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

feat(bilibili): add support for first option

Browse Source
This commit is contained in:
Riceball LEE 2023-02-15 11:56:51 +08:00
parent 2ba7493f12
commit 2fd06a4f67
No known key found for this signature in database
GPG Key ID: 10F15E84852CB868
2 changed files with 32 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/you_get/extractor.py
View File

@ -19,6 +19,9 @@ class Extractor():
self.url = args[0] self.url = args[0]
class VideoExtractor(): class VideoExtractor():
download_count = 0
skip_count = 0
def __init__(self, *args): def __init__(self, *args):
self.url = None self.url = None
self.title = None self.title = None
@ -177,6 +180,11 @@ class VideoExtractor():
print("videos:") print("videos:")
def download(self, **kwargs): def download(self, **kwargs):
self.__class__.download_count += 1
if self.__class__.skip_count and self.__class__.download_count < self.__class__.skip_count:
log.i("skipped({}): {}".format(self.__class__.download_count, self.title))
return
if 'json_output' in kwargs and kwargs['json_output']: if 'json_output' in kwargs and kwargs['json_output']:
json_output.output(self) json_output.output(self)
elif 'info_only' in kwargs and kwargs['info_only']: elif 'info_only' in kwargs and kwargs['info_only']:

28
src/you_get/extractors/bilibili.py
View File

@ -649,6 +649,16 @@ class Bilibili(VideoExtractor):
log.e('[Error] Unsupported URL pattern.') log.e('[Error] Unsupported URL pattern.')
exit(1) exit(1)
args = kwargs.get('args')
first = 0
if ('first' in args and args.first!= None):
first = int(args.first)
if first < 0: first = 0
if sort not in ['video', 'bangumi','bangumi_md','audio_menu']:
args.first = None
if first > 0:
self.__class__.skip_count = first
# regular video # regular video
if sort == 'video': if sort == 'video':
initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME initial_state_text = match1(html_content, r'__INITIAL_STATE__=(.*?);\(function\(\)') # FIXME
@ -658,12 +668,16 @@ class Bilibili(VideoExtractor):
if pn == len(initial_state['videoData']['pages']): if pn == len(initial_state['videoData']['pages']):
# non-interative video # non-interative video
for pi in range(1, pn + 1): for pi in range(first+1, pn + 1):
purl = 'https://www.bilibili.com/video/av%s?p=%s' % (aid, pi) purl = 'https://www.bilibili.com/video/av%s?p=%s' % (aid, pi)
self.__class__().download_by_url(purl, **kwargs) self.__class__().download_by_url(purl, **kwargs)
else: else:
# interative video # interative video
if first > 0:
args.first = None
self.__class__.skip_count = first
search_node_list = [] search_node_list = []
download_cid_set = set([initial_state['videoData']['cid']]) download_cid_set = set([initial_state['videoData']['cid']])
params = { params = {
@ -720,7 +734,9 @@ class Bilibili(VideoExtractor):
initial_state = json.loads(initial_state_text) initial_state = json.loads(initial_state_text)
epn, i = len(initial_state['epList']), 0 epn, i = len(initial_state['epList']), 0
for ep in initial_state['epList']: for ep in initial_state['epList']:
i += 1; log.w('Extracting %s of %s videos ...' % (i, epn)) i += 1
if i <= first: continue
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
self.__class__().download_by_url(epurl, **kwargs) self.__class__().download_by_url(epurl, **kwargs)
@ -730,7 +746,9 @@ class Bilibili(VideoExtractor):
initial_state = json.loads(initial_state_text) initial_state = json.loads(initial_state_text)
epn, i = len(initial_state['mediaInfo']['episodes']), 0 epn, i = len(initial_state['mediaInfo']['episodes']), 0
for ep in initial_state['mediaInfo']['episodes']: for ep in initial_state['mediaInfo']['episodes']:
i += 1; log.w('Extracting %s of %s videos ...' % (i, epn)) i += 1
if i <= first: continue
log.w('Extracting %s of %s videos ...' % (i, epn))
ep_id = ep['ep_id'] ep_id = ep['ep_id']
epurl = 'https://www.bilibili.com/bangumi/play/ep%s/' % ep_id epurl = 'https://www.bilibili.com/bangumi/play/ep%s/' % ep_id
self.__class__().download_by_url(epurl, **kwargs) self.__class__().download_by_url(epurl, **kwargs)
@ -843,7 +861,9 @@ class Bilibili(VideoExtractor):
menusong_info = json.loads(api_content) menusong_info = json.loads(api_content)
epn, i = len(menusong_info['data']['data']), 0 epn, i = len(menusong_info['data']['data']), 0
for song in menusong_info['data']['data']: for song in menusong_info['data']['data']:
i += 1; log.w('Extracting %s of %s songs ...' % (i, epn)) i += 1
if i <= first: continue
log.w('Extracting %s of %s songs ...' % (i, epn))
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)