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

improvements?

Browse Source 
Authored by: bashonly
This commit is contained in:
bashonly 2025-06-09 15:15:10 -05:00
parent ce6b8db516
commit 11801ca7b3
No known key found for this signature in database
GPG Key ID: 783F096F253D15B0
2 changed files with 61 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
test/test_InfoExtractor.py
View File

@ -1979,26 +1979,25 @@ def test_search_nuxt_json(self):
["Set"]
]
</script>'''
DATA = {
'podcast': {
'podcast': {
'title': 'Series Title',
'id': 'podcast-id-01',
},
'seasons': [1, 2, 3],
},
'activeEpisodeData': {
'episode': {
'title': 'Episode Title',
'id': 'episode-id-99',
},
'creators': ['Podcast Creator'],
'empty_list': [],
},
}
FULL = {
PAYLOAD = {
'data': {
'$abcdef123456': DATA,
'$abcdef123456': {
'podcast': {
'podcast': {
'title': 'Series Title',
'id': 'podcast-id-01',
},
'seasons': [1, 2, 3],
},
'activeEpisodeData': {
'episode': {
'title': 'Episode Title',
'id': 'episode-id-99',
},
'creators': ['Podcast Creator'],
'empty_list': [],
},
},
},
'state': {
'$ssite-config': {
@ -2006,7 +2005,7 @@ def test_search_nuxt_json(self):
'name': 'podcast-website',
},
},
'once': ['Set'],
'once': None,
}
BAD_HTML = '''
<script data-ssr="true" id="__NUXT_DATA__" type="application/json">
@ -2018,8 +2017,7 @@ def test_search_nuxt_json(self):
]
</script>'''
self.assertEqual(self.ie._search_nuxt_json(HTML, None), DATA)
self.assertEqual(self.ie._search_nuxt_json(HTML, None, traverse=None), FULL)
self.assertEqual(self.ie._search_nuxt_json(HTML, 'id'), PAYLOAD)
self.assertEqual(self.ie._search_nuxt_json('', None, fatal=False), {})
self.assertEqual(self.ie._search_nuxt_json(BAD_HTML, None, fatal=False), {})

64
yt_dlp/extractor/common.py
View File

@ -1795,39 +1795,57 @@ def _search_nuxt_data(self, webpage, video_id, context_name='__NUXT__', *, fatal
ret = self._parse_json(js, video_id, transform_source=functools.partial(js_to_json, vars=args), fatal=fatal)
return traverse_obj(ret, traverse) or {}
def _search_nuxt_json(self, webpage, video_id, *, fatal=True, traverse=('data', ..., {dict}, any)):
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
array = self._search_json(
r'<script\b[^>]+\bid="__NUXT_DATA__"[^>]*>', webpage, 'nuxt data', video_id,
contains_pattern=r'\[(?s:.+)\]', default=NO_DEFAULT if fatal else [{}])
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):
try:
if isinstance(element, list) and element:
if isinstance(element, list):
if element and isinstance(element[0], str):
if element[0] in ('ShallowReactive', 'Reactive') and isinstance(element[1], int):
return extract_element(array[element[1]])
if all(isinstance(ele, int) for ele in element):
return [extract_element(array[ele]) for ele in element]
if isinstance(element, dict):
ret = {}
for k, v in element.items():
if isinstance(v, int):
ret[k] = extract_element(array[v])
else:
ret[k] = v
return ret
except IndexError as e:
error_msg = f'Unable to extract NUXT JSON data: {e}'
if not fatal:
self.report_warning(error_msg, video_id=video_id, only_once=True)
if element[0] not in IGNORED_TYPES:
self.write_debug(
f'{video_id}: Discarding unsupported type in Nuxt payload: {element[0]}',
only_once=True)
return None
raise ExtractorError(error_msg)
return [extract_element(array[ele]) for ele in element]
if isinstance(element, dict):
ret = {}
for k, v in element.items():
ret[k] = extract_element(array[v])
return ret
return element
return traverse_obj(extract_element(array[0]), traverse) or {}
try:
payload = extract_element(array[0])
except IndexError as e:
error_msg = f'Unable to extract Nuxt JSON data: {e}'
if fatal:
raise ExtractorError(error_msg)
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):