mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-17 05:28:54 +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
2024-05-28 13:22:13 -05:00
parent 54ad67d785 111b61ddef
commit 6a84199473
295 changed files with 3573 additions and 1913 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
yt_dlp/extractor/common.py
View File

@@ -1,5 +1,6 @@
import base64
import collections
import functools
import getpass
import hashlib
import http.client
@@ -21,7 +22,6 @@ import urllib.parse
import urllib.request
import xml.etree.ElementTree
from ..compat import functools # isort: split
from ..compat import (
compat_etree_fromstring,
compat_expanduser,
@@ -2451,7 +2451,7 @@ class InfoExtractor:
})
continue
src_url = src if src.startswith('http') else urllib.parse.urljoin(base, src)
src_url = src if src.startswith('http') else urllib.parse.urljoin(f'{base}/', src)
src_url = src_url.strip()
if proto == 'm3u8' or src_ext == 'm3u8':
@@ -3398,23 +3398,16 @@ class InfoExtractor:
return formats
def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
mobj = re.search(
r'''(?s)jwplayer\s*\(\s*(?P<q>'|")(?!(?P=q)).+(?P=q)\s*\)(?!</script>).*?\.\s*setup\s*\(\s*(?P<options>(?:\([^)]*\)|[^)])+)\s*\)''',
webpage)
if mobj:
try:
jwplayer_data = self._parse_json(mobj.group('options'),
video_id=video_id,
transform_source=transform_source)
except ExtractorError:
pass
else:
if isinstance(jwplayer_data, dict):
return jwplayer_data
return self._search_json(
r'''(?<!-)\bjwplayer\s*\(\s*(?P<q>'|")(?!(?P=q)).+(?P=q)\s*\)(?:(?!</script>).)*?\.\s*(?:setup\s*\(|(?P<load>load)\s*\(\s*\[)''',
webpage, 'JWPlayer data', video_id,
# must be a {...} or sequence, ending
contains_pattern=r'\{(?s:.*)}(?(load)(?:\s*,\s*\{(?s:.*)})*)', end_pattern=r'(?(load)\]|\))',
transform_source=transform_source, default=None)
def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
def _extract_jwplayer_data(self, webpage, video_id, *args, transform_source=js_to_json, **kwargs):
jwplayer_data = self._find_jwplayer_data(
webpage, video_id, transform_source=js_to_json)
webpage, video_id, transform_source=transform_source)
return self._parse_jwplayer_data(
jwplayer_data, video_id, *args, **kwargs)
@@ -3446,22 +3439,14 @@ class InfoExtractor:
mpd_id=mpd_id, rtmp_params=rtmp_params, base_url=base_url)
subtitles = {}
tracks = video_data.get('tracks')
if tracks and isinstance(tracks, list):
for track in tracks:
if not isinstance(track, dict):
continue
track_kind = track.get('kind')
if not track_kind or not isinstance(track_kind, str):
continue
if track_kind.lower() not in ('captions', 'subtitles'):
continue
track_url = urljoin(base_url, track.get('file'))
if not track_url:
continue
subtitles.setdefault(track.get('label') or 'en', []).append({
'url': self._proto_relative_url(track_url)
})
for track in traverse_obj(video_data, (
'tracks', lambda _, v: v['kind'].lower() in ('captions', 'subtitles'))):
track_url = urljoin(base_url, track.get('file'))
if not track_url:
continue
subtitles.setdefault(track.get('label') or 'en', []).append({
'url': self._proto_relative_url(track_url)
})
entry = {
'id': this_video_id,
@@ -3546,7 +3531,7 @@ class InfoExtractor:
# See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
# of jwplayer.flash.swf
rtmp_url_parts = re.split(
r'((?:mp4|mp3|flv):)', source_url, 1)
r'((?:mp4|mp3|flv):)', source_url, maxsplit=1)
if len(rtmp_url_parts) == 3:
rtmp_url, prefix, play_path = rtmp_url_parts
a_format.update({