This commit is contained in:
Synarp 2024-11-18 18:00:25 +01:00 committed by GitHub
commit b51a8f3f2f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -78,7 +78,7 @@ def _parse_stream(self, stream, url):
return info return info
def _fetch_page(self, display_id, url, params, page): def _fetch_page(self, display_id, url, params, metapage_nr, page):
page += 1 page += 1
page_params = { page_params = {
'no_totals': True, 'no_totals': True,
@ -86,8 +86,12 @@ def _fetch_page(self, display_id, url, params, page):
'page_size': self._PAGE_SIZE, 'page_size': self._PAGE_SIZE,
**params, **params,
} }
if metapage_nr == 0:
resource = f'page {page}'
else:
resource = f'page {metapage_nr+1}_{page}'
result = self._call_api_proxy( result = self._call_api_proxy(
'claim_search', display_id, page_params, f'page {page}') 'claim_search', display_id, page_params, resource)
for item in traverse_obj(result, ('items', lambda _, v: v['name'] and v['claim_id'])): for item in traverse_obj(result, ('items', lambda _, v: v['name'] and v['claim_id'])):
yield { yield {
**self._parse_stream(item, url), **self._parse_stream(item, url),
@ -96,6 +100,32 @@ def _fetch_page(self, display_id, url, params, page):
'url': self._permanent_url(url, item['name'], item['claim_id']), 'url': self._permanent_url(url, item['name'], item['claim_id']),
} }
def _metapage_entries(self, display_id, url, params):
if 'release_time' in params:
raise ExtractorError('release_time isn\'t allowed because _metapage_entires needs to specify it.')
if not ('order_by' in params and params['order_by'] == ['release_time']):
raise ExtractorError('videos must be sorted by release_time for _metapage_entries to work.')
last_metapage = []
metapage = OnDemandPagedList(
functools.partial(self._fetch_page, display_id, url, params, 0),
self._PAGE_SIZE).getslice()
metapage_nr = 1
while len(metapage) > 0:
yield from metapage
next_metapage_params = {
**params,
'release_time': '<={}'.format(metapage[-1]['release_timestamp']),
}
last_metapage = metapage
metapage = OnDemandPagedList(
functools.partial(self._fetch_page, display_id, url, next_metapage_params, metapage_nr),
self._PAGE_SIZE).getslice()
metapage = [x for x in metapage if x not in last_metapage]
metapage_nr += 1
def _playlist_entries(self, url, display_id, claim_param, metadata): def _playlist_entries(self, url, display_id, claim_param, metadata):
qs = parse_qs(url) qs = parse_qs(url)
content = qs.get('content', [None])[0] content = qs.get('content', [None])[0]
@ -123,9 +153,13 @@ def _playlist_entries(self, url, display_id, claim_param, metadata):
languages.append('none') languages.append('none')
params['any_languages'] = languages params['any_languages'] = languages
entries = OnDemandPagedList( if qs.get('order', ['new'])[0] == 'new':
functools.partial(self._fetch_page, display_id, url, params), entries = self._metapage_entries(display_id, url, params)
self._PAGE_SIZE) else:
self.report_warning('Extraction is limited to 1000 Videos when not sorting by newest.')
entries = OnDemandPagedList(
functools.partial(self._fetch_page, display_id, url, params, 0),
self._PAGE_SIZE)
return self.playlist_result( return self.playlist_result(
entries, display_id, **traverse_obj(metadata, ('value', { entries, display_id, **traverse_obj(metadata, ('value', {