diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index cc344f601..74b50ecca 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -20,7 +20,7 @@ jobs: - name: Set up Python uses: actions/setup-python@v2 with: - python-version: '3.x' + python-version: '3.8' - name: Install packages run: sudo apt-get -y install zip pandoc man - name: Bump version diff --git a/README.md b/README.md index 08bddaa18..f884ad067 100644 --- a/README.md +++ b/README.md @@ -1,15 +1,15 @@ [![Build Status](https://travis-ci.com/blackjack4494/yt-dlc.svg?branch=master)](https://travis-ci.com/blackjack4494/yt-dlc) [![PyPi](https://img.shields.io/pypi/v/youtube-dlc.svg)](https://pypi.org/project/youtube-dlc) -[![Downloads](https://pepy.tech/badge/youtube-dlc)](https://pepy.tech/project/youtube-dlc) [![Gitter chat](https://img.shields.io/gitter/room/youtube-dlc/community)](https://gitter.im/youtube-dlc) -[![License: Unlicense](https://img.shields.io/badge/license-Unlicense-blue.svg)](https://github.com/blackjack4494/youtube-dlc/blob/master/LICENSE) +[![License: Unlicense](https://img.shields.io/badge/license-Unlicense-blue.svg)](https://github.com/blackjack4494/yt-dlc/blob/master/LICENSE) youtube-dlc - download videos from youtube.com or other video platforms. youtube-dlc is a fork of youtube-dl with the intention of getting features tested by the community merged in the tool faster, since youtube-dl's development seems to be slowing down. (https://web.archive.org/web/20201014194602/https://github.com/ytdl-org/youtube-dl/issues/26462) - [INSTALLATION](#installation) +- [UPDATE](#update) - [DESCRIPTION](#description) - [OPTIONS](#options) - [Network Options:](#network-options) @@ -44,6 +44,10 @@ You may want to use `python3` instead of `python` python -m pip install --upgrade youtube-dlc +If you want to install the current master branch + + python -m pip install git+https://github.com/blackjack4494/yt-dlc + **UNIX** (Linux, macOS, etc.) Using wget: diff --git a/setup.py b/setup.py index a10ef0a77..6908f2404 100644 --- a/setup.py +++ b/setup.py @@ -66,7 +66,7 @@ setup( description=DESCRIPTION, long_description=LONG_DESCRIPTION, # long_description_content_type="text/markdown", - url="https://github.com/blackjack4494/youtube-dlc", + url="https://github.com/blackjack4494/yt-dlc", packages=find_packages(exclude=("youtube_dl","test",)), #packages=[ # 'youtube_dlc', diff --git a/youtube_dlc/downloader/common.py b/youtube_dlc/downloader/common.py index 460364a0b..c65500d61 100644 --- a/youtube_dlc/downloader/common.py +++ b/youtube_dlc/downloader/common.py @@ -364,11 +364,12 @@ class FileDownloader(object): else '%.2f' % sleep_interval)) time.sleep(sleep_interval) else: - sleep_interval_sub = self.params.get('sleep_interval_subtitles') - self.to_screen( - '[download] Sleeping %s seconds...' % ( - int(sleep_interval_sub))) - time.sleep(sleep_interval_sub) + if self.params.get('sleep_interval_subtitles') > 0: + sleep_interval_sub = self.params.get('sleep_interval_subtitles') + self.to_screen( + '[download] Sleeping %s seconds...' % ( + sleep_interval_sub)) + time.sleep(sleep_interval_sub) return self.real_download(filename, info_dict) def real_download(self, filename, info_dict): diff --git a/youtube_dlc/extractor/extractors.py b/youtube_dlc/extractor/extractors.py index 666134d86..24c107598 100644 --- a/youtube_dlc/extractor/extractors.py +++ b/youtube_dlc/extractor/extractors.py @@ -1544,4 +1544,5 @@ from .zattoo import ( ) from .zdf import ZDFIE, ZDFChannelIE from .zingmp3 import ZingMp3IE +from .zoom import ZoomIE from .zype import ZypeIE diff --git a/youtube_dlc/extractor/la7.py b/youtube_dlc/extractor/la7.py index f5d4564fa..74b006fb5 100644 --- a/youtube_dlc/extractor/la7.py +++ b/youtube_dlc/extractor/la7.py @@ -36,6 +36,9 @@ class LA7IE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + if not url.startswith('http'): + url = '%s//%s' % (self.http_scheme(), url) + webpage = self._download_webpage(url, video_id) player_data = self._search_regex( diff --git a/youtube_dlc/extractor/mailru.py b/youtube_dlc/extractor/mailru.py index 6fdf70aa6..5bfe40649 100644 --- a/youtube_dlc/extractor/mailru.py +++ b/youtube_dlc/extractor/mailru.py @@ -12,6 +12,7 @@ from ..utils import ( parse_duration, remove_end, try_get, + urljoin, ) @@ -93,6 +94,14 @@ class MailRuIE(InfoExtractor): { 'url': 'https://my.mail.ru//list//sinyutin10/video/_myvideo/4.html', 'only_matching': True, + }, + { + 'url': 'https://my.mail.ru/mail/cloud-strife/video/embed/Games/2009', + 'only_matching': True, + }, + { + 'url': 'https://videoapi.my.mail.ru/videos/embed/mail/cloud-strife/Games/2009.html', + 'only_matching': True, } ] @@ -110,7 +119,7 @@ class MailRuIE(InfoExtractor): webpage = self._download_webpage(url, video_id) page_config = self._parse_json(self._search_regex([ r'(?s)]+class="sp-video__page-config"[^>]*>(.+?)', - r'(?s)"video":\s*(\{.+?\}),'], + r'(?s)"video":\s*({.+?}),'], webpage, 'page config', default='{}'), video_id, fatal=False) if page_config: meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl') or page_config.get('metadataUrl') @@ -121,7 +130,7 @@ class MailRuIE(InfoExtractor): # fix meta_url if missing the host address if re.match(r'^\/\+\/', meta_url): - meta_url = 'https://my.mail.ru' + meta_url + meta_url = urljoin('https://my.mail.ru', meta_url) if meta_url: video_data = self._download_json( diff --git a/youtube_dlc/extractor/skyitalia.py b/youtube_dlc/extractor/skyitalia.py index 3c7bd465d..22a6be2be 100644 --- a/youtube_dlc/extractor/skyitalia.py +++ b/youtube_dlc/extractor/skyitalia.py @@ -13,6 +13,7 @@ class SkyItaliaBaseIE(InfoExtractor): 'high': [854, 480], 'hd': [1280, 720] } + _GEO_BYPASS = False def _extract_video_id(self, url): webpage = self._download_webpage(url, 'skyitalia') @@ -43,6 +44,9 @@ class SkyItaliaBaseIE(InfoExtractor): 'height': r[1] }) + if not formats and video_data.get('geob') == 1: + self.raise_geo_restricted(countries=['IT']) + self._sort_formats(formats) title = video_data.get('title') thumb = video_data.get('thumb') diff --git a/youtube_dlc/extractor/viki.py b/youtube_dlc/extractor/viki.py index f8e360338..0f188f84d 100644 --- a/youtube_dlc/extractor/viki.py +++ b/youtube_dlc/extractor/viki.py @@ -308,19 +308,17 @@ class VikiIE(VikiBaseIE): 'url': thumbnail.get('url'), }) - stream_ids = [] - for f in formats: - s_id = f.get('stream_id') - if s_id is not None: - stream_ids.append(s_id) + new_video = self._download_json( + 'https://www.viki.com/api/videos/%s' % video_id, video_id, + 'Downloading new video JSON to get subtitles', headers={'x-viki-app-ver': '2.2.5.1428709186'}, expected_status=[200, 400, 404]) subtitles = {} - for subtitle_lang, _ in video.get('subtitle_completions', {}).items(): - subtitles[subtitle_lang] = [{ - 'ext': subtitles_format, - 'url': self._prepare_call( - 'videos/%s/subtitles/%s.%s?stream_id=%s' % (video_id, subtitle_lang, subtitles_format, stream_ids[0])), - } for subtitles_format in ('srt', 'vtt')] + for sub in new_video.get('streamSubtitles').get('dash'): + subtitles[sub.get('srclang')] = [{ + 'ext': 'vtt', + 'url': sub.get('src'), + 'completion': sub.get('percentage'), + }] result = { 'id': video_id, diff --git a/youtube_dlc/extractor/vlive.py b/youtube_dlc/extractor/vlive.py index f79531e6f..935560b57 100644 --- a/youtube_dlc/extractor/vlive.py +++ b/youtube_dlc/extractor/vlive.py @@ -11,7 +11,6 @@ from ..compat import compat_str from ..utils import ( ExtractorError, merge_dicts, - remove_start, try_get, urlencode_postdata, ) @@ -19,10 +18,10 @@ from ..utils import ( class VLiveIE(NaverBaseIE): IE_NAME = 'vlive' - _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P[0-9]+)' + _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/(?:video|post)/(?P(?:\d-)?