Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[ie/Twitch] Fix video formats extraction #8960

Merged
merged 2 commits into from Jan 9, 2024
Merged

[ie/Twitch] Fix video formats extraction #8960

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
adf2598
[ie/Twitch] Fix video formats extraction
DmitryScaletta Jan 8, 2024
9c40947
[ie/Twitch] Refactor extracting formats
DmitryScaletta Jan 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
52 changes: 22 additions & 30 deletions yt_dlp/extractor/twitch.py
View file
Open in desktop
Expand Up @@ -8,7 +8,6 @@
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
)
from ..utils import (
Expand Down Expand Up @@ -191,6 +190,24 @@ def _get_thumbnails(self, thumbnail):
'url': thumbnail,
}] if thumbnail else None

def _extract_twitch_m3u8_formats(self, type, id, token, signature):
URLS_MAP = {
'video': '%s/vod/%s.m3u8',
'stream': '%s/api/channel/hls/%s.m3u8'
}
query = {
'allow_source': 'true',
'allow_audio_only': 'true',
'allow_spectre': 'true',
'p': random.randint(1000000, 10000000),
'player': 'twitchweb',
'playlist_include_framerate': 'true',
'sig': signature,
'token': token,
}
return self._extract_m3u8_formats(
URLS_MAP[type] % (self._USHER_BASE, id), id, 'mp4', query=query)
Copy link
Member

@bashonly bashonly Jan 9, 2024 •
edited

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe it would be simpler to do it like this:

Suggested change
def _extract_twitch_m3u8_formats(self, type, id, token, signature):
URLS_MAP = {
'video': '%s/vod/%s.m3u8',
'stream': '%s/api/channel/hls/%s.m3u8'
}
query = {
'allow_source': 'true',
'allow_audio_only': 'true',
'allow_spectre': 'true',
'p': random.randint(1000000, 10000000),
'player': 'twitchweb',
'playlist_include_framerate': 'true',
'sig': signature,
'token': token,
}
return self._extract_m3u8_formats(
URLS_MAP[type] % (self._USHER_BASE, id), id, 'mp4', query=query)
def _extract_twitch_m3u8_formats(self, video_id, token, signature):
"""Subclasses must define _M3U8_PATH"""
return self._extract_m3u8_formats(
f'{self._USHER_BASE}/{self._M3U8_PATH}/{video_id}.m3u8', video_id, 'mp4', query={
'allow_source': 'true',
'allow_audio_only': 'true',
'allow_spectre': 'true',
'p': random.randint(1000000, 10000000),
'player': 'twitchweb',
'playlist_include_framerate': 'true',
'sig': signature,
'token': token,
})

and then in the respective concrete IE classes:

    _M3U8_PATH = 'vod'
    _M3U8_PATH = 'api/channel/hls'

(and remove the 'video' and 'stream' args from the method calls)

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why not just pass the m3u8 path itself as an argument? Each case is only used once

Copy link
Member

@bashonly bashonly Jan 10, 2024 •
edited

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

e8715c2 (#8968)



class TwitchVodIE(TwitchBaseIE):
IE_NAME = 'twitch:vod'
Expand Down Expand Up @@ -532,20 +549,8 @@ def _real_extract(self, url):
info = self._extract_info_gql(video, vod_id)
access_token = self._download_access_token(vod_id, 'video', 'id')

formats = self._extract_m3u8_formats(
'%s/vod/%s.m3u8?%s' % (
self._USHER_BASE, vod_id,
compat_urllib_parse_urlencode({
'allow_source': 'true',
'allow_audio_only': 'true',
'allow_spectre': 'true',
'player': 'twitchweb',
'playlist_include_framerate': 'true',
'nauth': access_token['value'],
'nauthsig': access_token['signature'],
})),
vod_id, 'mp4', entry_protocol='m3u8_native')

formats = self._extract_twitch_m3u8_formats(
'video', vod_id, access_token['value'], access_token['signature'])
formats.extend(self._extract_storyboard(vod_id, video.get('storyboard'), info.get('duration')))

self._prefer_source(formats)
Expand Down Expand Up @@ -1026,23 +1031,10 @@ def _real_extract(self, url):

access_token = self._download_access_token(
channel_name, 'stream', 'channelName')
token = access_token['value']

stream_id = stream.get('id') or channel_name
query = {
'allow_source': 'true',
'allow_audio_only': 'true',
'allow_spectre': 'true',
'p': random.randint(1000000, 10000000),
'player': 'twitchweb',
'playlist_include_framerate': 'true',
'segment_preference': '4',
'sig': access_token['signature'].encode('utf-8'),
'token': token.encode('utf-8'),
}
formats = self._extract_m3u8_formats(
'%s/api/channel/hls/%s.m3u8' % (self._USHER_BASE, channel_name),
stream_id, 'mp4', query=query)
formats = self._extract_twitch_m3u8_formats(
'stream', channel_name, access_token['value'], access_token['signature'])
self._prefer_source(formats)

view_count = stream.get('viewers')
Expand Down