from .veehd import VeeHDIE diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 8bed8ccd0..3a2b7cec5 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -1,10 +1,10 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..utils import ( + mimetype2ext, qualities, ) @@ -12,9 +12,9 @@ from ..utils import ( class ImdbIE(InfoExtractor): IE_NAME = 'imdb' IE_DESC = 'Internet Movie Database trailers' - _VALID_URL = r'https?://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)' + _VALID_URL = r'https?://(?:www|m)\.imdb\.com/video/[^/]+/vi(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.imdb.com/video/imdb/vi2524815897', 'info_dict': { 'id': '2524815897', @@ -22,7 +22,10 @@ class ImdbIE(InfoExtractor): 'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb', 'description': 'md5:9061c2219254e5d14e03c25c98e96a81', } - } + }, { + 'url': 'http://www.imdb.com/video/_/vi2524815897', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -48,13 +51,27 @@ class ImdbIE(InfoExtractor): json_data = self._search_regex( r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>', format_page, 'json data', flags=re.DOTALL) - info = json.loads(json_data) - format_info = info['videoPlayerObject']['video'] - f_id = format_info['ffname'] + info = self._parse_json(json_data, video_id, fatal=False) + if not info: + continue + format_info = info.get('videoPlayerObject', {}).get('video', {}) + if not format_info: + continue + video_info_list = format_info.get('videoInfoList') + if not video_info_list or not isinstance(video_info_list, list): + continue + video_info = video_info_list[0] + if not video_info or not isinstance(video_info, dict): + continue + video_url = video_info.get('videoUrl') + if not video_url: + continue + format_id = format_info.get('ffname') formats.append({ - 'format_id': f_id, - 'url': format_info['videoInfoList'][0]['videoUrl'], - 'quality': quality(f_id), + 'format_id': format_id, + 'url': video_url, + 'ext': mimetype2ext(video_info.get('videoMimeType')), + 'quality': quality(format_id), }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/mgtv.py b/youtube_dl/extractor/mgtv.py index a14d176a5..9fbc74f5d 100644 --- a/youtube_dl/extractor/mgtv.py +++ b/youtube_dl/extractor/mgtv.py @@ -11,7 +11,7 @@ class MGTVIE(InfoExtractor): _TEST = { 'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html', - 'md5': '', + 'md5': '1bdadcf760a0b90946ca68ee9a2db41a', 'info_dict': { 'id': '3116640', 'ext': 'mp4', @@ -20,15 +20,6 @@ class MGTVIE(InfoExtractor): 'duration': 7461, 'thumbnail': 're:^https?://.*\.jpg$', }, - 'params': { - 'skip_download': True, # m3u8 download - }, - } - - _FORMAT_MAP = { - '标清': ('Standard', 0), - '高清': ('High', 1), - '超清': ('SuperHigh', 2), } def _real_extract(self, url): @@ -40,17 +31,27 @@ class MGTVIE(InfoExtractor): formats = [] for idx, stream in enumerate(api_data['stream']): - format_name = stream.get('name') - format_id, preference = self._FORMAT_MAP.get(format_name, (None, None)) - format_info = self._download_json( - stream['url'], video_id, - note='Download video info for format %s' % format_id or '#%d' % idx) - formats.append({ - 'format_id': format_id, - 'url': format_info['info'], - 'ext': 'mp4', # These are m3u8 playlists - 'preference': preference, - }) + stream_url = stream.get('url') + if not stream_url: + continue + tbr = int_or_none(self._search_regex( + r'(\d+)\.mp4', stream_url, 'tbr', default=None)) + + def extract_format(stream_url, format_id, idx, query={}): + format_info = self._download_json( + stream_url, video_id, + note='Download video info for format %s' % format_id or '#%d' % idx, query=query) + return { + 'format_id': format_id, + 'url': format_info['info'], + 'ext': 'mp4', + 'tbr': tbr, + } + + formats.append(extract_format( + stream_url, 'hls-%d' % tbr if tbr else None, idx * 2)) + formats.append(extract_format(stream_url.replace( + '/playlist.m3u8', ''), 'http-%d' % tbr if tbr else None, idx * 2 + 1, {'pno': 1031})) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 51dfc27ac..7532f40c1 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -4,91 +4,217 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urlparse, - compat_urllib_parse_unquote, -) +from ..compat import compat_urllib_parse_unquote from ..utils import ( - determine_ext, ExtractorError, - float_or_none, + int_or_none, + parse_age_limit, parse_duration, - unified_strdate, ) -class