[0-9]+)' _NETRC_MACHINE = 'vlive' _TESTS = [{ - 'url': 'http://www.vlive.tv/video/1326', + 'url': 'https://www.vlive.tv/video/1326', 'md5': 'cc7314812855ce56de70a06a27314983', 'info_dict': { 'id': '1326', @@ -32,8 +31,21 @@ class VLiveIE(NaverBaseIE): 'view_count': int, 'uploader_id': 'muploader_a', }, - }, { - 'url': 'http://www.vlive.tv/video/16937', + }, + { + 'url': 'https://vlive.tv/post/1-18244258', + 'md5': 'cc7314812855ce56de70a06a27314983', + 'info_dict': { + 'id': '1326', + 'ext': 'mp4', + 'title': "[V LIVE] Girl's Day's Broadcast", + 'creator': "Girl's Day", + 'view_count': int, + 'uploader_id': 'muploader_a', + }, + }, + { + 'url': 'https://www.vlive.tv/video/16937', 'info_dict': { 'id': '16937', 'ext': 'mp4', @@ -96,50 +108,69 @@ class VLiveIE(NaverBaseIE): raise ExtractorError('Unable to log in', expected=True) def _real_extract(self, url): - video_id = self._match_id(url) + # url may match on a post or a video url with a post_id potentially matching a video_id + working_id = self._match_id(url) + webpage = self._download_webpage(url, working_id) - webpage = self._download_webpage( - 'https://www.vlive.tv/video/%s' % video_id, video_id) + PARAMS_RE = r'window\.__PRELOADED_STATE__\s*=\s*({.*});?\s*' + PARAMS_FIELD = 'params' - VIDEO_PARAMS_RE = r'\bvlive\.video\.init\(([^)]+)' - VIDEO_PARAMS_FIELD = 'video params' + params = self._search_regex( + PARAMS_RE, webpage, PARAMS_FIELD, default='', flags=re.DOTALL) + params = self._parse_json(params, working_id, fatal=False) - params = self._parse_json(self._search_regex( - VIDEO_PARAMS_RE, webpage, VIDEO_PARAMS_FIELD, default=''), video_id, - transform_source=lambda s: '[' + s + ']', fatal=False) + video_params = try_get(params, lambda x: x["postDetail"]["post"]["officialVideo"], dict) - if not params or len(params) < 7: - params = self._search_regex( - VIDEO_PARAMS_RE, webpage, VIDEO_PARAMS_FIELD) - params = [p.strip(r'"') for p in re.split(r'\s*,\s*', params)] + if video_params is None: + error = try_get(params, lambda x: x["postDetail"]["error"], dict) + error_data = try_get(error, lambda x: x["data"], dict) + error_video = try_get(error_data, lambda x: x["officialVideo"], dict) + error_msg = try_get(error, lambda x: x["message"], compat_str) + product_type = try_get(error_data, + [lambda x: x["officialVideo"]["productType"], + lambda x: x["board"]["boardType"]], + compat_str) - status, long_video_id, key = params[2], params[5], params[6] - status = remove_start(status, 'PRODUCT_') + if error_video is not None: + if product_type in ('VLIVE_PLUS', 'VLIVE+'): + self.raise_login_required('This video is only available with V LIVE+.') + elif error_msg is not None: + raise ExtractorError('V LIVE reported the following error: %s' % error_msg) + else: + raise ExtractorError('Failed to extract video parameters.') + elif 'post' in url: + raise ExtractorError('Url does not appear to be a video post.', expected=True) + else: + raise ExtractorError('Failed to extract video parameters.') - if status in ('LIVE_ON_AIR', 'BIG_EVENT_ON_AIR'): - return self._live(video_id, webpage) - elif status in ('VOD_ON_AIR', 'BIG_EVENT_INTRO'): - return self._replay(video_id, webpage, long_video_id, key) + video_id = working_id if 'video' in url else str(video_params["videoSeq"]) - if status == 'LIVE_END': - raise ExtractorError('Uploading for replay. Please wait...', - expected=True) - elif status == 'COMING_SOON': - raise ExtractorError('Coming soon!', expected=True) - elif status == 'CANCELED': - raise ExtractorError('We are sorry, ' - 'but the live broadcast has been canceled.', - expected=True) - elif status == 'ONLY_APP': - raise ExtractorError('Unsupported video type', expected=True) + video_type = video_params["type"] + if video_type in ('VOD'): + encoding_status = video_params["encodingStatus"] + if encoding_status == 'COMPLETE': + return