diff options
| -rw-r--r-- | youtube_dlc/extractor/extractors.py | 1 | ||||
| -rw-r--r-- | youtube_dlc/extractor/la7.py | 3 | ||||
| -rw-r--r-- | youtube_dlc/extractor/vlive.py | 187 | ||||
| -rw-r--r-- | youtube_dlc/extractor/youtube.py | 4 | ||||
| -rw-r--r-- | youtube_dlc/extractor/zoom.py | 82 | ||||
| -rw-r--r-- | youtube_dlc/postprocessor/ffmpeg.py | 11 |
6 files changed, 203 insertions, 85 deletions
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/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<id>[0-9]+)' + _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/(?:video|post)/(?P<id>(?:\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) - - webpage = self._download_webpage( - 'https://www.vlive.tv/video/%s' % video_id, video_id) - - VIDEO_PARAMS_RE = r'\bvlive\.video\.init\(([^)]+)' - VIDEO_PARAMS_FIELD = 'video params' - - params = self._parse_json(self._search_regex( - VIDEO_PARAMS_RE, webpage, VIDEO_PARAMS_FIELD, default=''), video_id, - transform_source=lambda s: '[' + s + ']', fatal=False) - - 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)] - - status, long_video_id, key = params[2], params[5], params[6] - status = remove_start(status, 'PRODUCT_') - - 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) - - 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) + # 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) + + PARAMS_RE = r'window\.__PRELOADED_STATE__\s*=\s*({.*});?\s*</script>' + PARAMS_FIELD = 'params' + + params = self._search_regex( + PARAMS_RE, webpage, PARAMS_FIELD, default='', flags=re.DOTALL) + params = self._parse_json(params, working_id, fatal=False) + + video_params = try_get(params, lambda x: x["postDetail"]["post"]["officialVideo"], dict) + + 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) + + 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.') + + video_id = working_id if 'video' in url else str(video_params["videoSeq"]) + + 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'<div[^>]+class="info_area"[^>]*>\s*(?:<em[^>]*>.*?</em\s*>\s*)?<a\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*</script', - r'(?s)oVideoStatus\s*=\s*({.+})'), init_page, 'video info'), - video_id) - if video_info.get('status') == 'NEED_CHANNEL_PLUS': - self.raise_login_required( - 'This video is only available for CH+ subscribers') - long_video_id, key = video_info['vid'], video_info['inkey'] + def _replay(self, video_id, webpage, params, video_params): + long_video_id = video_params["vodId"] + + VOD_KEY_ENDPOINT = 'https://www.vlive.tv/globalv-web/vam-web/video/v1.0/vod/%s/inkey' % video_id + key_json = self._download_json(VOD_KEY_ENDPOINT, video_id, + headers={"referer": "https://www.vlive.tv"}) + key = key_json["inkey"] return merge_dicts( - self._get_common_fields(webpage), + self._get_common_fields(webpage, params), self._extract_video_info(video_id, long_video_id, key)) - def _download_init_page(self, video_id): - return self._download_webpage( - 'https://www.vlive.tv/video/init/view', - video_id, note='Downloading live webpage', - data=urlencode_postdata({'videoSeq': video_id}), - headers={ - 'Referer': 'https://www.vlive.tv/video/%s' % video_id, - 'Content-Type': 'application/x-www-form-urlencoded' - }) - class VLiveChannelIE(InfoExtractor): IE_NAME = 'vlive:channel' - _VALID_URL = r'https?://channels\.vlive\.tv/(?P<id>[0-9A-Z]+)' - _TEST = { - 'url': 'http://channels.vlive.tv/FCD4B', + _VALID_URL = r'https?://(?:(?:www|m)\.)?(?:channels\.vlive\.tv/|vlive\.tv/channels?/)(?P<id>[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 cd4e844a0..3ec2581dc 100644 --- a/youtube_dlc/extractor/youtube.py +++ b/youtube_dlc/extractor/youtube.py @@ -2848,6 +2848,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): # 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) @@ -2881,6 +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): 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</title>"], 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'<input[^>]+?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 |