diff options
| -rw-r--r-- | README.md | 5 | ||||
| -rw-r--r-- | youtube_dlc/extractor/skyitalia.py | 4 | ||||
| -rw-r--r-- | youtube_dlc/extractor/youtube.py | 160 |
3 files changed, 105 insertions, 64 deletions
@@ -1,6 +1,5 @@ [](https://travis-ci.com/blackjack4494/yt-dlc) [](https://pypi.org/project/youtube-dlc) -[](https://pepy.tech/project/youtube-dlc) [](https://gitter.im/youtube-dlc) [](https://github.com/blackjack4494/youtube-dlc/blob/master/LICENSE) @@ -44,6 +43,10 @@ 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/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/youtube.py b/youtube_dlc/extractor/youtube.py index d605f1e74..2e70ad6fa 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) - - 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 "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 + + 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) @@ -2811,6 +2828,16 @@ 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 @@ -2824,6 +2851,13 @@ 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] |