diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 2bf54cd58..dd6a95256 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -82,7 +82,7 @@ jobs: - name: Set up Python uses: actions/setup-python@v2 with: - python-version: '3.x' + python-version: '3.8' - name: Install Requirements run: pip install pyinstaller - name: Bump version @@ -109,14 +109,14 @@ jobs: runs-on: windows-latest - needs: build_unix + needs: [build_unix, build_windows] steps: - uses: actions/checkout@v2 - - name: Set up Python 3.5.4 32-Bit + - name: Set up Python 3.4.4 32-Bit uses: actions/setup-python@v2 with: - python-version: '3.5.4' + python-version: '3.4.4' architecture: 'x86' - name: Install Requirements for 32 Bit run: pip install pyinstaller==3.5 @@ -146,10 +146,10 @@ jobs: SHA2_UNIX: ${{ needs.build_unix.outputs.sha2_unix }} YTDLC_VERSION: ${{ needs.build_unix.outputs.ytdlc_version }} run: | - echo "version:$YTDLC_VERSION" >> SHA2-256SUMS - echo "youtube-dlc.exe:$SHA2_WINDOWS" >> SHA2-256SUMS - echo "youtube-dlc32.exe:$SHA2_WINDOWS32" >> SHA2-256SUMS - echo "youtube-dlc:$SHA2_UNIX" >> SHA2-256SUMS + echo "version:${env:YTDLC_VERSION}" >> SHA2-256SUMS + echo "youtube-dlc.exe:${env:SHA2_WINDOWS}" >> SHA2-256SUMS + echo "youtube-dlc_x86.exe:${env:SHA2_WINDOWS32}" >> SHA2-256SUMS + echo "youtube-dlc:${env:SHA2_UNIX}" >> SHA2-256SUMS - name: Upload 256SUMS file id: upload-sums 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 c65500d61..7d303be1c 100644 --- a/youtube_dlc/downloader/common.py +++ b/youtube_dlc/downloader/common.py @@ -364,8 +364,10 @@ class FileDownloader(object): else '%.2f' % sleep_interval)) time.sleep(sleep_interval) else: - if self.params.get('sleep_interval_subtitles') > 0: + sleep_interval_sub = 0 + if type(self.params.get('sleep_interval_subtitles')) is int: sleep_interval_sub = self.params.get('sleep_interval_subtitles') + if sleep_interval_sub > 0: self.to_screen( '[download] Sleeping %s seconds...' % ( sleep_interval_sub)) diff --git a/youtube_dlc/downloader/external.py b/youtube_dlc/downloader/external.py index c31f8910a..d2f8f271d 100644 --- a/youtube_dlc/downloader/external.py +++ b/youtube_dlc/downloader/external.py @@ -115,8 +115,10 @@ class CurlFD(ExternalFD): def _make_cmd(self, tmpfilename, info_dict): cmd = [self.exe, '--location', '-o', tmpfilename] - for key, val in info_dict['http_headers'].items(): - cmd += ['--header', '%s: %s' % (key, val)] + if info_dict.get('http_headers') is not None: + for key, val in info_dict['http_headers'].items(): + cmd += ['--header', '%s: %s' % (key, val)] + cmd += self._bool_option('--continue-at', 'continuedl', '-', '0') cmd += self._valueless_option('--silent', 'noprogress') cmd += self._valueless_option('--verbose', 'verbose') @@ -150,8 +152,9 @@ class AxelFD(ExternalFD): def _make_cmd(self, tmpfilename, info_dict): cmd = [self.exe, '-o', tmpfilename] - for key, val in info_dict['http_headers'].items(): - cmd += ['-H', '%s: %s' % (key, val)] + if info_dict.get('http_headers') is not None: + for key, val in info_dict['http_headers'].items(): + cmd += ['-H', '%s: %s' % (key, val)] cmd += self._configuration_args() cmd += ['--', info_dict['url']] return cmd @@ -162,8 +165,9 @@ class WgetFD(ExternalFD): def _make_cmd(self, tmpfilename, info_dict): cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies'] - for key, val in info_dict['http_headers'].items(): - cmd += ['--header', '%s: %s' % (key, val)] + if info_dict.get('http_headers') is not None: + for key, val in info_dict['http_headers'].items(): + cmd += ['--header', '%s: %s' % (key, val)] cmd += self._option('--limit-rate', 'ratelimit') retry = self._option('--tries', 'retries') if len(retry) == 2: @@ -189,8 +193,9 @@ class Aria2cFD(ExternalFD): if dn: cmd += ['--dir', dn] cmd += ['--out', os.path.basename(tmpfilename)] - for key, val in info_dict['http_headers'].items(): - cmd += ['--header', '%s: %s' % (key, val)] + if info_dict.get('http_headers') is not None: + for key, val in info_dict['http_headers'].items(): + cmd += ['--header', '%s: %s' % (key, val)] cmd += self._option('--interface', 'source_address') cmd += self._option('--all-proxy', 'proxy') cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=') @@ -206,8 +211,10 @@ class HttpieFD(ExternalFD): def _make_cmd(self, tmpfilename, info_dict): cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']] - for key, val in info_dict['http_headers'].items(): - cmd += ['%s:%s' % (key, val)] + + if info_dict.get('http_headers') is not None: + for key, val in info_dict['http_headers'].items(): + cmd += ['%s:%s' % (key, val)] return cmd @@ -253,7 +260,7 @@ class FFmpegFD(ExternalFD): # if end_time: # args += ['-t', compat_str(end_time - start_time)] - if info_dict['http_headers'] and re.match(r'^https?://', url): + if info_dict.get('http_headers') is not None and re.match(r'^https?://', url): # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv: # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header. headers = handle_youtubedl_headers(info_dict['http_headers']) diff --git a/youtube_dlc/downloader/youtube_live_chat.py b/youtube_dlc/downloader/youtube_live_chat.py index 4932dd9c5..b333afa5b 100644 --- a/youtube_dlc/downloader/youtube_live_chat.py +++ b/youtube_dlc/downloader/youtube_live_chat.py @@ -82,7 +82,10 @@ class YoutubeLiveChatReplayFD(FragmentFD): offset = int(replay_chat_item_action['videoOffsetTimeMsec']) processed_fragment.extend( json.dumps(action, ensure_ascii=False).encode('utf-8') + b'\n') - continuation_id = live_chat_continuation['continuations'][0]['liveChatReplayContinuationData']['continuation'] + try: + continuation_id = live_chat_continuation['continuations'][0]['liveChatReplayContinuationData']['continuation'] + except KeyError: + continuation_id = None self._append_fragment(ctx, processed_fragment) diff --git a/youtube_dlc/extractor/extractors.py b/youtube_dlc/extractor/extractors.py index 5dde2965b..c18a64fa4 100644 --- a/youtube_dlc/extractor/extractors.py +++ b/youtube_dlc/extractor/extractors.py @@ -1175,6 +1175,7 @@ from .theweatherchannel import TheWeatherChannelIE from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE from .thisoldhouse import ThisOldHouseIE +from .thisvid import ThisVidIE from .threeqsdn import ThreeQSDNIE from .tiktok import TikTokIE from .tinypic import TinyPicIE @@ -1541,4 +1542,5 @@ 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/thisvid.py b/youtube_dlc/extractor/thisvid.py new file mode 100644 index 000000000..f507e1b06 --- /dev/null +++ b/youtube_dlc/extractor/thisvid.py @@ -0,0 +1,97 @@ +# coding: utf-8 +from __future__ import unicode_literals +import re + +from .common import InfoExtractor + + +class ThisVidIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?thisvid\.com/(?Pvideos|embed)/(?P[A-Za-z0-9-]+/?)' + _TESTS = [{ + 'url': 'https://thisvid.com/videos/french-boy-pantsed/', + 'md5': '3397979512c682f6b85b3b04989df224', + 'info_dict': { + 'id': '2400174', + 'ext': 'mp4', + 'title': 'French Boy Pantsed', + 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg', + 'age_limit': 18, + } + }, { + 'url': 'https://thisvid.com/embed/2400174/', + 'md5': '3397979512c682f6b85b3b04989df224', + 'info_dict': { + 'id': '2400174', + 'ext': 'mp4', + 'title': 'French Boy Pantsed', + 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg', + 'age_limit': 18, + } + }] + + def _real_extract(self, url): + main_id = self._match_id(url) + webpage = self._download_webpage(url, main_id) + + # URL decryptor was reversed from version 4.0.4, later verified working with 5.2.0 and may change in the future. + kvs_version = self._html_search_regex(r'' + 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..97cc793f9 100644 --- a/youtube_dlc/extractor/youtube.py +++ b/youtube_dlc/extractor/youtube.py @@ -36,6 +36,7 @@ from ..utils import ( get_element_by_attribute, get_element_by_id, int_or_none, + js_to_json, mimetype2ext, orderedSet, parse_codecs, @@ -70,6 +71,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor): _LOGIN_REQUIRED = False _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}' + _INITIAL_DATA_RE = r'(?:window\["ytInitialData"\]|ytInitialData)\W?=\W?({.*?});' + _YTCFG_DATA_RE = r"ytcfg.set\(({.*?})\)" _YOUTUBE_CLIENT_HEADERS = { 'x-youtube-client-name': '1', @@ -274,11 +277,19 @@ class YoutubeBaseInfoExtractor(InfoExtractor): def _download_webpage_handle(self, *args, **kwargs): query = kwargs.get('query', {}).copy() - query['disable_polymer'] = 'true' kwargs['query'] = query 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 @@ -288,15 +299,61 @@ class YoutubeBaseInfoExtractor(InfoExtractor): class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor): - # Extract entries from page with "Load more" button - def _entries(self, page, playlist_id): - more_widget_html = content_html = page - for page_num in itertools.count(1): - for entry in self._process_page(content_html): + + def _find_entries_in_json(self, extracted): + entries = [] + c = {} + + def _real_find(obj): + if obj is None or isinstance(obj, str): + return + + if type(obj) is list: + for elem in obj: + _real_find(elem) + + if type(obj) is