PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-02 16:24:00 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

update bilibili.py for audio_base_url

Browse Source
This commit is contained in:
cage 2019-10-17 02:36:21 +08:00
parent da62c488cd
commit 968bfaab5a
2 changed files with 48 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.gitignore vendored
View File

@ -83,3 +83,9 @@ _*
/.idea /.idea
*.m4a *.m4a
*.DS_Store *.DS_Store
*.txt
*.zip
.vscode

67
src/you_get/extractors/bilibili.py
View File

@ -123,7 +123,7 @@ class Bilibili(VideoExtractor):
self.stream_qualities = {s['quality']: s for s in self.stream_types} self.stream_qualities = {s['quality']: s for s in self.stream_types}
try: try:
html_content = get_content(self.url, headers=self.bilibili_headers()) html_content = get_content(self.url, headers=self.bilibili_headers(referer=self.url))
except: except:
html_content = '' # live always returns 400 (why?) html_content = '' # live always returns 400 (why?)
#self.title = match1(html_content, #self.title = match1(html_content,
@ -255,17 +255,21 @@ class Bilibili(VideoExtractor):
size = self.url_size(baseurl, headers=self.bilibili_headers(referer=self.url)) size = self.url_size(baseurl, headers=self.bilibili_headers(referer=self.url))
# find matching audio track # find matching audio track
audio_baseurl = playinfo['data']['dash']['audio'][0]['baseUrl'] if playinfo['data']['dash']['audio']:
for audio in playinfo['data']['dash']['audio']: audio_baseurl = playinfo['data']['dash']['audio'][0]['baseUrl']
if int(audio['id']) == audio_quality: for audio in playinfo['data']['dash']['audio']:
audio_baseurl = audio['baseUrl'] if int(audio['id']) == audio_quality:
break audio_baseurl = audio['baseUrl']
if not audio_size_cache.get(audio_quality, False): break
audio_size_cache[audio_quality] = self.url_size(audio_baseurl, headers=self.bilibili_headers(referer=self.url)) if not audio_size_cache.get(audio_quality, False):
size += audio_size_cache[audio_quality] audio_size_cache[audio_quality] = self.url_size(audio_baseurl, headers=self.bilibili_headers(referer=self.url))
size += audio_size_cache[audio_quality]
self.dash_streams[format_id] = {'container': container, 'quality': desc, self.dash_streams[format_id] = {'container': container, 'quality': desc,
'src': [[baseurl], [audio_baseurl]], 'size': size} 'src': [[baseurl], [audio_baseurl]], 'size': size}
else:
self.dash_streams[format_id] = {'container': container, 'quality': desc,
'src': [[baseurl]], 'size': size}
# get danmaku # get danmaku
self.danmaku = get_content('http://comment.bilibili.com/%s.xml' % cid) self.danmaku = get_content('http://comment.bilibili.com/%s.xml' % cid)
@ -492,18 +496,22 @@ class Bilibili(VideoExtractor):
size = self.url_size(baseurl, headers=self.bilibili_headers(referer=self.url)) size = self.url_size(baseurl, headers=self.bilibili_headers(referer=self.url))
# find matching audio track # find matching audio track
audio_baseurl = playinfo['data']['dash']['audio'][0]['baseUrl'] if playinfo['data']['dash']['audio']:
for audio in playinfo['data']['dash']['audio']: audio_baseurl = playinfo['data']['dash']['audio'][0]['baseUrl']
if int(audio['id']) == audio_quality: for audio in playinfo['data']['dash']['audio']:
audio_baseurl = audio['baseUrl'] if int(audio['id']) == audio_quality:
break audio_baseurl = audio['baseUrl']
if not audio_size_cache.get(audio_quality, False): break
audio_size_cache[audio_quality] = self.url_size(audio_baseurl, if not audio_size_cache.get(audio_quality, False):
headers=self.bilibili_headers(referer=self.url)) audio_size_cache[audio_quality] = self.url_size(audio_baseurl,
size += audio_size_cache[audio_quality] headers=self.bilibili_headers(referer=self.url))
size += audio_size_cache[audio_quality]
self.dash_streams[format_id] = {'container': container, 'quality': desc, self.dash_streams[format_id] = {'container': container, 'quality': desc,
'src': [[baseurl], [audio_baseurl]], 'size': size} 'src': [[baseurl], [audio_baseurl]], 'size': size}
else:
self.dash_streams[format_id] = {'container': container, 'quality': desc,
'src': [[baseurl]], 'size': size}
# get danmaku # get danmaku
self.danmaku = get_content('http://comment.bilibili.com/%s.xml' % cid) self.danmaku = get_content('http://comment.bilibili.com/%s.xml' % cid)
@ -610,9 +618,18 @@ class Bilibili(VideoExtractor):
self.extract(**kwargs) self.extract(**kwargs)
self.download(**kwargs) self.download(**kwargs)
else: else:
for pi in range(1, pn + 1): playinfo_text = match1(html_content, r'__playinfo__=(.*?)</script><script>') # FIXME
purl = 'https://www.bilibili.com/video/av%s?p=%s' % (aid, pi) playinfo = json.loads(playinfo_text) if playinfo_text else None
self.__class__().download_by_url(purl, **kwargs)
html_content_ = get_content(self.url, headers=self.bilibili_headers(cookie='CURRENT_FNVAL=16'))
playinfo_text_ = match1(html_content_, r'__playinfo__=(.*?)</script><script>') # FIXME
playinfo_ = json.loads(playinfo_text_) if playinfo_text_ else None
for pi in range(pn):
self.prepare_by_cid(aid,initial_state['videoData']['pages'][pi]['cid'],'%s (P%s. %s)' % (initial_state['videoData']['title'], pi+1, initial_state['videoData']['pages'][pi]['part']),html_content,playinfo,playinfo_,url)
self.extract(**kwargs)
self.download(**kwargs)
# purl = 'https://www.bilibili.com/video/av%s?p=%s' % (aid, pi+1)
# self.__class__().download_by_url(purl, **kwargs)
elif sort == 'bangumi': elif sort == 'bangumi':
initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME