diff options
Diffstat (limited to 'yt_dlp/extractor/common.py')
| -rw-r--r-- | yt_dlp/extractor/common.py | 56 |
1 files changed, 31 insertions, 25 deletions
diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index aa98c0cc9..fc28bca2e 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import base64 +import collections import datetime import hashlib import itertools @@ -54,6 +55,7 @@ from ..utils import ( GeoRestrictedError, GeoUtils, int_or_none, + join_nonempty, js_to_json, JSON_LD_RE, mimetype2ext, @@ -341,6 +343,7 @@ class InfoExtractor(object): series, programme or podcast: series: Title of the series or programme the video episode belongs to. + series_id: Id of the series or programme the video episode belongs to, as a unicode string. season: Title of the season the video episode belongs to. season_number: Number of the season the video episode belongs to, as an integer. season_id: Id of the season the video episode belongs to, as a unicode string. @@ -441,11 +444,11 @@ class InfoExtractor(object): _WORKING = True _LOGIN_HINTS = { - 'any': 'Use --cookies, --username and --password or --netrc to provide account credentials', + 'any': 'Use --cookies, --username and --password, or --netrc to provide account credentials', 'cookies': ( 'Use --cookies-from-browser or --cookies for the authentication. ' 'See https://github.com/ytdl-org/youtube-dl#how-do-i-pass-cookies-to-youtube-dl for how to manually pass cookies'), - 'password': 'Use --username and --password or --netrc to provide account credentials', + 'password': 'Use --username and --password, or --netrc to provide account credentials', } def __init__(self, downloader=None): @@ -1449,6 +1452,9 @@ class InfoExtractor(object): item_type = e.get('@type') if expected_type is not None and expected_type != item_type: continue + rating = traverse_obj(e, ('aggregateRating', 'ratingValue'), expected_type=float_or_none) + if rating is not None: + info['average_rating'] = rating if item_type in ('TVEpisode', 'Episode'): episode_name = unescapeHTML(e.get('name')) info.update({ @@ -1495,6 +1501,13 @@ class InfoExtractor(object): break return dict((k, v) for k, v in info.items() if v is not None) + def _search_nextjs_data(self, webpage, video_id, **kw): + return self._parse_json( + self._search_regex( + r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>', + webpage, 'next.js data', **kw), + video_id, **kw) + @staticmethod def _hidden_inputs(html): html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html) @@ -1531,7 +1544,7 @@ class InfoExtractor(object): 'vcodec': {'type': 'ordered', 'regex': True, 'order': ['av0?1', 'vp0?9.2', 'vp0?9', '[hx]265|he?vc?', '[hx]264|avc', 'vp0?8', 'mp4v|h263', 'theora', '', None, 'none']}, 'acodec': {'type': 'ordered', 'regex': True, - 'order': ['opus', 'vorbis', 'aac', 'mp?4a?', 'mp3', 'e?a?c-?3', 'dts', '', None, 'none']}, + 'order': ['opus', 'vorbis', 'aac', 'mp?4a?', 'mp3', 'e-?a?c-?3', 'ac-?3', 'dts', '', None, 'none']}, 'hdr': {'type': 'ordered', 'regex': True, 'field': 'dynamic_range', 'order': ['dv', '(hdr)?12', r'(hdr)?10\+', '(hdr)?10', 'hlg', '', 'sdr', None]}, 'proto': {'type': 'ordered', 'regex': True, 'field': 'protocol', @@ -1911,7 +1924,7 @@ class InfoExtractor(object): tbr = int_or_none(media_el.attrib.get('bitrate')) width = int_or_none(media_el.attrib.get('width')) height = int_or_none(media_el.attrib.get('height')) - format_id = '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])) + format_id = join_nonempty(f4m_id, tbr or i) # If <bootstrapInfo> is present, the specified f4m is a # stream-level manifest, and only set-level manifests may refer to # external resources. See section 11.4 and section 4 of F4M spec @@ -1973,7 +1986,7 @@ class InfoExtractor(object): def _m3u8_meta_format(self, m3u8_url, ext=None, preference=None, quality=None, m3u8_id=None): return { - 'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])), + 'format_id': join_nonempty(m3u8_id, 'meta'), 'url': m3u8_url, 'ext': ext, 'protocol': 'm3u8', @@ -2026,10 +2039,10 @@ class InfoExtractor(object): video_id=None): formats, subtitles = [], {} - if '#EXT-X-FAXS-CM:' in m3u8_doc: # Adobe Flash Access - return formats, subtitles - - has_drm = re.search(r'#EXT-X-(?:SESSION-)?KEY:.