NRKIE(InfoExtractor): - _VALID_URL = r'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)' - - _TESTS = [ - { - 'url': 'http://www.nrk.no/video/PS*150533', - # MD5 is unstable - 'info_dict': { - 'id': '150533', - 'ext': 'flv', - 'title': 'Dompap og andre fugler i Piip-Show', - 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', - 'duration': 263, - } - }, - { - 'url': 'http://www.nrk.no/video/PS*154915', - # MD5 is unstable - 'info_dict': { - 'id': '154915', - 'ext': 'flv', - 'title': 'Slik høres internett ut når du er blind', - 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568', - 'duration': 20, - } - }, - ] +class NRKBaseIE(InfoExtractor): + def _extract_formats(self, manifest_url, video_id, fatal=True): + formats = [] + formats.extend(self._extract_f4m_formats( + manifest_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', + video_id, f4m_id='hds', fatal=fatal)) + formats.extend(self._extract_m3u8_formats(manifest_url.replace( + 'akamaihd.net/z/', 'akamaihd.net/i/').replace('/manifest.f4m', '/master.m3u8'), + video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=fatal)) + return formats def _real_extract(self, url): video_id = self._match_id(url) data = self._download_json( - 'http://v8.psapi.nrk.no/mediaelement/%s' % video_id, - video_id, 'Downloading media JSON') + 'http://%s/mediaelement/%s' % (self._API_HOST, video_id), + video_id, 'Downloading mediaelement JSON') + + title = data.get('fullTitle') or data.get('mainTitle') or data['title'] + video_id = data.get('id') or video_id + + entries = [] + + media_assets = data.get('mediaAssets') + if media_assets and isinstance(media_assets, list): + def video_id_and_title(idx): + return ((video_id, title) if len(media_assets) == 1 + else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx))) + for num, asset in enumerate(media_assets, 1): + asset_url = asset.get('url') + if not asset_url: + continue + formats = self._extract_formats(asset_url, video_id, fatal=False) + if not formats: + continue + self._sort_formats(formats) + entry_id, entry_title = video_id_and_title(num) + duration = parse_duration(asset.get('duration')) + subtitles = {} + for subtitle in ('webVtt', 'timedText'): + subtitle_url = asset.get('%sSubtitlesUrl' % subtitle) + if subtitle_url: + subtitles.setdefault('no', []).append({'url': subtitle_url}) + entries.append({ + 'id': asset.get('carrierId') or entry_id, + 'title': entry_title, + 'duration': duration, + 'subtitles': subtitles, + 'formats': formats, + }) - media_url = data.get('mediaUrl') + if not entries: + media_url = data.get('mediaUrl') + if media_url: + formats = self._extract_formats(media_url, video_id) + self._sort_formats(formats) + duration = parse_duration(data.get('duration')) + entries = [{ + 'id': video_id, + 'title': title, + 'duration': duration, + 'formats': formats, + }] - if not media_url: - if data['usageRights']['isGeoBlocked']: + if not entries: + if data.get('usageRights', {}).get('isGeoBlocked'): raise ExtractorError( 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', expected=True) - if determine_ext(media_url) == 'f4m': - formats = self._extract_f4m_formats( - media_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id, f4m_id='hds') - self._sort_formats(formats) - else: - formats = [{ - 'url': media_url, - 'ext': 'flv', - }] - - duration = parse_duration(data.get('duration')) + conviva = data.get('convivaStatistics') or {} + series = conviva.get('seriesName') or data.get('seriesTitle') + episode = conviva.get('episodeName') or data.get('episodeNumberOrDate') + thumbnails = None images = data.get('images') - if images: - thumbnails = images['webImages'] - thumbnails.sort(key=lambda image: image['pixelWidth']) - thumbnail = thumbnails[-1]['imageUrl'] - else: - thumbnail = None - - return { - 'id': video_id, - 'title': data['title'], - 'description': data['description'], - 'duration': duration, - 'thumbnail': thumbnail, - 'formats': formats, + if images and isinstance(images, dict): + web_images = images.get('webImages') + if isinstance(web_images, list): + thumbnails = [{ + 'url': image['imageUrl'], + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + } for image in web_images if image.get('imageUrl')] + + description = data.get('description') + + common_info = { + 'description': description, + 'series': series, + 'episode': episode, + 'age_limit': parse_age_limit(data.get('legalAge')), + 