self._replay(video_id, webpage, params, video_params) + else: + raise ExtractorError('VOD encoding not yet complete. Please try again later.', + expected=True) + elif video_type in ('LIVE'): + video_status = video_params["status"] + if video_status in ('RESERVED'): + raise ExtractorError('Coming soon!', expected=True) + elif video_status in ('ENDED', 'END'): + raise ExtractorError('Uploading for replay. Please wait...', expected=True) + else: + return self._live(video_id, webpage, params) else: - raise ExtractorError('Unknown status %s' % status) + raise ExtractorError('Unknown video type %s' % video_type) - def _get_common_fields(self, webpage): + def _get_common_fields(self, webpage, params): title = self._og_search_title(webpage) - creator = self._html_search_regex( - r']+class="info_area"[^>]*>\s*(?:]*>.*?\s*)?]*>([^<]+)', - webpage, 'creator', fatal=False) + description = self._html_search_meta( + ['og:description', 'description', 'twitter:description'], + webpage, 'description', default=None) + creator = (try_get(params, lambda x: x["channel"]["channel"]["channelName"], compat_str) + or self._search_regex(r'on (.*) channel', description or '', 'creator', fatal=False)) thumbnail = self._og_search_thumbnail(webpage) return { 'title': title, @@ -147,24 +178,21 @@ class VLiveIE(NaverBaseIE): 'thumbnail': thumbnail, } - def _live(self, video_id, webpage): - init_page = self._download_init_page(video_id) + def _live(self, video_id, webpage, params): + LIVE_INFO_ENDPOINT = 'https://www.vlive.tv/globalv-web/vam-web/old/v3/live/%s/playInfo' % video_id + play_info = self._download_json(LIVE_INFO_ENDPOINT, video_id, + headers={"referer": "https://www.vlive.tv"}) - live_params = self._search_regex( - r'"liveStreamInfo"\s*:\s*(".*"),', - init_page, 'live stream info') - live_params = self._parse_json(live_params, video_id) - live_params = self._parse_json(live_params, video_id) + streams = try_get(play_info, lambda x: x["result"]["streamList"], list) or [] formats = [] - for vid in live_params.get('resolutions', []): + for stream in streams: formats.extend(self._extract_m3u8_formats( - vid['cdnUrl'], video_id, 'mp4', - m3u8_id=vid.get('name'), + stream['serviceUrl'], video_id, 'mp4', fatal=False, live=True)) self._sort_formats(formats) - info = self._get_common_fields(webpage) + info = self._get_common_fields(webpage, params) info.update({ 'title': self._live_title(info['title']), 'id': video_id, @@ -173,44 +201,37 @@ class VLiveIE(NaverBaseIE): }) return info - def _replay(self, video_id, webpage, long_video_id, key): - if '' in (long_video_id, key): - init_page = self._download_init_page(video_id) - video_info = self._parse_json(self._search_regex( - (r'(?s)oVideoStatus\s*=\s*({.+?})\s*[0-9A-Z]+)' - _TEST = { - 'url': 'http://channels.vlive.tv/FCD4B', + _VALID_URL = r'https?://(?:(?:www|m)\.)?(?:channels\.vlive\.tv/|vlive\.tv/channels?/)(?P[0-9A-Z]+)' + _TESTS = [{ + 'url': 'https://channels.vlive.tv/FCD4B', 'info_dict': { 'id': 'FCD4B', 'title': 'MAMAMOO', }, 'playlist_mincount': 110 - } + }, { + 'url': 'https://www.vlive.tv/channel/FCD4B', + 'info_dict': { + 'id': 'FCD4B', + 'title': 'MAMAMOO', + }, + 'playlist_mincount': 110 + }] _APP_ID = '8c6cc7b45d2568fb668be6e05b6e5a3b' def _real_extract(self, url): diff --git a/youtube_dlc/extractor/youtube.py b/youtube_dlc/extractor/youtube.py index d605f1e74..3ec2581dc 100644 --- a/youtube_dlc/extractor/youtube.py +++ b/youtube_dlc/extractor/youtube.py @@ -279,6 +279,15 @@ class YoutubeBaseInfoExtractor(InfoExtractor): return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle( *args, **compat_kwargs(kwargs)) + def _get_yt_initial_data(self, video_id, webpage): + config = self._search_regex( + (r'window\["ytInitialData"\]\s*=\s*(.*?)(?<=});', + r'var\s+ytInitialData\s*=\s*(.*?)(?<=});'), + webpage, 'ytInitialData', default=None) + if config: + return self._parse_json( + uppercase_escape(config), video_id, fatal=False) + def _real_initialize(self): if self._downloader is None: return @@ -1390,6 +1399,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # https://github.com/ytdl-org/youtube-dl/pull/7599) r';ytplayer\.config\s*=\s*({.+?});ytplayer', r';ytplayer\.config\s*=\s*({.+?});', + r'ytInitialPlayerResponse\s*=\s*({.+?});var meta' ) config = self._search_regex( patterns, webpage, 'ytplayer.config', default=None) @@ -1397,15 +1407,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return self._parse_json( uppercase_escape(config), video_id, fatal=False) - def _get_yt_initial_data(self, video_id, webpage): - config = self._search_regex( - (r'window\["ytInitialData"\]\s*=\s*(.*?)(?<=});', - r'var\s+ytInitialData\s*=\s*(.*?)(?<=});'), - webpage, 'ytInitialData', default=None) - if config: - return self._parse_json( - uppercase_escape(config), video_id, fatal=False) - def _get_music_metadata_from_yt_initial(self, yt_initial): music_metadata = [] key_map = { @@ -1454,10 +1455,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self._downloader.report_warning(err_msg) return {} try: - args = player_config['args'] - caption_url = args.get('ttsurl') - if caption_url: + if "args" in player_config and "ttsurl" in player_config["args"]: + args = player_config['args'] + caption_url = args['ttsurl'] timestamp = args['timestamp'] + # We get the available subtitles list_params = compat_urllib_parse_urlencode({ 'type': 'list', @@ -1513,40 +1515,50 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return captions # New captions format as of 22.06.2017 - player_response = args.get('player_response') - if player_response and isinstance(player_response, compat_str): - player_response = self._parse_json( - player_response, video_id, fatal=False) - if player_response: - renderer = player_response['captions']['playerCaptionsTracklistRenderer'] - caption_tracks = renderer['captionTracks'] - for caption_track in caption_tracks: - if 'kind' not in caption_track: - # not an automatic transcription - continue - base_url = caption_track['baseUrl'] - sub_lang_list = [] - for lang in renderer['translationLanguages']: - lang_code = lang.get('languageCode') - if lang_code: - sub_lang_list.append(lang_code) - return make_captions(base_url, sub_lang_list) + if "args" in player_config: + player_response = player_config["args"].get('player_response') + else: + # New player system (ytInitialPlayerResponse) as of October 2020 + player_response = player_config - self._downloader.report_warning("Couldn't find automatic captions for %s" % video_id) - return {} - # Some videos don't provide ttsurl but rather caption_tracks and - # caption_translation_languages (e.g. 20LmZk1hakA) - # Does not used anymore as of 22.06.2017 - caption_tracks = args['caption_tracks'] - caption_translation_languages = args['caption_translation_languages'] - caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0] - sub_lang_list = [] - for lang in caption_translation_languages.split(','): - lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang)) - sub_lang = lang_qs.get('lc', [None])[0] - if sub_lang: - sub_lang_list.append(sub_lang) - return make_captions(caption_url, sub_lang_list) + if player_response: + if isinstance(player_response, compat_str): + player_response = self._parse_json( + player_response, video_id, fatal=False) + + renderer = player_response['captions']['playerCaptionsTracklistRenderer'] + caption_tracks = renderer['captionTracks'] + for caption_track in caption_tracks: + if 'kind' not in caption_track: + # not an automatic transcription + continue + base_url = caption_track['baseUrl'] + sub_lang_list = [] + for lang in renderer['translationLanguages']: + lang_code = lang.get('languageCode') + if lang_code: + sub_lang_list.append(lang_code) + return