Skip to content

Update bilibili.py #3005

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jpppppppppppppppppppppppp wants to merge 1 commit into
base: develop
Choose a base branch
from
+32 −47
Open

Update bilibili.py #3005

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
79 changes: 32 additions & 47 deletions src/you_get/extractors/bilibili.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@

class Bilibili(VideoExtractor):
name = "Bilibili"

epid = ""
# Bilibili media encoding options, in descending quality order.
stream_types = [
{'id': 'hdflv2_8k', 'quality': 127, 'audio_quality': 30280,
Expand Down Expand Up @@ -42,8 +42,6 @@ class Bilibili(VideoExtractor):
{'id': 'jpg', 'quality': 0},
]

codecids = {7: 'AVC', 12: 'HEVC', 13: 'AV1'}

@staticmethod
def height_to_quality(height, qn):
if height <= 360 and qn <= 16:
Expand Down Expand Up @@ -72,7 +70,7 @@ def bilibili_headers(referer=None, cookie=None):

@staticmethod
def bilibili_api(avid, cid, qn=0):
return 'https://api.bilibili.com/x/player/playurl?avid=%s&cid=%s&qn=%s&type=&otype=json&fnver=0&fnval=4048&fourk=1' % (avid, cid, qn)
return 'https://api.bilibili.com/x/player/playurl?avid=%s&cid=%s&qn=%s&type=&otype=json&fnver=0&fnval=16&fourk=1' % (avid, cid, qn)

@staticmethod
def bilibili_audio_api(sid):
Expand Down Expand Up @@ -117,15 +115,15 @@ def bilibili_live_room_init_api(room_id):
@staticmethod
def bilibili_space_channel_api(mid, cid, pn=1, ps=100):
return 'https://api.bilibili.com/x/space/channel/video?mid=%s&cid=%s&pn=%s&ps=%s&order=0&jsonp=jsonp' % (mid, cid, pn, ps)

@staticmethod
def bilibili_space_collection_api(mid, cid, pn=1, ps=30):
return 'https://api.bilibili.com/x/polymer/space/seasons_archives_list?mid=%s&season_id=%s&sort_reverse=false&page_num=%s&page_size=%s' % (mid, cid, pn, ps)

@staticmethod
def bilibili_series_archives_api(mid, sid, pn=1, ps=100):
return 'https://api.bilibili.com/x/series/archives?mid=%s&series_id=%s&pn=%s&ps=%s&only_normal=true&sort=asc&jsonp=jsonp' % (mid, sid, pn, ps)

@staticmethod
def bilibili_space_favlist_api(fid, pn=1, ps=20):
return 'https://api.bilibili.com/x/v3/fav/resource/list?media_id=%s&pn=%s&ps=%s&order=mtime&type=0&tid=0&jsonp=jsonp' % (fid, pn, ps)
Expand Down Expand Up @@ -172,9 +170,9 @@ def prepare(self, **kwargs):
# redirect: bangumi.bilibili.com/anime -> bangumi/play/ep
elif re.match(r'https?://(www\.)?bilibili\.com/bangumi/play/ss(\d+)', self.url) or \
re.match(r'https?://bangumi\.bilibili\.com/anime/(\d+)/play', self.url):
initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME
initial_state_text = '{' + match1(html_content, r'("initEpList":.*?),"initSections"') + '}' # FIXME
initial_state = json.loads(initial_state_text)
ep_id = initial_state['epList'][0]['id']
ep_id = initial_state['initEpList'][0]['id']
self.url = 'https://www.bilibili.com/bangumi/play/ep%s' % ep_id
html_content = get_content(self.url, headers=self.bilibili_headers(referer=self.url))

Expand All @@ -193,6 +191,7 @@ def prepare(self, **kwargs):
sort = 'audio'
elif re.match(r'https?://(www\.)?bilibili\.com/bangumi/play/ep(\d+)', self.url):
sort = 'bangumi'
self.epid = re.findall(r'https?://(www\.)?bilibili\.com/bangumi/play/ep(\d+)', self.url)[0][1]
elif match1(html_content, r'<meta property="og:url" content="(https://www.bilibili.com/bangumi/play/[^"]+)"'):
sort = 'bangumi'
elif re.match(r'https?://live\.bilibili\.com/', self.url):
Expand Down Expand Up @@ -224,10 +223,6 @@ def prepare(self, **kwargs):
if 'videoData' in initial_state:
# (standard video)

# warn if cookies are not loaded
if cookies is None:
log.w('You will need login cookies for 720p formats or above. (use --cookies to load cookies.txt.)')