dict: + if self._is_entry(obj): + entries.append(obj) + return + + if 'continuationCommand' in obj: + c['continuation'] = obj + return + + for _, o in obj.items(): + _real_find(o) + + _real_find(extracted) + + return entries, try_get(c, lambda x: x["continuation"]) + + def _entries(self, page, playlist_id, max_pages=None): + seen = [] + + yt_conf = {} + for m in re.finditer(self._YTCFG_DATA_RE, page): + parsed = self._parse_json(m.group(1), playlist_id, + transform_source=js_to_json, fatal=False) + if parsed: + yt_conf.update(parsed) + + data_json = self._parse_json(self._search_regex(self._INITIAL_DATA_RE, page, 'ytInitialData'), None) + + for page_num in range(1, max_pages + 1) if max_pages is not None else itertools.count(1): + entries, continuation = self._find_entries_in_json(data_json) + processed = self._process_entries(entries, seen) + + if not processed: + break + for entry in processed: yield entry - mobj = re.search(r'data-uix-load-more-href="/?(?P[^"]+)"', more_widget_html) - if not mobj: + if not continuation or not yt_conf: + break + continuation_token = try_get(continuation, lambda x: x['continuationCommand']['token']) + continuation_url = try_get(continuation, lambda x: x['commandMetadata']['webCommandMetadata']['apiUrl']) + if not continuation_token or not continuation_url: break count = 0 @@ -305,12 +362,23 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor): try: # Downloading page may result in intermittent 5xx HTTP error # that is usually worked around with a retry - more = self._download_json( - 'https://www.youtube.com/%s' % mobj.group('more'), playlist_id, - 'Downloading page #%s%s' - % (page_num, ' (retry #%d)' % count if count else ''), + data_json = self._download_json( + 'https://www.youtube.com%s' % continuation_url, + playlist_id, + 'Downloading continuation page #%s%s' % (page_num, ' (retry #%d)' % count if count else ''), + transform_source=uppercase_escape, - headers=self._YOUTUBE_CLIENT_HEADERS) + query={ + 'key': try_get(yt_conf, lambda x: x['INNERTUBE_API_KEY']) + }, + data=str(json.dumps({ + 'context': try_get(yt_conf, lambda x: x['INNERTUBE_CONTEXT']), + 'continuation': continuation_token + })).encode(encoding='UTF-8', errors='strict'), + headers={ + 'Content-Type': 'application/json' + } + ) break except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503): @@ -319,31 +387,30 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor): continue raise - content_html = more['content_html'] - if not content_html.strip(): - # Some webpages show a "Load more" button but they don't - # have more videos - break - more_widget_html = more['load_more_widget_html'] + def _extract_title(self, renderer): + title = try_get(renderer, lambda x: x['title']['runs'][0]['text'], compat_str) + if title: + return title + return try_get(renderer, lambda x: x['title']['simpleText'], compat_str) class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): - def _process_page(self, content): - for video_id, video_title in self.extract_videos_from_page(content): - yield self.url_result(video_id, 'Youtube', video_id, video_title) + def _is_entry(self, obj): + return 'videoId' in obj - def extract_videos_from_page_impl(self, video_re, page, ids_in_page, titles_in_page): - for mobj in re.finditer(video_re, page): - # The link with index 0 is not the first video of the playlist (not sure if still actual) - if 'index' in mobj.groupdict() and mobj.group('id') == '0': + def _process_entries(self, entries, seen): + ids_in_page = [] + titles_in_page = [] + for renderer in entries: + video_id = try_get(renderer, lambda x: x['videoId']) + video_title = self._extract_title(renderer) + + if video_id is None or video_title is None: + # we do not have a videoRenderer or title extraction broke continue - video_id = mobj.group('id') - video_title = unescapeHTML( - mobj.group('title')) if 'title' in mobj.groupdict() else None - if video_title: - video_title = video_title.strip() - if video_title == '► Play all': - video_title = None + + video_title = video_title.strip() + try: idx = ids_in_page.index(video_id) if video_title and not titles_in_page[idx]: @@ -352,19 +419,17 @@ class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): ids_in_page.append(video_id) titles_in_page.append(video_title) - def extract_videos_from_page(self, page): - ids_in_page = [] - titles_in_page = [] - self.extract_videos_from_page_impl( - self._VIDEO_RE, page, ids_in_page, titles_in_page) - return zip(ids_in_page, titles_in_page) + for video_id, video_title in zip(ids_in_page, titles_in_page): + yield