make_captions(base_url, sub_lang_list) + + self._downloader.report_warning("Couldn't find automatic captions for %s" % video_id) + return {} + + if "args" in player_config: + args = player_config["args"] + + # Some videos don't provide ttsurl but rather caption_tracks and + # caption_translation_languages (e.g. 20LmZk1hakA) + # Does not used anymore as of 22.06.2017 + caption_tracks = args['caption_tracks'] + caption_translation_languages = args['caption_translation_languages'] + caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0] + sub_lang_list = [] + for lang in caption_translation_languages.split(','): + lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang)) + sub_lang = lang_qs.get('lc', [None])[0] + if sub_lang: + sub_lang_list.append(sub_lang) + return make_captions(caption_url, sub_lang_list) # An extractor error can be raise by the download process if there are # no automatic captions but there are subtitles except (KeyError, IndexError, ExtractorError): @@ -1822,21 +1834,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # Try looking directly into the video webpage ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) if ytplayer_config: - args = ytplayer_config['args'] - if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'): - # Convert to the same format returned by compat_parse_qs - video_info = dict((k, [v]) for k, v in args.items()) - add_dash_mpd(video_info) - # Rental video is not rented but preview is available (e.g. - # https://www.youtube.com/watch?v=yYr8q0y5Jfg, - # https://github.com/ytdl-org/youtube-dl/issues/10532) - if not video_info and args.get('ypc_vid'): - return self.url_result( - args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) - if args.get('livestream') == '1' or args.get('live_playback') == 1: - is_live = True - if not player_response: - player_response = extract_player_response(args.get('player_response'), video_id) + args = ytplayer_config.get("args") + if args is not None: + if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'): + # Convert to the same format returned by compat_parse_qs + video_info = dict((k, [v]) for k, v in args.items()) + add_dash_mpd(video_info) + # Rental video is not rented but preview is available (e.g. + # https://www.youtube.com/watch?v=yYr8q0y5Jfg, + # https://github.com/ytdl-org/youtube-dl/issues/10532) + if not video_info and args.get('ypc_vid'): + return self.url_result( + args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) + if args.get('livestream') == '1' or args.get('live_playback') == 1: + is_live = True + if not player_response: + player_response = extract_player_response(args.get('player_response'), video_id) + elif not player_response: + player_response = ytplayer_config if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): add_dash_mpd_pr(player_response) else: @@ -1866,8 +1881,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): age_gate = False # Try looking directly into the video webpage ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) - if ytplayer_config: - args = ytplayer_config['args'] + args = ytplayer_config.get("args") + if args is not None: if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'): # Convert to the same format returned by compat_parse_qs video_info = dict((k, [v]) for k, v in args.items()) @@ -1882,6 +1897,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): is_live = True if not player_response: player_response = extract_player_response(args.get('player_response'), video_id) + elif not player_response: + player_response = ytplayer_config if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): add_dash_mpd_pr(player_response) @@ -2614,6 +2631,12 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P\d+))?(?:[^>]+>(?P[^<]+))?)