PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-03-13 11:24:02 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

Updated bilibili extractor to support new site code parsing when using cookies

Browse Source
This commit is contained in:
Johannes Wong 2023-03-04 17:33:19 -08:00
parent 2aaa877a9b
commit 9b306bee13
1 changed files with 48 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
src/you_get/extractors/bilibili.py
View File

@ -338,21 +338,47 @@ class Bilibili(VideoExtractor):
# bangumi # bangumi
elif sort == 'bangumi': elif sort == 'bangumi':
ep_id = ""
avid = ""
cid = ""
initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME
initial_state = json.loads(initial_state_text) if (initial_state_text):
initial_state = json.loads(initial_state_text)
# warn if this bangumi has more than 1 video # warn if this bangumi has more than 1 video
epn = len(initial_state['epList']) epn = len(initial_state['epList'])
if epn > 1 and not kwargs.get('playlist'): if epn > 1 and not kwargs.get('playlist'):
log.w('This bangumi currently has %s videos. (use --playlist to download all videos.)' % epn) log.w('This bangumi currently has %s videos. (use --playlist to download all videos.)' % epn)
# set video title # set video title
self.title = initial_state['h1Title'] self.title = initial_state['h1Title']
# construct playinfos
ep_id = initial_state['epInfo']['id']
avid = initial_state['epInfo']['aid']
cid = initial_state['epInfo']['cid']
else:
initial_state_text = match1(html_content, r'\"episodes\":(.*?)\,\"user_status')
pinitial_state = json.loads(initial_state_text)
epn = len(pinitial_state)
if epn > 1 and not kwargs.get('playlist'):
log.w('This bangumi currently has %s videos. (use --playlist to download all videos.)' % epn)
initial_state = {}
for dic in pinitial_state:
if dic['link'] == self.url.rstrip('/'):
initial_state = dic
break
self.title = initial_state['share_copy']
# construct playinfos
ep_id = initial_state['id']
avid = initial_state['aid']
cid = initial_state['cid']
# construct playinfos
ep_id = initial_state['epInfo']['id']
avid = initial_state['epInfo']['aid']
cid = initial_state['epInfo']['cid']
playinfos = [] playinfos = []
api_url = self.bilibili_bangumi_api(avid, cid, ep_id) api_url = self.bilibili_bangumi_api(avid, cid, ep_id)
api_content = get_content(api_url, headers=self.bilibili_headers(referer=self.url)) api_content = get_content(api_url, headers=self.bilibili_headers(referer=self.url))
@ -716,10 +742,18 @@ class Bilibili(VideoExtractor):
self.download(**kwargs) self.download(**kwargs)
elif sort == 'bangumi': elif sort == 'bangumi':
episodes = []
initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME
initial_state = json.loads(initial_state_text) if (initial_state_text):
epn, i = len(initial_state['epList']), 0 # initial_state = json.loads(initial_state_text)
for ep in initial_state['epList']: episodes = json.loads(initial_state_text)['epList']
else:
initial_state_text = match1(html_content, r'\"episodes\":(.*?)\,\"user_status')
# initial_state = json.loads(initial_state_text)
episodes = json.loads(initial_state_text)
epn, i = len(episodes), 0
for ep in episodes:
i += 1; log.w('Extracting %s of %s videos ...' % (i, epn)) i += 1; log.w('Extracting %s of %s videos ...' % (i, epn))
ep_id = ep['id'] ep_id = ep['id']
epurl = 'https://www.bilibili.com/bangumi/play/ep%s/' % ep_id epurl = 'https://www.bilibili.com/bangumi/play/ep%s/' % ep_id