'thumbnails': thumbnails, } + vcodec = 'none' if data.get('mediaType') == 'Audio' else None + + # TODO: extract chapters when https://github.com/rg3/youtube-dl/pull/9409 is merged + + for entry in entries: + entry.update(common_info) + for f in entry['formats']: + f['vcodec'] = vcodec + + return self.playlist_result(entries, video_id, title, description) + + +class NRKIE(NRKBaseIE): + _VALID_URL = r'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)' + _API_HOST = 'v8.psapi.nrk.no' + _TESTS = [{ + # video + 'url': 'http://www.nrk.no/video/PS*150533', + 'md5': '2f7f6eeb2aacdd99885f355428715cfa', + 'info_dict': { + 'id': '150533', + 'ext': 'mp4', + 'title': 'Dompap og andre fugler i Piip-Show', + 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', + 'duration': 263, + } + }, { + # audio + 'url': 'http://www.nrk.no/video/PS*154915', + # MD5 is unstable + 'info_dict': { + 'id': '154915', + 'ext': 'flv', + 'title': 'Slik høres internett ut når du er blind', + 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568', + 'duration': 20, + } + }] + + +class NRKTVIE(NRKBaseIE): + IE_DESC = 'NRK TV and NRK Radio' + _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?' + _API_HOST = 'psapi-we.nrk.no' + + _TESTS = [{ + 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', + 'md5': '4e9ca6629f09e588ed240fb11619922a', + 'info_dict': { + 'id': 'MUHH48000314AA', + 'ext': 'mp4', + 'title': '20 spørsmål 23.05.2014', + 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', + 'duration': 1741.52, + }, + }, { + 'url': 'https://tv.nrk.no/program/mdfp15000514', + 'md5': '43d0be26663d380603a9cf0c24366531', + 'info_dict': { + 'id': 'MDFP15000514CA', + 'ext': 'mp4', + 'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014', + 'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db', + 'duration': 4605.08, + }, + }, { + # single playlist video + 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2', + 'md5': 'adbd1dbd813edaf532b0a253780719c2', + 'info_dict': { + 'id': 'MSPO40010515-part2', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + }, + 'skip': 'Only works from Norway', + }, { + 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015', + 'playlist': [{ + 'md5': '9480285eff92d64f06e02a5367970a7a', + 'info_dict': { + 'id': 'MSPO40010515-part1', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + }, + }, { + 'md5': 'adbd1dbd813edaf532b0a253780719c2', + 'info_dict': { + 'id': 'MSPO40010515-part2', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + }, + }], + 'info_dict': { + 'id': 'MSPO40010515', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + 'duration': 6947.52, + }, + 'skip': 'Only works from Norway', + }, { + 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#', + 'only_matching': True, + }] + class NRKPlaylistIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)' @@ -159,179 +285,3 @@ class NRKSkoleIE(InfoExtractor): nrk_id = self._search_regex(r'data-nrk-id=["\'](\d+)', webpage, 'nrk id') return self.url_result('nrk:%s' % nrk_id) - - -class NRKTVIE(InfoExtractor): - IE_DESC = 'NRK TV and NRK Radio' - _VALID_URL = r'(?P<baseurl>https?://(?:tv|radio)\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?' - - _TESTS = [ - { - 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', - 'info_dict': { - 'id': 'MUHH48000314', - 'ext': 'mp4', - 'title': '20 spørsmål', - 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', - 'upload_date': '20140523', - 'duration': 1741.52, - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, - { - 'url': 'https://tv.nrk.no/program/mdfp15000514', - 'info_dict': { - 'id': 'mdfp15000514', - 'ext': 'mp4', - 'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting', - 'description': 'md5:654c12511f035aed1e42bdf5db3b206a', - 'upload_date': '20140524', - 'duration': 4605.08, - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, - { - # single playlist video - 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2', - 'md5': 'adbd1dbd813edaf532b0a253780719c2', - 'info_dict': { - 'id': 'MSPO40010515-part2', - 'ext': 'flv', - 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', - 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', - 'upload_date': '20150106', - }, - 'skip': 'Only works from Norway', - }, - { - 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015', - 'playlist': [ - { - 'md5': '9480285eff92d64f06e02a5367970a7a', - 'info_dict': { - 