?' _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})' IE_NAME = 'youtube:playlist' + _YTM_PLAYLIST_PREFIX = 'RDCLAK5uy_' + _YTM_CHANNEL_INFO = { + 'uploader': 'Youtube Music', + 'uploader_id': 'music', # or "UC-9-kyTW8ZkZNDHQJ6FgpwQ" + 'uploader_url': 'https://www.youtube.com/music' + } _TESTS = [{ 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', 'info_dict': { @@ -2811,10 +2834,21 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): return zip(ids_in_page, titles_in_page) + def _extract_mix_ids_from_yt_initial(self, yt_initial): + ids = [] + playlist_contents = try_get(yt_initial, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist']['contents'], list) + if playlist_contents: + for item in playlist_contents: + videoId = try_get(item, lambda x: x['playlistPanelVideoRenderer']['videoId'], compat_str) + if videoId: + ids.append(videoId) + return ids + def _extract_mix(self, playlist_id): # The mixes are generated from a single video # the id of the playlist is just 'RD' + video_id ids = [] + yt_initial = None last_id = playlist_id[-11:] for n in itertools.count(1): url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id) @@ -2824,6 +2858,13 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): r'''(?xs)data-video-username=".*?".*? href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), webpage)) + + # if no ids in html of page, try using embedded json + if (len(new_ids) == 0): + yt_initial = self._get_yt_initial_data(playlist_id, webpage) + if yt_initial: + new_ids = self._extract_mix_ids_from_yt_initial(yt_initial) + # Fetch new pages until all the videos are repeated, it seems that # there are always 51 unique videos. new_ids = [_id for _id in new_ids if _id not in ids] @@ -2841,6 +2882,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): or search_title('title')) title = clean_html(title_span) + if not title: + title = try_get(yt_initial, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist']['title'], compat_str) + return self.playlist_result(url_results, playlist_id, title) def _extract_playlist(self, playlist_id): @@ -2902,6 +2946,8 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'uploader_id': uploader_id, 'uploader_url': uploader_url, }) + if playlist_id.startswith(self._YTM_PLAYLIST_PREFIX): + playlist.update(self._YTM_CHANNEL_INFO) return has_videos, playlist @@ -2932,8 +2978,10 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): return video if playlist_id.startswith(('RD', 'UL', 'PU')): - # Mixes require a custom extraction process - return self._extract_mix(playlist_id) + if not playlist_id.startswith(self._YTM_PLAYLIST_PREFIX): + # Mixes require a custom extraction process, + # Youtube Music playlists act like normal playlists (with randomized order) + return self._extract_mix(playlist_id) has_videos, playlist = self._extract_playlist(playlist_id) if has_videos or not video_id: diff --git a/youtube_dlc/extractor/zoom.py b/youtube_dlc/extractor/zoom.py new file mode 100644 index 000000000..003e1f901 --- /dev/null +++ b/youtube_dlc/extractor/zoom.py @@ -0,0 +1,82 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, + url_or_none, + parse_filesize, + urlencode_postdata +) + + +class ZoomIE(InfoExtractor): + IE_NAME = 'zoom' + _VALID_URL = r'https://(?:.*).?zoom.us/rec(?:ording)?/play/(?P<id>[A-Za-z0-9\-_]+)' + + _TEST = { + 'url': 'https://zoom.us/recording/play/SILVuCL4bFtRwWTtOCFQQxAsBQsJljFtm9e4Z_bvo-A8B-nzUSYZRNuPl3qW5IGK', + 'info_dict': { + 'md5': '031a5b379f1547a8b29c5c4c837dccf2', + 'title': "GAZ Transformational Tuesdays W/ Landon & Stapes", + 'id': "SILVuCL4bFtRwWTtOCFQQxAsBQsJljFtm9e4Z_bvo-A8B-nzUSYZRNuPl3qW5IGK", + 'ext': "mp4" + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + password_protected = self._search_regex(r'<form[^>]+?id="(password_form)"', webpage, 'password field', fatal=False, default=None) + if password_protected is not None: + self._verify_video_password(url, display_id, webpage) + webpage = self._download_webpage(url, display_id) + + video_url = self._search_regex(r"viewMp4Url: \'(.