mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-27 17:08:32 +00:00
Code Issues Projects Releases Wiki Activity

actual improvements

Browse Source 
Authored by: bashonly
This commit is contained in:
bashonly 2025-06-09 15:29:13 -05:00
parent 11801ca7b3
commit f98a31a32d
No known key found for this signature in database
GPG Key ID: 783F096F253D15B0
1 changed files with 11 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
yt_dlp/extractor/common.py
View File

@ -1799,18 +1799,6 @@ def _search_nuxt_json(self, webpage, video_id, *, fatal=True, default=NO_DEFAULT
"""Parses metadata from Nuxt rich JSON payload arrays"""
# Ref: https://github.com/nuxt/nuxt/commit/9e503be0f2a24f4df72a3ccab2db4d3e63511f57
# https://github.com/nuxt/nuxt/pull/19205
try:
array = self._search_json(
r'<script\b[^>]+\bid="__NUXT_DATA__"[^>]*>', webpage,
'Nuxt JSON data', video_id, contains_pattern=r'\[(?s:.+)\]')
except ExtractorError as e:
if fatal:
raise
if default is NO_DEFAULT:
self.report_warning(e.orig_msg)
return {}
return default
IGNORED_TYPES = ('Map', 'Set', 'Ref', 'ShallowRef', 'EmptyRef', 'EmptyShallowRef', 'NuxtError')
def extract_element(element):
@ -1831,22 +1819,24 @@ def extract_element(element):
return ret
return element
if default is not NO_DEFAULT:
fatal = False
array = self._search_json(
r'<script\b[^>]+\bid="__NUXT_DATA__"[^>]*>', webpage, 'Nuxt JSON data', video_id,
contains_pattern=r'\[(?s:.+)\]', default=NO_DEFAULT if fatal else [])
try:
payload = extract_element(array[0])
except IndexError as e:
error_msg = f'Unable to extract Nuxt JSON data: {e}'
return extract_element(array[0])
except IndexError:
error_msg = 'Unable to extract Nuxt JSON data'
if fatal:
raise ExtractorError(error_msg)
raise ExtractorError(error_msg, video_id=video_id)
if default is NO_DEFAULT:
self.report_warning(error_msg, video_id=video_id)
return {}
return default
if default is NO_DEFAULT:
default = {}
return payload or default
@staticmethod
def _hidden_inputs(html):
html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)