'id': 'MSPO40010515-part1', - 'ext': 'flv', - 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)', - 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', - 'upload_date': '20150106', - }, - }, - { - 'md5': 'adbd1dbd813edaf532b0a253780719c2', - 'info_dict': { - 'id': 'MSPO40010515-part2', - 'ext': 'flv', - 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', - 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', - 'upload_date': '20150106', - }, - }, - ], - 'info_dict': { - 'id': 'MSPO40010515', - 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn', - 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', - 'upload_date': '20150106', - 'duration': 6947.5199999999995, - }, - 'skip': 'Only works from Norway', - }, - { - 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#', - 'only_matching': True, - } - ] - - def _extract_f4m(self, manifest_url, video_id): - return self._extract_f4m_formats( - manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id, f4m_id='hds') - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - part_id = mobj.group('part_id') - base_url = mobj.group('baseurl') - - webpage = self._download_webpage(url, video_id) - - title = self._html_search_meta( - 'title', webpage, 'title') - description = self._html_search_meta( - 'description', webpage, 'description') - - thumbnail = self._html_search_regex( - r'data-posterimage="([^"]+)"', - webpage, 'thumbnail', fatal=False) - upload_date = unified_strdate(self._html_search_meta( - 'rightsfrom', webpage, 'upload date', fatal=False)) - duration = float_or_none(self._html_search_regex( - r'data-duration="([^"]+)"', - webpage, 'duration', fatal=False)) - - # playlist - parts = re.findall( - r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage) - if parts: - entries = [] - for current_part_id, stream_url, part_title in parts: - if part_id and current_part_id != part_id: - continue - video_part_id = '%s-part%s' % (video_id, current_part_id) - formats = self._extract_f4m(stream_url, video_part_id) - entries.append({ - 'id': video_part_id, - 'title': part_title, - 'description': description, - 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'formats': formats, - }) - if part_id: - if entries: - return entries[0] - else: - playlist = self.playlist_result(entries, video_id, title, description) - playlist.update({ - 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'duration': duration, - }) - return playlist - - formats = [] - - f4m_url = re.search(r'data-media="([^"]+)"', webpage) - if f4m_url: - formats.extend(self._extract_f4m(f4m_url.group(1), video_id)) - - m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage) - if m3u8_url: - formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4', m3u8_id='hls')) - self._sort_formats(formats) - - subtitles_url = self._html_search_regex( - r'data-subtitlesurl\s*=\s*(["\'])(?P<url>.+?)\1', - webpage, 'subtitle URL', default=None, group='url') - subtitles = {} - if subtitles_url: - subtitles['no'] = [{ - 'ext': 'ttml', - 'url': compat_urlparse.urljoin(base_url, subtitles_url), - }] - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - } diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 456561bcc..5049b870e 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -100,7 +100,7 @@ class OpenloadIE(InfoExtractor): raise ExtractorError('File not found', expected=True) code = self._search_regex( - r'<video[^>]+>\s*<script[^>]+>([^<]+)</script>', + r'</video>\s*</div>\s*<script[^>]+>([^<]+)</script>', webpage, 'JS code') decoded = self.openload_decode(code) diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py index d03f1b1d4..8fc66732a 100644 --- a/youtube_dl/extractor/sina.py +++ b/youtube_dl/extractor/sina.py @@ -4,28 +4,35 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urllib_parse_urlencode -from ..utils import sanitized_Request +from ..utils import ( + HEADRequest, + ExtractorError, + int_or_none, + update_url_query, + qualities, + get_element_by_attribute, + clean_html, +) class SinaIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://(.*?\.)?video\.sina\.com\.cn/ - ( - (.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=)|b/)(?P<id>\d+?)($|&|\-)))) - | + _VALID_URL = r'''(?x)https?://(?:.*?\.)?video\.sina\.com\.cn/ + (?: + (?:view/|.*\#)(?P<video_id>\d+)| + .+?/(?P<pseudo_id>[^/?#]+)(?:\.s?html)| # This is used by external sites like Weibo - (api/sinawebApi/outplay.php/(?P<token>.