PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-03 00:33:58 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

change how page count is calculated

Browse Source 
skip invalid video
This commit is contained in:
p 2020-11-21 02:32:47 -05:00
parent 6f9cd8a069
commit cbeb9d5b5f
1 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/you_get/extractors/bilibili.py
View File

@ -710,12 +710,11 @@ class Bilibili(VideoExtractor):
elif sort == 'space_favlist': elif sort == 'space_favlist':
m = re.match(r'https?://space\.?bilibili\.com/(\d+)/favlist\?.*fid=(\d+)', self.url) m = re.match(r'https?://space\.?bilibili\.com/(\d+)/favlist\?.*fid=(\d+)', self.url)
vmid, fid = m.group(1), m.group(2) vmid, fid = m.group(1), m.group(2)
api_url = self.bilibili_space_favlist_api(fid) page_size=20
api_url = self.bilibili_space_favlist_api(fid, ps=page_size)
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))
favlist_info = json.loads(api_content) favlist_info = json.loads(api_content)
pc = favlist_info['data']['info']['media_count'] // len(favlist_info['data']['medias']) pc = int((favlist_info['data']['info']['media_count']+page_size-1) / page_size)
if favlist_info['data']['info']['media_count'] % len(favlist_info['data']['medias']) != 0:
pc += 1
for pn in range(1, pc + 1): for pn in range(1, pc + 1):
log.w('Extracting %s of %s pages ...' % (pn, pc)) log.w('Extracting %s of %s pages ...' % (pn, pc))
api_url = self.bilibili_space_favlist_api(fid, pn=pn) api_url = self.bilibili_space_favlist_api(fid, pn=pn)
@ -725,6 +724,9 @@ class Bilibili(VideoExtractor):
epn, i = len(favlist_info['data']['medias']), 0 epn, i = len(favlist_info['data']['medias']), 0
for video in favlist_info['data']['medias']: for video in favlist_info['data']['medias']:
i += 1; log.w('Extracting %s of %s videos ...' % (i, epn)) i += 1; log.w('Extracting %s of %s videos ...' % (i, epn))
if self.is_video_invalid(video):
log.w("{}:{} is invalid, skip".format(video['id'], video['title']))
continue
url = 'https://www.bilibili.com/video/av%s' % video['id'] url = 'https://www.bilibili.com/video/av%s' % video['id']
self.__class__().download_playlist_by_url(url, **kwargs) self.__class__().download_playlist_by_url(url, **kwargs)
@ -762,6 +764,9 @@ class Bilibili(VideoExtractor):
url = 'https://www.bilibili.com/audio/au%s' % song['id'] url = 'https://www.bilibili.com/audio/au%s' % song['id']
self.__class__().download_by_url(url, **kwargs) self.__class__().download_by_url(url, **kwargs)
@staticmethod
def is_video_invalid(video_dict):
return not (video_dict["attr"] and video_dict["attr"] in (0, "0")) # assume 0 is for all valid video
site = Bilibili() site = Bilibili()
download = site.download_by_url download = site.download_by_url