Supported more params

This commit is contained in:
grqx_wsl 2024-06-29 20:05:53 +12:00
parent 41bb0c6b37
commit 72fac58401
2 changed files with 43 additions and 13 deletions

View File

@ -174,7 +174,9 @@ # Supported sites
- **BilibiliFavoritesList**
- **BiliBiliPlayer**
- **BilibiliPlaylist**
- **BiliBiliSearchAll**: Bilibili all search; "bilisearchall:" prefix
- **BiliBiliSearch**: Bilibili video search; "bilisearch:" prefix
- **BiliBiliSearchPage**
- **BilibiliSeriesList**
- **BilibiliSpaceAudio**
- **BilibiliSpaceVideo**

View File

@ -2312,7 +2312,7 @@ def _real_extract(self, url):
class BiliBiliSearchPageIE(BilibiliBaseIE):
_VALID_URL = r'https?://search\.bilibili\.com/(?P<type>all|video|bangumi|pgc|live|upuser)/?\?keyword=(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://search\.bilibili\.com/(?P<type>all|video|bangumi|pgc|live|upuser).*'
_TESTS = [{
'url': r'https://search.bilibili.com/all?keyword=yt+-+dlp+%E4%B8%8B%E8%BD%BD%E5%99%A8',
'playlist_count': 20,
@ -2321,20 +2321,33 @@ class BiliBiliSearchPageIE(BilibiliBaseIE):
'title': 'yt - dlp 下载器',
},
}, {
'url': r'https://search.bilibili.com/bangumi?keyword=%E5%AD%A4%E7%8B%AC%E6%91%87%E6%BB%9A&from_source=webtop_search&spm_id_from=333.1007&search_source=5',
'url': r'https://search.bilibili.com/bangumi/?keyword=%E5%AD%A4%E7%8B%AC%E6%91%87%E6%BB%9A&from_source=webtop_search&spm_id_from=333.1007&search_source=5',
'playlist_mincount': 1,
'info_dict': {
'id': '孤独摇滚',
'title': '孤独摇滚',
},
'skip': 'geo-restricted',
}, {
'url': r'https://search.bilibili.com/video?keyword=%E8%AE%A9%E5%AD%90%E5%BC%B9%E9%A3%9E&from_source=webtop_search&spm_id_from=333.1007&search_source=5&order=dm&duration=4&tids=181&page=3&o=72',
'playlist_mincount': 5,
'info_dict': {
'id': '让子弹飞',
'title': '让子弹飞',
},
}]
def _real_extract(self, url):
headers = self.geo_verification_headers()
entries = []
params = parse_qs(url)
query = {}
if not self._get_cookies('https://api.bilibili.com').get('buvid3'):
self._set_cookie('.bilibili.com', 'buvid3', f'{uuid.uuid4()}infoc')
search_type, raw_playlist_id = self._match_valid_url(url).group('type', 'id')
search_type = self._match_valid_url(url).group('type')
raw_playlist_id = traverse_obj(params, ('keyword', 0))
if raw_playlist_id is None:
raise ExtractorError('Please specify the keyword to search for!', expected=True)
playlist_id = urllib.parse.unquote_plus(raw_playlist_id)
search_type_mapping = {
'video': 'video',
@ -2343,24 +2356,38 @@ def _real_extract(self, url):
'live': 'live_room',
'upuser': 'bili_user',
}
valid_params = [
'keyword',
'page',
'order',
'duration',
'tids',
'search_type',
'order_sort',
'user_type',
]
for valid_param in valid_params:
param_value = traverse_obj(params, (valid_param, 0))
if param_value is not None:
query[valid_param] = param_value
live_room_prefix = 'https://live.bilibili.com/'
bili_user_prefix = 'https://space.bilibili.com/'
if search_type == 'live' and traverse_obj(params, ('search_type', 0)) == 'live_user':
raise ExtractorError('Live users are not downloadable!', expected=True)
if search_type == 'all':
try:
search_all_result = self._download_json(
r'https://api.bilibili.com/x/web-interface/search/all/v2',
video_id=playlist_id, query={
'keyword': playlist_id,
}, headers=headers)
video_id=playlist_id, query=query, headers=headers)
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 412:
raise ExtractorError('Request is blocked by server (-412).', expected=True)
raise
status_code = search_all_result['code']
if status_code == -400:
raise ExtractorError('Invalid request (-400).', expected=True)
result_list = search_all_result['data'].get('result')
if result_list is None:
self.write_debug(f'Response: {search_all_result}')
raise ExtractorError(f'Result not found in the response ({status_code}).',
expected=True)
for result_type_dict in result_list:
@ -2378,20 +2405,21 @@ def _real_extract(self, url):
search_type_result = self._download_json(
r'https://api.bilibili.com/x/web-interface/search/type',
video_id=playlist_id, query={
'keyword': playlist_id,
'search_type': search_type_mapping[search_type],
**query, # search_type in type is overridden when specified in url params
}, headers=headers)
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 412:
raise ExtractorError('Request is blocked by server (-412).', expected=True)
raise ExtractorError('Request is blocked by server (-412).')
raise
status_code = search_type_result['code']
if status_code == -400:
raise ExtractorError('Invalid request (-400).', expected=True)
raise ExtractorError('Invalid request (-400).')
result_list = search_type_result['data'].get('result')
if result_list is None:
self.write_debug(f'Response: {search_type_result}')
raise ExtractorError(f'Result not found in the response ({status_code}).',
expected=True)
raise ExtractorError(
f'Result not found in the response ({status_code}). '
'You might want to try a VPN or a proxy server (with --proxy)', expected=True)
for result_data in result_list:
if result_data['type'] == 'video':
entries.append(self.url_result(result_data['arcurl']))