+?)\.swf) + api/sinawebApi/outplay.php/(?P<token>.+?)\.swf ) ''' _TESTS = [ { - 'url': 'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898', - 'md5': 'd65dd22ddcf44e38ce2bf58a10c3e71f', + 'url': 'http://video.sina.com.cn/news/spj/topvideoes20160504/?opsubject_id=top1#250576622', + 'md5': 'd38433e2fc886007729735650ae4b3e9', 'info_dict': { - 'id': '110028898', - 'ext': 'flv', - 'title': '《中国新闻》 朝鲜要求巴拿马立即释放被扣船员', + 'id': '250576622', + 'ext': 'mp4', + 'title': '现场:克鲁兹宣布退选 特朗普将稳获提名', } }, { @@ -35,37 +42,74 @@ class SinaIE(InfoExtractor): 'ext': 'flv', 'title': '军方提高对朝情报监视级别', }, + 'skip': 'the page does not exist or has been deleted', + }, + { + 'url': 'http://video.sina.com.cn/view/250587748.html', + 'md5': '3d1807a25c775092aab3bc157fff49b4', + 'info_dict': { + 'id': '250587748', + 'ext': 'mp4', + 'title': '瞬间泪目：8年前汶川地震珍贵视频首曝光', + }, }, ] - def _extract_video(self, video_id): - data = compat_urllib_parse_urlencode({'vid': video_id}) - url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data, - video_id, 'Downloading video url') - image_page = self._download_webpage( - 'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data, - video_id, 'Downloading thumbnail info') - - return {'id': video_id, - 'url': url_doc.find('./durl/url').text, - 'ext': 'flv', - 'title': url_doc.find('./vname').text, - 'thumbnail': image_page.split('=')[1], - } - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - if mobj.group('token') is not None: - # The video id is in the redirected url - self.to_screen('Getting video id') - request = sanitized_Request(url) - request.get_method = lambda: 'HEAD' - (_, urlh) = self._download_webpage_handle(request, 'NA', False) - return self._real_extract(urlh.geturl()) - elif video_id is None: - pseudo_id = mobj.group('pseudo_id') - webpage = self._download_webpage(url, pseudo_id) - video_id = self._search_regex(r'vid:\'(\d+?)\'', webpage, 'video id') - return self._extract_video(video_id) + video_id = mobj.group('video_id') + if not video_id: + if mobj.group('token') is not None: + # The video id is in the redirected url + self.to_screen('Getting video id') + request = HEADRequest(url) + (_, urlh) = self._download_webpage_handle(request, 'NA', False) + return self._real_extract(urlh.geturl()) + else: + pseudo_id = mobj.group('pseudo_id') + webpage = self._download_webpage(url, pseudo_id) + error = get_element_by_attribute('class', 'errtitle', webpage) + if error: + raise ExtractorError('%s said: %s' % ( + self.IE_NAME, clean_html(error)), expected=True) + video_id = self._search_regex( + r"video_id\s*:\s*'(\d+)'", webpage, 'video id') + + video_data = self._download_json( + 'http://s.video.sina.com.cn/video/h5play', + video_id, query={'video_id': video_id}) + if video_data['code'] != 1: + raise ExtractorError('%s said: %s' % ( + self.IE_NAME, video_data['message']), expected=True) + else: + video_data = video_data['data'] + title = video_data['title'] + description = video_data.get('description') + if description: + description = description.strip() + + preference = qualities(['cif', 'sd', 'hd', 'fhd', 'ffd']) + formats = [] + for quality_id, quality in video_data.get('videos', {}).get('mp4', {}).items(): + file_api = quality.get('file_api') + file_id = quality.get('file_id') + if not file_api or not file_id: + continue + formats.append({ + 'format_id': quality_id, + 'url': update_url_query(file_api, {'vid': file_id}), + 'preference': preference(quality_id), + 'ext': 'mp4', + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': video_data.get('image'), + 'duration': int_or_none(video_data.get('length')), + 'timestamp': int_or_none(video_data.get('create_time')), + 'formats': formats, + } diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 36ee1adff..f7b98e190 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -171,6 +171,7 @@ class TwitchVideoIE(TwitchItemBaseIE): 'title': 'Worlds Semifinals - Star Horn Royal Club vs. OMG', }, 'playlist_mincount': 12, + 'skip': 'HTTP Error 404: Not Found', } @@ -187,6 +188,7 @@ class TwitchChapterIE(TwitchItemBaseIE): 'title': 'ACRL Off Season - Sports Cars @ Nordschleife', }, 'playlist_mincount': 3, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://www.twitch.tv/tsm_theoddone/c/2349361', 'only_matching': True, @@ -355,31 +357,6 @@ class TwitchPastBroadcastsIE(TwitchPlaylistBaseIE): } -class TwitchBookmarksIE(TwitchPlaylistBaseIE): - IE_NAME = 'twitch:bookmarks' - _VALID_URL = r'%s/(?P<id>[^/]+)/profile/bookmarks/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE - _PLAYLIST_URL = '%s/api/bookmark/?user=%%s&offset=%%d&limit=%%d' % TwitchBaseIE._API_BASE - _PLAYLIST_TYPE = 'bookmarks' - - _TEST = { - 'url': 'http://www.twitch.tv/ognos/profile/bookmarks', - 'info_dict': { - 'id': 'ognos', - 'title': 'Ognos', - }, - 'playlist_mincount': 3, - } - - def _extract_playlist_page(self, response): - entries = [] - for bookmark in response.get('bookmarks', []): - video = bookmark.get('video') - if not video: - continue - entries.append(video['url']) - return entries - - class TwitchStreamIE(TwitchBaseIE): IE_NAME = 'twitch:stream' _VALID_URL = r'%s/(?P<id>[^/#?]+)/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE diff --git a/youtube_dl/extractor/ustudio.py b/youtube_dl/extractor/ustudio.py index cafc082b6..3484a2046 100644 --- a/youtube_dl/extractor/ustudio.py +++ b/youtube_dl/extractor/ustudio.py @@ -6,10 +6,12 @@ from .common import InfoExtractor from ..utils import ( int_or_none, unified_strdate, + unescapeHTML, ) class UstudioIE(InfoExtractor): + IE_NAME = 'ustudio' _VALID_URL = r'https?://(?:(?:www|v1)\.)?ustudio\.com/video/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)' _TEST = { 'url': 'http://ustudio.com/video/Uxu2my9bgSph/san_francisco_golden_gate_bridge', @@ -27,9 +29,7 @@ class UstudioIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') + video_id, display_id = re.match(self._VALID_URL, url).groups() config = self._download_xml( 'http://v1.ustudio.com/embed/%s/ustudio/config.xml' % video_id, @@ -37,7 +37,7 @@ class UstudioIE(InfoExtractor): def extract(kind): return [{ - 'url': item.attrib['url'], + 'url': unescapeHTML(item.attrib['url']), 'width': int_or_none(item.get('width')), 'height': int_or_none(item.get('height')), } for item in config.findall('./qualities/quality/%s' % kind) if item.get('url')] @@ -65,3 +65,61 @@ class UstudioIE(InfoExtractor): 'uploader': uploader, 'formats': formats, } + + +class UstudioEmbedIE(InfoExtractor): + IE_NAME = 'ustudio:embed' + _VALID_URL = r'https?://(?:(?:app|embed)\.)?ustudio\.com/embed/(?P<uid>[^/]+)/(?P<id>[^/]+)' + _TEST = { + 'url': 'http://app.ustudio.com/embed/DeN7VdYRDKhP/Uw7G1kMCe65T', + 'md5': '47c0be52a09b23a7f40de9469cec58f4', + 'info_dict': { + 'id': 'Uw7G1kMCe65T', + 'ext': 'mp4', + 'title': '5 Things IT Should Know About Video', + 'description': 'md5:93d32650884b500115e158c5677d25ad', + 'uploader_id': 'DeN7VdYRDKhP', + } + } + + def _real_extract(self, url): + uploader_id, video_id = re.match(self._VALID_URL, url).groups() + video_data = self._download_json( + 'http://app.ustudio.com/embed/%s/%s/config.json' % (uploader_id, video_id), + video_id)['videos'][0] + title = video_data['name'] + + formats = [] + for ext, qualities in video_data.get('transcodes', {}).items(): + for quality in qualities: + quality_url = quality.get('url') + if not quality_url: + continue + height = int_or_none(quality.get('height')) + formats.append({ + 'format_id': '%s-%dp' % (ext, height) if height else ext, + 'url': quality_url, + 'width': int_or_none(quality.get('width')), + 'height': height, + }) + self._sort_formats(formats) + + thumbnails = [] + for image in video_data.get('images', []): + image_url = image.get('url') + if not image_url: + continue + thumbnails.append({ + 'url': image_url, + }) + + return { + 'id': video_id, + 'title': title, + 'description': video_data.get('description'), + 'duration': int_or_none(video_data.get('duration')), + 'uploader_id': uploader_id, + 'tags': video_data.get('keywords'), + 'thumbnails': thumbnails, + 'formats': formats, + } diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 6592c8ec2..d6f94f8cd 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -50,6 +50,7 @@ from .compat import ( compat_urllib_parse, compat_urllib_parse_urlencode, compat_urllib_parse_urlparse, + compat_urllib_parse_unquote_plus, compat_urllib_request, compat_urlparse, compat_xpath, @@ -886,7 +887,8 @@ def make_socks_conn_class(base_class, socks_proxy): socks_type, url_components.hostname, url_components.port or 1080, True, # Remote DNS - url_components.username, url_components.password + compat_urllib_parse_unquote_plus(url_components.username), + compat_urllib_parse_unquote_plus(url_components.password), ) class SocksConnection(base_class): |