*)\'", webpage, 'video url') + title = self._html_search_regex([r"topic: \"(.*)\",", r"<title>(.*) - Zoom"], webpage, 'title') + viewResolvtionsWidth = self._search_regex(r"viewResolvtionsWidth: (\d*)", webpage, 'res width', fatal=False) + viewResolvtionsHeight = self._search_regex(r"viewResolvtionsHeight: (\d*)", webpage, 'res height', fatal=False) + fileSize = parse_filesize(self._search_regex(r"fileSize: \'(.+)\'", webpage, 'fileSize', fatal=False)) + + urlprefix = url.split("zoom.us")[0] + "zoom.us/" + + formats = [] + formats.append({ + 'url': url_or_none(video_url), + 'width': int_or_none(viewResolvtionsWidth), + 'height': int_or_none(viewResolvtionsHeight), + 'http_headers': {'Accept': 'video/webm,video/ogg,video/*;q=0.9,application/ogg;q=0.7,audio/*;q=0.6,*/*;q=0.5', + 'Referer': urlprefix}, + 'ext': "mp4", + 'filesize_approx': int_or_none(fileSize) + }) + self._sort_formats(formats) + + return { + 'id': display_id, + 'title': title, + 'formats': formats + } + + def _verify_video_password(self, url, video_id, webpage): + password = self._downloader.params.get('videopassword') + if password is None: + raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) + meetId = self._search_regex(r']+?id="meetId" value="([^\"]+)"', webpage, 'meetId') + data = urlencode_postdata({ + 'id': meetId, + 'passwd': password, + 'action': "viewdetailedpage", + 'recaptcha': "" + }) + validation_url = url.split("zoom.us")[0] + "zoom.us/rec/validate_meet_passwd" + validation_response = self._download_json( + validation_url, video_id, + note='Validating Password...', + errnote='Wrong password?', + data=data) + + if validation_response['errorCode'] != 0: + raise ExtractorError('Login failed, %s said: %r' % (self.IE_NAME, validation_response['errorMessage'])) diff --git a/youtube_dlc/options.py b/youtube_dlc/options.py index 66b45220c..3c8a1305e 100644 --- a/youtube_dlc/options.py +++ b/youtube_dlc/options.py @@ -582,7 +582,7 @@ def parseOpts(overrideArguments=None): 'along with --min-sleep-interval.')) workarounds.add_option( '--sleep-subtitles', - dest='sleep_interval_subtitles', action='store_true', default=0, + dest='sleep_interval_subtitles', default=0, type=int, help='Enforce sleep interval on subtitles as well') verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') diff --git a/youtube_dlc/postprocessor/ffmpeg.py b/youtube_dlc/postprocessor/ffmpeg.py index 5e85f4eeb..c38db3143 100644 --- a/youtube_dlc/postprocessor/ffmpeg.py +++ b/youtube_dlc/postprocessor/ffmpeg.py @@ -412,7 +412,9 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): for lang, sub_info in subtitles.items(): sub_ext = sub_info['ext'] - if ext != 'webm' or ext == 'webm' and sub_ext == 'vtt': + if sub_ext == 'json': + self._downloader.to_screen('[ffmpeg] JSON subtitles cannot be embedded') + elif ext != 'webm' or ext == 'webm' and sub_ext == 'vtt': sub_langs.append(lang) sub_filenames.append(subtitles_filename(filename, lang, sub_ext, ext)) else: @@ -643,13 +645,18 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor): self._downloader.to_screen( '[ffmpeg] Subtitle file for %s is already in the requested format' % new_ext) continue + elif ext == 'json': + self._downloader.to_screen( + '[ffmpeg] You have requested to convert json subtitles into another format, ' + 'which is currently not possible') + continue old_file = subtitles_filename(filename, lang, ext, info.get('ext')) sub_filenames.append(old_file) new_file = subtitles_filename(filename, lang, new_ext, info.get('ext')) if ext in ('dfxp', 'ttml', 'tt'): self._downloader.report_warning( - 'You have requested to convert dfxp (TTML) subtitles into another format, ' + '[ffmpeg] You have requested to convert dfxp (TTML) subtitles into another format, ' 'which results in style information loss') dfxp_file = old_file