PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-09 11:42:30 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[bilibili] fix support of partitions (close #688)

Browse Source 
- Download only one partition by default
- Support playlist (for downloading all partitions without merging)
This commit is contained in:
Mort Yao 2015-10-17 01:10:10 +02:00
parent 1994198b65
commit 86cb42ba48
1 changed files with 41 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -89,9 +89,9 @@ def bilibili_download_by_cids(cids, title, output_dir='.', merge=True, info_only
if not info_only: if not info_only:
download_urls(urls, title, type_, total_size=None, output_dir=output_dir, merge=merge) download_urls(urls, title, type_, total_size=None, output_dir=output_dir, merge=merge)
def bilibili_download_by_cid(id, title, output_dir='.', merge=True, info_only=False): def bilibili_download_by_cid(cid, title, output_dir='.', merge=True, info_only=False):
sign_this = hashlib.md5(bytes('appkey=' + appkey + '&cid=' + id + secretkey, 'utf-8')).hexdigest() sign_this = hashlib.md5(bytes('appkey=' + appkey + '&cid=' + cid + secretkey, 'utf-8')).hexdigest()
url = 'http://interface.bilibili.com/playurl?appkey=' + appkey + '&cid=' + id + '&sign=' + sign_this url = 'http://interface.bilibili.com/playurl?appkey=' + appkey + '&cid=' + cid + '&sign=' + sign_this
urls = [i urls = [i
if not re.match(r'.*\.qqvideo\.tc\.qq\.com', i) if not re.match(r'.*\.qqvideo\.tc\.qq\.com', i)
else re.sub(r'.*\.qqvideo\.tc\.qq\.com', 'http://vsrc.store.qq.com', i) else re.sub(r'.*\.qqvideo\.tc\.qq\.com', 'http://vsrc.store.qq.com', i)
@ -110,46 +110,66 @@ def bilibili_download_by_cid(id, title, output_dir='.', merge=True, info_only=Fa
def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs): def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
html = get_html(url) html = get_html(url)
title = r1_of([r'<meta name="title" content="([^<>]{1,999})" />',r'<h1[^>]*>([^<>]+)</h1>'], html) title = r1_of([r'<meta name="description" content="(.+)"',
r'<meta name="title" content="([^<>]{1,999})" />',
r'<h1[^>]*>([^<>]+)</h1>'], html)
title = title.split('\r')[0]
title = unescape_html(title) title = unescape_html(title)
title = escape_file_path(title) title = escape_file_path(title)
flashvars = r1_of([r'(cid=\d+)', r'(cid: \d+)', r'flashvars="([^"]+)"', r'"https://[a-z]+\.bilibili\.com/secure,(cid=\d+)(?:&aid=\d+)?"'], html) flashvars = r1_of([r'(cid=\d+)', r'(cid: \d+)', r'flashvars="([^"]+)"', r'"https://[a-z]+\.bilibili\.com/secure,(cid=\d+)(?:&aid=\d+)?"'], html)
assert flashvars assert flashvars
flashvars = flashvars.replace(': ','=') flashvars = flashvars.replace(': ','=')
t, id = flashvars.split('=', 1) t, cid = flashvars.split('=', 1)
id = id.split('&')[0] cid = cid.split('&')[0]
if t == 'cid': if t == 'cid':
# Multi-P if 'playlist' in kwargs and kwargs['playlist']:
cids = [id] # multi-P
p = re.findall('<option value=\'([^\']*)\'>', html) cids = []
if not p: pages = re.findall('<option value=\'([^\']*)\'', html)
bilibili_download_by_cid(id, title, output_dir=output_dir, merge=merge, info_only=info_only) titles = re.findall('<option value=.*>(.+)</option>', html)
else: for page in pages:
for i in p: html = get_html("http://www.bilibili.com%s" % page)
html = get_html("http://www.bilibili.com%s" % i) flashvars = r1_of([r'(cid=\d+)',
flashvars = r1_of([r'(cid=\d+)', r'flashvars="([^"]+)"', r'"https://[a-z]+\.bilibili\.com/secure,(cid=\d+)(?:&aid=\d+)?"'], html) r'flashvars="([^"]+)"',
r'"https://[a-z]+\.bilibili\.com/secure,(cid=\d+)(?:&aid=\d+)?"'], html)
if flashvars: if flashvars:
t, cid = flashvars.split('=', 1) t, cid = flashvars.split('=', 1)
cids.append(cid.split('&')[0]) cids.append(cid.split('&')[0])
bilibili_download_by_cids(cids, title, output_dir=output_dir, merge=merge, info_only=info_only) for i in range(len(cids)):
bilibili_download_by_cid(cids[i],
titles[i],
output_dir=output_dir,
merge=merge,
info_only=info_only)
else:
title = r1(r'<option value=.* selected>(.+)</option>', html) or title
bilibili_download_by_cid(cid, title, output_dir=output_dir, merge=merge, info_only=info_only)
elif t == 'vid': elif t == 'vid':
sina_download_by_vid(id, title, output_dir = output_dir, merge = merge, info_only = info_only) sina_download_by_vid(cid, title=title, output_dir=output_dir, merge=merge, info_only=info_only)
elif t == 'ykid': elif t == 'ykid':
youku_download_by_vid(id, title=title, output_dir = output_dir, merge = merge, info_only = info_only) youku_download_by_vid(cid, title=title, output_dir=output_dir, merge=merge, info_only=info_only)
elif t == 'uid': elif t == 'uid':
tudou_download_by_id(id, title, output_dir = output_dir, merge = merge, info_only = info_only) tudou_download_by_id(cid, title, output_dir=output_dir, merge=merge, info_only=info_only)
else: else:
raise NotImplementedError(flashvars) raise NotImplementedError(flashvars)
if not info_only and not dry_run: if not info_only and not dry_run:
title = get_filename(title) title = get_filename(title)
print('Downloading %s ...\n' % (title + '.cmt.xml')) print('Downloading %s ...\n' % (title + '.cmt.xml'))
xml = get_srt_xml(id) xml = get_srt_xml(cid)
with open(os.path.join(output_dir, title + '.cmt.xml'), 'w', encoding='utf-8') as x: with open(os.path.join(output_dir, title + '.cmt.xml'), 'w', encoding='utf-8') as x:
x.write(xml) x.write(xml)
def bilibili_download_playlist(url, output_dir='.', merge=True, info_only=False, **kwargs):
bilibili_download(url,
output_dir=output_dir,
merge=merge,
info_only=info_only,
playlist=True,
**kwargs)
site_info = "bilibili.com" site_info = "bilibili.com"
download = bilibili_download download = bilibili_download
download_playlist = playlist_not_supported('bilibili') download_playlist = bilibili_download_playlist