mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-17 13:38:55 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'master' into yt-live-from-start-range

Browse Source
This commit is contained in:
bashonly
2024-10-09 11:23:14 -05:00
committed by GitHub
parent 160d973aee 983c58fb7a
commit 9dd8574b68
109 changed files with 2392 additions and 757 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
yt_dlp/extractor/common.py
View File

@@ -35,6 +35,7 @@ from ..networking import HEADRequest, Request
from ..networking.exceptions import (
HTTPError,
IncompleteRead,
TransportError,
network_exceptions,
)
from ..networking.impersonate import ImpersonateTarget
@@ -965,6 +966,9 @@ class InfoExtractor:
return False
content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal,
encoding=encoding, data=data)
if content is False:
assert not fatal
return False
return (content, urlh)
@staticmethod
@@ -1039,7 +1043,15 @@ class InfoExtractor:
def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True,
prefix=None, encoding=None, data=None):
webpage_bytes = urlh.read()
try:
webpage_bytes = urlh.read()
except TransportError as err:
errmsg = f'{video_id}: Error reading response: {err.msg}'
if fatal:
raise ExtractorError(errmsg, cause=err)
self.report_warning(errmsg)
return False
if prefix is not None:
webpage_bytes = prefix + webpage_bytes
if self.get_param('dump_intermediate_pages', False):
@@ -1698,7 +1710,7 @@ class InfoExtractor:
rating = traverse_obj(e, ('aggregateRating', 'ratingValue'), expected_type=float_or_none)
if rating is not None:
info['average_rating'] = rating
if is_type(e, 'TVEpisode', 'Episode'):
if is_type(e, 'TVEpisode', 'Episode', 'PodcastEpisode'):
episode_name = unescapeHTML(e.get('name'))
info.update({
'episode': episode_name,
@@ -2065,7 +2077,7 @@ class InfoExtractor:
has_drm = HlsFD._has_drm(m3u8_doc)
def format_url(url):
return url if re.match(r'^https?://', url) else urllib.parse.urljoin(m3u8_url, url)
return url if re.match(r'https?://', url) else urllib.parse.urljoin(m3u8_url, url)
if self.get_param('hls_split_discontinuity', False):
def _extract_m3u8_playlist_indices(manifest_url=None, m3u8_doc=None):
@@ -2806,11 +2818,11 @@ class InfoExtractor:
base_url_e = element.find(_add_ns('BaseURL'))
if try_call(lambda: base_url_e.text) is not None:
base_url = base_url_e.text + base_url
if re.match(r'^https?://', base_url):
if re.match(r'https?://', base_url):
break
if mpd_base_url and base_url.startswith('/'):
base_url = urllib.parse.urljoin(mpd_base_url, base_url)
elif mpd_base_url and not re.match(r'^https?://', base_url):
elif mpd_base_url and not re.match(r'https?://', base_url):
if not mpd_base_url.endswith('/'):
mpd_base_url += '/'
base_url = mpd_base_url + base_url
@@ -2900,7 +2912,7 @@ class InfoExtractor:
}
def location_key(location):
return 'url' if re.match(r'^https?://', location) else 'path'
return 'url' if re.match(r'https?://', location) else 'path'
if 'segment_urls' not in representation_ms_info and 'media' in representation_ms_info:
@@ -3503,7 +3515,7 @@ class InfoExtractor:
continue
urls.add(source_url)
source_type = source.get('type') or ''
ext = mimetype2ext(source_type) or determine_ext(source_url)
ext = determine_ext(source_url, default_ext=mimetype2ext(source_type))
if source_type == 'hls' or ext == 'm3u8' or 'format=m3u8-aapl' in source_url:
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', entry_protocol='m3u8_native',