PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-11 20:52:31 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

fix #1436

Browse Source
This commit is contained in:
柯非 2016-10-20 23:48:36 +08:00
parent 95a8d1e8af
commit 0895e98265
1 changed files with 16 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
src/you_get/extractors/bilibili.py
View File

@ -121,8 +121,22 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
if re.match(r'https?://bangumi\.bilibili\.com/', url): if re.match(r'https?://bangumi\.bilibili\.com/', url):
# quick hack for bangumi URLs # quick hack for bangumi URLs
url = r1(r'"([^"]+)" class="v-av-link"', html) #url = r1(r'"([^"]+)" class="v-av-link"', html)
html = get_content(url) #html = get_content(url)
from urllib import parse
from urllib.request import Request, urlopen
import zlib
episode_id = r1(r'episode-id="(\d+)"', html)
data = parse.urlencode({'episode_id':episode_id})
r = Request('http://bangumi.bilibili.com/web_api/get_source', headers=fake_headers)
response = urlopen(r, data=data.encode('UTF-8'))
if response.headers.get('Content-Encoding') == 'gzip':
get_cid = zlib.decompress(response.read(), 16+zlib.MAX_WBITS).decode('UTF-8')
else:
get_cid = response.read().decode('UTF-8')
html += get_cid.replace('"', '').replace(':', '=')
title = r1_of([r'<meta name="title" content="\s*([^<>]{1,999})\s*" />', title = r1_of([r'<meta name="title" content="\s*([^<>]{1,999})\s*" />',
r'<h1[^>]*>\s*([^<>]+)\s*</h1>'], html) r'<h1[^>]*>\s*([^<>]+)\s*</h1>'], html)