# warn if it is a multi-part video
pn = initial_state['videoData']['videos']
if pn > 1 and not kwargs.get('playlist'):
Expand Down Expand Up @@ -308,10 +303,11 @@ def prepare(self, **kwargs):
if 'dash' in playinfo['data']:
audio_size_cache = {}
for video in playinfo['data']['dash']['video']:
# prefer the latter codecs!
s = self.stream_qualities[video['id']]
format_id = f"dash-{s['id']}-{self.codecids[video['codecid']]}" # prefix
format_id = 'dash-' + s['id'] # prefix
container = 'mp4' # enforce MP4 container
desc = s['desc'] + ' ' + video['codecs']
desc = s['desc']
audio_quality = s['audio_quality']
baseurl = video['baseUrl']
size = self.url_size(baseurl, headers=self.bilibili_headers(referer=self.url))
Expand All @@ -338,21 +334,24 @@ def prepare(self, **kwargs):

# bangumi
elif sort == 'bangumi':
initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME
initial_state_text = '{' + match1(html_content, r'("initEpList":.*?),"initSections"') + '}'
initial_state = json.loads(initial_state_text)

# warn if this bangumi has more than 1 video
epn = len(initial_state['epList'])
epn = len(initial_state['initEpList'])
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 %d videos. (use --playlist to download all videos.)' % epn)

# set video title
self.title = initial_state['h1Title']
for i in range(epn):
if int(initial_state['initEpList'][i]['id']) == int(self.epid):
break
self.title = initial_state['initEpList'][i]['share_copy']

# construct playinfos
ep_id = initial_state['epInfo']['id']
avid = initial_state['epInfo']['aid']
cid = initial_state['epInfo']['cid']
ep_id = self.epid
avid = initial_state['initEpList'][i]['aid']
cid = initial_state['initEpList'][i]['cid']
playinfos = []
api_url = self.bilibili_bangumi_api(avid, cid, ep_id)
api_content = get_content(api_url, headers=self.bilibili_headers(referer=self.url))
Expand Down Expand Up @@ -752,41 +751,27 @@ def download_playlist_by_url(self, url, **kwargs):
elif sort == 'space_channel_series':
m = re.match(r'https?://space\.?bilibili\.com/(\d+)/channel/seriesdetail\?.*sid=(\d+)', self.url)
mid, sid = m.group(1), m.group(2)
pn = 1
video_list = []
while True:
api_url = self.bilibili_series_archives_api(mid, sid, pn)
api_content = get_content(api_url, headers=self.bilibili_headers(referer=self.url))
archives_info = json.loads(api_content)
video_list.extend(archives_info['data']['archives'])
if len(video_list) < archives_info['data']['page']['total'] and len(archives_info['data']['archives']) > 0:
pn += 1
else:
break
api_url = self.bilibili_series_archives_api(mid, sid)
api_content = get_content(api_url, headers=self.bilibili_headers(referer=self.url))
archives_info = json.loads(api_content)
# TBD: channel of more than 100 videos

epn, i = len(video_list), 0
for video in video_list:
epn, i = len(archives_info['data']['archives']), 0
for video in archives_info['data']['archives']:
i += 1; log.w('Extracting %s of %s videos ...' % (i, epn))
url = 'https://www.bilibili.com/video/av%s' % video['aid']
self.__class__().download_playlist_by_url(url, **kwargs)

elif sort == 'space_channel_collection':
m = re.match(r'https?://space\.?bilibili\.com/(\d+)/channel/collectiondetail\?.*sid=(\d+)', self.url)
mid, sid = m.group(1), m.group(2)
pn = 1
video_list = []
while True:
api_url = self.bilibili_space_collection_api(mid, sid, pn)
api_content = get_content(api_url, headers=self.bilibili_headers(referer=self.url))
archives_info = json.loads(api_content)
video_list.extend(archives_info['data']['archives'])
if len(video_list) < archives_info['data']['page']['total'] and len(archives_info['data']['archives']) > 0:
pn += 1
else:
break
api_url = self.bilibili_space_collection_api(mid, sid)
api_content = get_content(api_url, headers=self.bilibili_headers(referer=self.url))
archives_info = json.loads(api_content)
# TBD: channel of more than 100 videos

epn, i = len(video_list), 0
for video in video_list:
epn, i = len(archives_info['data']['archives']), 0
for video in archives_info['data']['archives']:
i += 1; log.w('Extracting %s of %s videos ...' % (i, epn))
url = 'https://www.bilibili.com/video/av%s' % video['aid']
self.__class__().download_playlist_by_url(url, **kwargs)
Expand Down