PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-01-24 05:55:02 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[Bilibili] download specified P according to the link

Browse Source
This commit is contained in:
Yi Zhi 2016-06-05 10:39:03 +08:00
parent c000bd4fad
commit b05fa57a36
1 changed files with 21 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -11,12 +11,14 @@ from .youku import youku_download_by_vid
import hashlib import hashlib
import re import re
appkey='f3bb208b3d081dc8' appkey = 'f3bb208b3d081dc8'
def get_srt_xml(id): def get_srt_xml(id):
url = 'http://comment.bilibili.com/%s.xml' % id url = 'http://comment.bilibili.com/%s.xml' % id
return get_html(url) return get_html(url)
def parse_srt_p(p): def parse_srt_p(p):
fields = p.split(',') fields = p.split(',')
assert len(fields) == 8, fields assert len(fields) == 8, fields
@ -44,12 +46,14 @@ def parse_srt_p(p):
return pool, mode, font_size, font_color return pool, mode, font_size, font_color
def parse_srt_xml(xml): def parse_srt_xml(xml):
d = re.findall(r'<d p="([^"]+)">(.*)</d>', xml) d = re.findall(r'<d p="([^"]+)">(.*)</d>', xml)
for x, y in d: for x, y in d:
p = parse_srt_p(x) p = parse_srt_p(x)
raise NotImplementedError() raise NotImplementedError()
def parse_cid_playurl(xml): def parse_cid_playurl(xml):
from xml.dom.minidom import parseString from xml.dom.minidom import parseString
try: try:
@ -59,14 +63,15 @@ def parse_cid_playurl(xml):
except: except:
return [] return []
def bilibili_download_by_cids(cids, title, output_dir='.', merge=True, info_only=False): def bilibili_download_by_cids(cids, title, output_dir='.', merge=True, info_only=False):
urls = [] urls = []
for cid in cids: for cid in cids:
url = 'http://interface.bilibili.com/playurl?appkey=' + appkey + '&cid=' + cid url = 'http://interface.bilibili.com/playurl?appkey=' + appkey + '&cid=' + cid
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)
for i in parse_cid_playurl(get_content(url))] for i in parse_cid_playurl(get_content(url))]
type_ = '' type_ = ''
size = 0 size = 0
@ -78,6 +83,7 @@ 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(cid, title, output_dir='.', merge=True, info_only=False): def bilibili_download_by_cid(cid, title, output_dir='.', merge=True, info_only=False):
url = 'http://interface.bilibili.com/playurl?appkey=' + appkey + '&cid=' + cid url = 'http://interface.bilibili.com/playurl?appkey=' + appkey + '&cid=' + cid
urls = [i urls = [i
@ -98,6 +104,7 @@ def bilibili_download_by_cid(cid, title, output_dir='.', merge=True, info_only=F
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_live_download_by_cid(cid, title, output_dir='.', merge=True, info_only=False): def bilibili_live_download_by_cid(cid, title, output_dir='.', merge=True, info_only=False):
api_url = 'http://live.bilibili.com/api/playurl?cid=' + cid api_url = 'http://live.bilibili.com/api/playurl?cid=' + cid
urls = parse_cid_playurl(get_content(api_url)) urls = parse_cid_playurl(get_content(api_url))
@ -109,6 +116,7 @@ def bilibili_live_download_by_cid(cid, title, output_dir='.', merge=True, info_o
if not info_only: if not info_only:
download_urls([url], title, type_, total_size=None, output_dir=output_dir, merge=merge) download_urls([url], title, type_, total_size=None, output_dir=output_dir, merge=merge)
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_content(url) html = get_content(url)
@ -118,9 +126,10 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
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, cid = flashvars.split('=', 1) t, cid = flashvars.split('=', 1)
cid = cid.split('&')[0] cid = cid.split('&')[0]
if t == 'cid': if t == 'cid':
@ -133,7 +142,7 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
cids = [] cids = []
pages = re.findall('<option value=\'([^\']*)\'', html) pages = re.findall('<option value=\'([^\']*)\'', html)
titles = re.findall('<option value=.*>(.+)</option>', html) titles = re.findall('<option value=.*>(.+)</option>', html)
for page in pages: for i, page in enumerate(pages):
html = get_html("http://www.bilibili.com%s" % page) html = get_html("http://www.bilibili.com%s" % page)
flashvars = r1_of([r'(cid=\d+)', flashvars = r1_of([r'(cid=\d+)',
r'flashvars="([^"]+)"', r'flashvars="([^"]+)"',
@ -141,6 +150,10 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
if flashvars: if flashvars:
t, cid = flashvars.split('=', 1) t, cid = flashvars.split('=', 1)
cids.append(cid.split('&')[0]) cids.append(cid.split('&')[0])
if url.endswith(page):
cids = [cid.split('&')[0]]
titles = [titles[i]]
break
# no multi-P # no multi-P
if not pages: if not pages:
@ -173,6 +186,7 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
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)
site_info = "bilibili.com" site_info = "bilibili.com"
download = bilibili_download download = bilibili_download
download_playlist = bilibili_download download_playlist = bilibili_download