*?URI="skd://', m3u8_doc) + has_drm = re.search('|'.join([ + r'#EXT-X-FAXS-CM:', # Adobe Flash Access + r'#EXT-X-(?:SESSION-)?KEY:.*?URI="skd://', # Apple FairPlay + ]), m3u8_doc) def format_url(url): return url if re.match(r'^https?://', url) else compat_urlparse.urljoin(m3u8_url, url) @@ -2068,7 +2081,7 @@ class InfoExtractor(object): if '#EXT-X-TARGETDURATION' in m3u8_doc: # media playlist, return as is formats = [{ - 'format_id': '-'.join(map(str, filter(None, [m3u8_id, idx]))), + 'format_id': join_nonempty(m3u8_id, idx), 'format_index': idx, 'url': m3u8_url, 'ext': ext, @@ -2117,7 +2130,7 @@ class InfoExtractor(object): if media_url: manifest_url = format_url(media_url) formats.extend({ - 'format_id': '-'.join(map(str, filter(None, (m3u8_id, group_id, name, idx)))), + 'format_id': join_nonempty(m3u8_id, group_id, name, idx), 'format_note': name, 'format_index': idx, 'url': manifest_url, @@ -2174,9 +2187,9 @@ class InfoExtractor(object): # format_id intact. if not live: stream_name = build_stream_name() - format_id[1] = stream_name if stream_name else '%d' % (tbr if tbr else len(formats)) + format_id[1] = stream_name or '%d' % (tbr or len(formats)) f = { - 'format_id': '-'.join(map(str, filter(None, format_id))), + 'format_id': join_nonempty(*format_id), 'format_index': idx, 'url': manifest_url, 'manifest_url': m3u8_url, @@ -2640,7 +2653,7 @@ class InfoExtractor(object): mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration')) formats, subtitles = [], {} - stream_numbers = {'audio': 0, 'video': 0} + stream_numbers = collections.defaultdict(int) for period in mpd_doc.findall(_add_ns('Period')): period_duration = parse_duration(period.get('duration')) or mpd_duration period_ms_info = extract_multisegment_info(period, { @@ -2706,10 +2719,8 @@ class InfoExtractor(object): 'format_note': 'DASH %s' % content_type, 'filesize': filesize, 'container': mimetype2ext(mime_type) + '_dash', - 'manifest_stream_number': stream_numbers[content_type] } f.update(parse_codecs(codecs)) - stream_numbers[content_type] += 1 elif content_type == 'text': f = { 'ext': mimetype2ext(mime_type), @@ -2876,7 +2887,9 @@ class InfoExtractor(object): else: # Assuming direct URL to unfragmented media. f['url'] = base_url - if content_type in ('video', 'audio') or mime_type == 'image/jpeg': + if content_type in ('video', 'audio', 'image/jpeg'): + f['manifest_stream_number'] = stream_numbers[f['url']] + stream_numbers[f['url']] += 1 formats.append(f) elif content_type == 'text': subtitles.setdefault(lang or 'und', []).append(f) @@ -2965,13 +2978,6 @@ class InfoExtractor(object): }) fragment_ctx['time'] += fragment_ctx['duration'] - format_id = [] - if ism_id: - format_id.append(ism_id) - if stream_name: - format_id.append(stream_name) - format_id.append(compat_str(tbr)) - if stream_type == 'text': subtitles.setdefault(stream_language, []).append({ 'ext': 'ismt', @@ -2990,7 +2996,7 @@ class InfoExtractor(object): }) elif stream_type in ('video', 'audio'): formats.append({ - 'format_id': '-'.join(format_id), + 'format_id': join_nonempty(ism_id, stream_name, tbr), 'url': ism_url, 'manifest_url': ism_url, 'ext': 'ismv' if stream_type == 'video' else 'isma', |