mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-15 20:48:58 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'yt-dlp:master' into pr/live-sections

Browse Source
This commit is contained in:
bashonly
2024-12-13 08:43:54 -06:00
parent 03eee53919 2037a6414f
commit 7d101c82a0
11 changed files with 68 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
yt_dlp/extractor/youtube.py
View File

@@ -3156,9 +3156,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# ;N&&(N=sig(decodeURIComponent(N)),J.set(R,encodeURIComponent(N)));return J};
# {var H=u,k=f.sp,v=sig(decodeURIComponent(f.s));H.set(k,encodeURIComponent(v))}
funcname = self._search_regex(
(r'\b(?P<var>[a-zA-Z0-9$]+)&&\((?P=var)=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\((?P=var)\)\)',
r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*(?P<arg>[a-zA-Z0-9$]+)\s*\)\s*{\s*(?P=arg)\s*=\s*(?P=arg)\.split\(\s*""\s*\)\s*;\s*[^}]+;\s*return\s+(?P=arg)\.join\(\s*""\s*\)',
r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)(?:;[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\))?',
(r'\b(?P<var>[a-zA-Z0-9_$]+)&&\((?P=var)=(?P<sig>[a-zA-Z0-9_$]{2,})\(decodeURIComponent\((?P=var)\)\)',
r'(?P<sig>[a-zA-Z0-9_$]+)\s*=\s*function\(\s*(?P<arg>[a-zA-Z0-9_$]+)\s*\)\s*{\s*(?P=arg)\s*=\s*(?P=arg)\.split\(\s*""\s*\)\s*;\s*[^}]+;\s*return\s+(?P=arg)\.join\(\s*""\s*\)',
r'(?:\b|[^a-zA-Z0-9_$])(?P<sig>[a-zA-Z0-9_$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)(?:;[a-zA-Z0-9_$]{2}\.[a-zA-Z0-9_$]{2}\(a,\d+\))?',
# Old patterns
r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
@@ -4096,10 +4096,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if height:
res_qualities[height] = quality
display_name = audio_track.get('displayName') or ''
is_original = 'original' in display_name.lower()
is_descriptive = 'descriptive' in display_name.lower()
is_default = audio_track.get('audioIsDefault')
is_descriptive = 'descriptive' in (audio_track.get('displayName') or '').lower()
language_code = audio_track.get('id', '').split('.')[0]
if language_code and is_default:
if language_code and (is_original or (is_default and not original_language)):
original_language = language_code
# FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
@@ -4180,7 +4182,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'filesize': int_or_none(fmt.get('contentLength')),
'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
'format_note': join_nonempty(
join_nonempty(audio_track.get('displayName'), is_default and ' (default)', delim=''),
join_nonempty(display_name, is_default and ' (default)', delim=''),
name, fmt.get('isDrc') and 'DRC',
try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
@@ -4199,7 +4201,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': fmt_url,
'width': int_or_none(fmt.get('width')),
'language': join_nonempty(language_code, 'desc' if is_descriptive else '') or None,
'language_preference': PREFERRED_LANG_VALUE if is_default else -10 if is_descriptive else -1,
'language_preference': PREFERRED_LANG_VALUE if is_original else 5 if is_default else -10 if is_descriptive else -1,
# Strictly de-prioritize broken, damaged and 3gp formats
'preference': -20 if is_broken else -10 if is_damaged else -2 if itag == '17' else None,
}
@@ -4721,7 +4723,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
(?=(?P<artist>[^\n]+))(?P=artist)\n+
(?=(?P<album>[^\n]+))(?P=album)\n
(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
(?:.+?Released\ on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
(.+?\nArtist\s*:\s*
(?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
)?.+\nAuto-generated\ by\ YouTube\.\s*$
@@ -5314,6 +5316,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
'lockupViewModel': lambda x: [self._extract_lockup_view_model(x)],
}
for key, renderer in isr_content.items():
if key not in known_renderers: