smokephil/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-06 14:55:02 +01:00
Code Issues Projects Releases Packages Wiki Activity

use extinf

Browse source
This commit is contained in:
DTrombett 2025-11-10 17:34:33 +01:00
parent c7df4bf3ec
commit 2c6b324278
No known key found for this signature in database
GPG key ID: FD8700F69650F6AA
1 changed files with 25 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

39
yt_dlp/extractor/plutotv.py
View file

@ -1,4 +1,5 @@
import re import re
import urllib.parse
import uuid import uuid
from .common import InfoExtractor from .common import InfoExtractor
@ -29,28 +30,38 @@ class PlutoTVBase(InfoExtractor):
def _to_ad_free_formats(self, video_id, formats): def _to_ad_free_formats(self, video_id, formats):
for fmt in formats: for fmt in formats:
res = self._download_webpage( res, base = self._download_webpage_handle(
fmt.get('url'), video_id, 'Downloading m3u8 playlist', fmt.get('url'), video_id, 'Downloading m3u8 playlist',
fatal=False) fatal=False)
if not res: if not res:
continue continue
lines = res.splitlines() base = base.url
max_iv = 0 res = res.splitlines()
url_path = None path_occur = {}
for line in lines: extinf = 0
if line.startswith('#EXT-X-KEY:'): for line in res:
path, iv = re.search(r'URI="(?P<path>[^"]+)/[^.]+\.key",IV=0x0*(?P<iv>\d+)', line).group('path', 'iv') match = re.match(r'^#EXTINF:(\d+)', line)
iv = int(iv) if match:
if iv > max_iv: extinf = float_or_none(match.group(1)) or 0
max_iv = iv elif not line.startswith('#'):
url_path = path match = re.search(r'^(.+)/[^/]+$', line)
if match:
path = urllib.parse.urlparse(urllib.parse.urljoin(base, match.group(1))).path
path_occur[path] = path_occur.get(path, 0) + extinf
url_path = max(path_occur, key=path_occur.get)
if url_path: if url_path:
fmt['hls_media_playlist_data'] = '' fmt['hls_media_playlist_data'] = ''
valid = True valid = True
for line in lines: for line in res:
# prevent key mismatch
if line.startswith('#EXT-X-KEY:'): if line.startswith('#EXT-X-KEY:'):
path = re.search(r'URI="([^"]+)/[^.]+\.key"', line).group(1) match = re.search(r'URI="([^"]+)/[^.]+\.key"', line)
valid = path == url_path # if no match, the line is probably malformed, keep it as is
valid = not match or urllib.parse.urlparse(urllib.parse.urljoin(base, match.group(1))).path == url_path
elif not line.startswith('#'):
match = re.search(r'^(.+)/[^/]+$', line)
if match:
valid = urllib.parse.urlparse(urllib.parse.urljoin(base, match.group(1))).path == url_path
if valid: if valid:
fmt['hls_media_playlist_data'] += line + '\n' fmt['hls_media_playlist_data'] += line + '\n'
else: else: