mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-07-29 00:28:29 +00:00
Code Issues Projects Releases Wiki Activity

refactor

Browse Source 
Authored by: bashonly
This commit is contained in:
bashonly 2025-07-12 03:27:00 -05:00
parent e2f25c0588
commit f383c0b600
No known key found for this signature in database
GPG Key ID: 783F096F253D15B0
1 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
yt_dlp/extractor/common.py
View File

@ -1798,7 +1798,7 @@ def flatten(flight_data):
if not isinstance(data, dict): if not isinstance(data, dict):
return return
children = data.pop('children', None) children = data.pop('children', None)
if data and isinstance(name, str) and name[:1] == '$': if data and isinstance(name, str) and name.startswith('$'):
# It is useful hydration JSON data # It is useful hydration JSON data
nextjs_data.append(data) nextjs_data.append(data)
flatten(children) flatten(children)
@ -1806,6 +1806,7 @@ def flatten(flight_data):
for f in flight_data: for f in flight_data:
flatten(f) flatten(f)
flight_text = ''
# The flight segments regex pattern can afford to be (and should be) strict # The flight segments regex pattern can afford to be (and should be) strict
# Ref: https://github.com/vercel/next.js/commit/5a4a08fdce91a038f2ed3a70568d3ed040403150 # Ref: https://github.com/vercel/next.js/commit/5a4a08fdce91a038f2ed3a70568d3ed040403150
# /packages/next/src/server/app-render/use-flight-response.tsx # /packages/next/src/server/app-render/use-flight-response.tsx
@ -1830,10 +1831,14 @@ def flatten(flight_data):
elif payload_type != 1: elif payload_type != 1:
# Ignore useless payload types (0: bootstrap, 2: form state) # Ignore useless payload types (0: bootstrap, 2: form state)
continue continue
# Not all chunks are complete JSON data; this should always be non-fatal flight_text += chunk
flatten(self._search_json(
r'^[\da-f]+:', chunk, 'flight data', video_id, for f in flight_text.splitlines():
default=None, contains_pattern=r'\[.+\]')) prefix, _, body = f.partition(':')
if not (body.startswith('[') and body.endswith(']') and re.fullmatch(r'[0-9a-f]{1,3}', prefix)):
continue
# The body isn't necessarily valid JSON; this should always be non-fatal
flatten(self._parse_json(body, video_id, fatal=False, errnote=False))
return nextjs_data return nextjs_data