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

[Ku6]Fix baidu.ku6.com, close #1163

Browse Source 
As in #1163 .
This commit is contained in:
David Zhuang 2016-05-25 16:38:01 -04:00
parent 6938894337
commit 00d272b3d9
1 changed files with 18 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
src/you_get/extractors/ku6.py
View File

@ -7,6 +7,7 @@ from ..common import *
import json import json
import re import re
#----------------------------------------------------------------------
def ku6_download_by_id(id, title = None, output_dir = '.', merge = True, info_only = False): def ku6_download_by_id(id, title = None, output_dir = '.', merge = True, info_only = False):
data = json.loads(get_html('http://v.ku6.com/fetchVideo4Player/%s...html' % id))['data'] data = json.loads(get_html('http://v.ku6.com/fetchVideo4Player/%s...html' % id))['data']
t = data['t'] t = data['t']
@ -26,11 +27,24 @@ def ku6_download_by_id(id, title = None, output_dir = '.', merge = True, info_on
if not info_only: if not info_only:
download_urls(urls, title, ext, size, output_dir, merge = merge) download_urls(urls, title, ext, size, output_dir, merge = merge)
#----------------------------------------------------------------------
def ku6_baidu_get_id(url):
"""str->str"""
baidu_id = match1(url, r'http://baidu.ku6.com/watch/(\d+).+')
inner_url = 'http://v.baidu.com/watch/{baidu_id}.html'.format(baidu_id = baidu_id)
html = get_content(inner_url)
ku6_id = match1(html, r'http%3A%2F%2Fv.ku6.com%2Fshow%2F(.*)\.\.\.html')
return ku6_id
#----------------------------------------------------------------------
def ku6_download(url, output_dir = '.', merge = True, info_only = False, **kwargs): def ku6_download(url, output_dir = '.', merge = True, info_only = False, **kwargs):
patterns = [r'http://v.ku6.com/special/show_\d+/(.*)\.\.\.html', if 'baidu.ku6' in url:
r'http://v.ku6.com/show/(.*)\.\.\.html', id = ku6_baidu_get_id(url)
r'http://my.ku6.com/watch\?.*v=(.*)\.\..*'] else:
id = r1_of(patterns, url) patterns = [r'http://v.ku6.com/special/show_\d+/(.*)\.\.\.html',
r'http://v.ku6.com/show/(.*)\.\.\.html',
r'http://my.ku6.com/watch\?.*v=(.*)\.\..*']
id = r1_of(patterns, url)
ku6_download_by_id(id, output_dir = output_dir, merge = merge, info_only = info_only) ku6_download_by_id(id, output_dir = output_dir, merge = merge, info_only = info_only)