etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-22 06:00:00 +00:00
Code Issues Projects Releases Wiki Activity

[plutotv] Fix format extraction for some urls

Browse source 
* And fallback to the first urls if ad-free urls can't be found
Closes #299
This commit is contained in:
pukkandan 2021-05-06 00:23:19 +05:30
parent 7700b37f39
commit 12e73423f1
No known key found for this signature in database
GPG key ID: 0F00D95A001F4698
1 changed files with 17 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
yt_dlp/extractor/plutotv.py
View file

@ -80,26 +80,37 @@ class PlutoTVIE(InfoExtractor):
def _to_ad_free_formats(self, video_id, formats, subtitles):
ad_free_formats, ad_free_subtitles, m3u8_urls = [], {}, set()
for format in formats:
for fmt in formats:
res = self._download_webpage(
format.get('url'), video_id, note='Downloading m3u8 playlist',
fmt.get('url'), video_id, note='Downloading m3u8 playlist',
fatal=False)
if not res:
continue
first_segment_url = re.search(
r'^(https?://.*/)0\-(end|[0-9]+)/[^/]+\.ts$', res,
re.MULTILINE)
if not first_segment_url:
if first_segment_url:
m3u8_urls.add(
compat_urlparse.urljoin(first_segment_url.group(1), '0-end/master.m3u8'))
continue
first_segment_url = re.search(
r'^(https?://.*/).+\-0+\.ts$', res,
re.MULTILINE)
if first_segment_url:
m3u8_urls.add(
compat_urlparse.urljoin(first_segment_url.group(1), 'master.m3u8'))
continue
m3u8_urls.add(
compat_urlparse.urljoin(first_segment_url.group(1), '0-end/master.m3u8'))
for m3u8_url in m3u8_urls:
fmts, subs = self._extract_m3u8_formats_and_subtitles(
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
ad_free_formats.extend(fmts)
ad_free_subtitles = self._merge_subtitles(ad_free_subtitles, subs)
return ad_free_formats, ad_free_subtitles
if ad_free_formats:
formats, subtitles = ad_free_formats, ad_free_subtitles
else:
self._downloader.report_warning('Unable to find ad-free formats')
return formats, subtitles
def _get_video_info(self, video_json, slug, series_name=None):
video_id = video_json.get('_id', slug)