self.url_result(video_id, 'Youtube', video_id, video_title) class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): - def _process_page(self, content): - for playlist_id in orderedSet(re.findall( - r']+class="[^"]*yt-lockup-title[^"]*"[^>]*>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"', - content)): + def _is_entry(self, obj): + return 'playlistId' in obj + + def _process_entries(self, entries, seen): + for playlist_id in orderedSet(try_get(r, lambda x: x['playlistId']) for r in entries): + yield self.url_result( 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist') @@ -1390,6 +1455,7 @@ 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 +1463,6 @@ 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 +1511,11 @@ 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 +1571,50 @@ 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 +1890,24 @@ 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 +1937,8 @@ 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 +1953,8 @@ 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 +2687,12 @@ 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 +2890,21 @@ 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 +2914,13 @@ 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 +2938,9 @@ 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 +3002,8 @@ 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 +3034,10 @@ 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: @@ -3192,11 +3296,7 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): }] -class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor): - _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?' - - -class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor): +class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistBaseInfoExtractor): IE_DESC = 'YouTube.com searches' # there doesn't appear to be a real limit, for example if you search for # 'python' you get more than 8.000.000 results @@ -3293,11 +3393,10 @@ class YoutubeSearchDateIE(YoutubeSearchIE): _SEARCH_PARAMS = 'CAI%3D' -class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor): +class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor): IE_DESC = 'YouTube.com search URLs' IE_NAME = 'youtube:search_url' _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)' - _SEARCH_DATA = r'(?:window\["ytInitialData"\]|ytInitialData)\W?=\W?({.*?});' _TESTS = [{ 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', 'playlist_mincount': 5, @@ -3309,63 +3408,20 @@ class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor): 'only_matching': True, }] - def _find_videos_in_json(self, extracted): - videos = [] + def _process_json_dict(self, obj, videos, c): + if "videoId" in obj: + videos.append(obj) + return - def _real_find(obj): - if obj is None or isinstance(obj, str): - return - - if type(obj) is list: - for elem in obj: - _real_find(elem) - - if type(obj) is dict: - if "videoId" in obj: - videos.append(obj) - return - - for _, o in obj.items(): - _real_find(o) - - _real_find(extracted) - - return videos - - def extract_videos_from_page_impl(self, page, ids_in_page, titles_in_page): - search_response = self._parse_json(self._search_regex(self._SEARCH_DATA, page, 'ytInitialData'), None) - - result_items = self._find_videos_in_json(search_response) - - for renderer in result_items: - video_id = try_get(renderer, lambda x: x['videoId']) - video_title = try_get(renderer, lambda x: x['title']['runs'][0]['text']) or try_get(renderer, lambda x: x['title']['simpleText']) - - if video_id is None or video_title is None: - # we do not have a videoRenderer or title extraction broke - continue - - video_title = video_title.strip() - - try: - idx = ids_in_page.index(video_id) - if video_title and not titles_in_page[idx]: - titles_in_page[idx] = video_title - except ValueError: - ids_in_page.append(video_id) - titles_in_page.append(video_title) - - def extract_videos_from_page(self, page): - ids_in_page = [] - titles_in_page = [] - self.extract_videos_from_page_impl(page, ids_in_page, titles_in_page) - return zip(ids_in_page, titles_in_page) + if "nextContinuationData" in obj: + c["continuation"] = obj["nextContinuationData"] + return def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) query = compat_urllib_parse_unquote_plus(mobj.group('query')) webpage = self._download_webpage(url, query) - return self.playlist_result(self._process_page(webpage), playlist_title=query) + return self.playlist_result(self._entries(webpage, query, max_pages=5), playlist_title=query) class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): @@ -3387,14 +3443,12 @@ class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): 'https://www.youtube.com/show/%s/playlists' % playlist_id) -class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): +class YoutubeFeedsInfoExtractor(YoutubePlaylistBaseInfoExtractor): """ Base class for feed extractors Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. """ _LOGIN_REQUIRED = True - _FEED_DATA = r'(?:window\["ytInitialData"\]|ytInitialData)\W?=\W?({.*?});' - _YTCFG_DATA = r"ytcfg.set\(({.*?})\)" @property def IE_NAME(self): @@ -3403,96 +3457,35 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): def _real_initialize(self): self._login() - def _find_videos_in_json(self, extracted): - videos = [] - c = {} + def _process_entries(self, entries, seen): + new_info = [] + for v in entries: + v_id = try_get(v, lambda x: x['videoId']) + if not v_id: + continue - def _real_find(obj): - if obj is None or isinstance(obj, str): - return + have_video = False + for old in seen: + if old['videoId'] == v_id: + have_video = True + break - if type(obj) is list: - for elem in obj: - _real_find(elem) + if not have_video: + new_info.append(v) - if type(obj) is dict: - if "videoId" in obj: - videos.append(obj) - return + if not new_info: + return - if "nextContinuationData" in obj: - c["continuation"] = obj["nextContinuationData"] - return - - for _, o in obj.items(): - _real_find(o) - - _real_find(extracted) - - return videos, try_get(c, lambda x: x["continuation"]) - - def _entries(self, page): - info = [] - - yt_conf = self._parse_json(self._search_regex(self._YTCFG_DATA, page, 'ytcfg.set', default="null"), None, fatal=False) - - search_response = self._parse_json(self._search_regex(self._FEED_DATA, page, 'ytInitialData'), None) - - for page_num in itertools.count(1): - video_info, continuation = self._find_videos_in_json(search_response) - - new_info = [] - - for v in video_info: - v_id = try_get(v, lambda x: x['videoId']) - if not v_id: - continue - - have_video = False - for old in info: - if old['videoId'] == v_id: - have_video = True - break - - if not have_video: - new_info.append(v) - - if not new_info: - break - - info.extend(new_info) - - for video in new_info: - yield self.url_result(try_get(video, lambda x: x['videoId']), YoutubeIE.ie_key(), video_title=try_get(video, lambda x: x['title']['runs'][0]['text']) or try_get(video, lambda x: x['title']['simpleText'])) - - if not continuation or not yt_conf: - break - - search_response = self._download_json( - 'https://www.youtube.com/browse_ajax', self._PLAYLIST_TITLE, - 'Downloading page #%s' % page_num, - transform_source=uppercase_escape, - query={ - "ctoken": try_get(continuation, lambda x: x["continuation"]), - "continuation": try_get(continuation, lambda x: x["continuation"]), - "itct": try_get(continuation, lambda x: x["clickTrackingParams"]) - }, - headers={ - "X-YouTube-Client-Name": try_get(yt_conf, lambda x: x["INNERTUBE_CONTEXT_CLIENT_NAME"]), - "X-YouTube-Client-Version": try_get(yt_conf, lambda x: x["INNERTUBE_CONTEXT_CLIENT_VERSION"]), - "X-Youtube-Identity-Token": try_get(yt_conf, lambda x: x["ID_TOKEN"]), - "X-YouTube-Device": try_get(yt_conf, lambda x: x["DEVICE"]), - "X-YouTube-Page-CL": try_get(yt_conf, lambda x: x["PAGE_CL"]), - "X-YouTube-Page-Label": try_get(yt_conf, lambda x: x["PAGE_BUILD_LABEL"]), - "X-YouTube-Variants-Checksum": try_get(yt_conf, lambda x: x["VARIANTS_CHECKSUM"]), - }) + seen.extend(new_info) + for video in new_info: + yield self.url_result(try_get(video, lambda x: x['videoId']), YoutubeIE.ie_key(), video_title=self._extract_title(video)) def _real_extract(self, url): page = self._download_webpage( 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE) - return self.playlist_result( - self._entries(page), playlist_title=self._PLAYLIST_TITLE) + return self.playlist_result(self._entries(page, self._PLAYLIST_TITLE), + playlist_title=self._PLAYLIST_TITLE) class YoutubeWatchLaterIE(YoutubePlaylistIE): diff --git a/youtube_dlc/extractor/zoom.py b/youtube_dlc/extractor/zoom.py new file mode 100644 index 000000000..038a90297 --- /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|share)/(?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/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 diff --git a/youtube_dlc/version.py b/youtube_dlc/version.py index 440d8e488..201a981cf 100644 --- a/youtube_dlc/version.py +++ b/youtube_dlc/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2020.10.25' +__version__ = '2020.11.11-2'