PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-03 08:43:58 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

Merge branch 'fix_weibo' of https://github.com/rosynirvana/you-get into rosynirvana-fix_weibo

Browse Source
This commit is contained in:
Mort Yao 2017-05-12 12:35:47 +02:00
commit 303922f9d4
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 24 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
src/you_get/extractors/miaopai.py
View File

@ -5,39 +5,35 @@ __all__ = ['miaopai_download']
from ..common import *
import urllib.error
def miaopai_download_by_url(url, output_dir = '.', merge = False, info_only = False, **kwargs):
def miaopai_download_by_fid(fid, output_dir = '.', merge = False, info_only = False, **kwargs):
'''Source: Android mobile'''
if re.match(r'http://video.weibo.com/show\?fid=(\d{4}:\w{32})\w*', url):
fake_headers_mobile = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Charset': 'UTF-8,*;q=0.5',
'Accept-Encoding': 'gzip,deflate,sdch',
'Accept-Language': 'en-US,en;q=0.8',
'User-Agent': 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'
}
webpage_url = re.search(r'(http://video.weibo.com/show\?fid=\d{4}:\w{32})\w*', url).group(1) + '&type=mp4' #mobile
fake_headers_mobile = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Charset': 'UTF-8,*;q=0.5',
'Accept-Encoding': 'gzip,deflate,sdch',
'Accept-Language': 'en-US,en;q=0.8',
'User-Agent': 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'
}
page_url = 'http://video.weibo.com/show?fid=' + fid + '&type=mp4'
#grab download URL
a = get_content(webpage_url, headers= fake_headers_mobile , decoded=True)
url = match1(a, r'<video id=.*?src=[\'"](.*?)[\'"]\W')
#grab title
b = get_content(webpage_url) #normal
title = match1(b, r'<meta name="description" content="([\s\S]*?)\"\W')
type_, ext, size = url_info(url)
print_info(site_info, title, type_, size)
if not info_only:
download_urls([url], title.replace('\n',''), ext, total_size=None, output_dir=output_dir, merge=merge)
mobile_page = get_content(page_url, headers=fake_headers_mobile)
url = match1(mobile_page, r'<video id=.*?src=[\'"](.*?)[\'"]\W')
title = match1(mobile_page, r'<title>([^<]+)</title>')
type_, ext, size = url_info(url)
print_info(site_info, title, type_, size)
if not info_only:
download_urls([url], title.replace('\n',''), ext, total_size=None, output_dir=output_dir, merge=merge)
#----------------------------------------------------------------------
def miaopai_download(url, output_dir = '.', merge = False, info_only = False, **kwargs):
""""""
if re.match(r'http://video.weibo.com/show\?fid=(\d{4}:\w{32})\w*', url):
miaopai_download_by_url(url, output_dir, merge, info_only)
elif re.match(r'http://weibo.com/p/230444\w+', url):
_fid = match1(url, r'http://weibo.com/p/230444(\w+)')
miaopai_download_by_url('http://video.weibo.com/show?fid=1034:{_fid}'.format(_fid = _fid), output_dir, merge, info_only)
fid = match1(url, r'\?fid=(\d{4}:\w{32})')
if fid is not None:
miaopai_download_by_fid(fid, output_dir, merge, info_only)
elif '/p/230444' in url:
fid = match1(url, r'/p/230444(\w+)')
miaopai_download_by_fid('1034:'+fid, output_dir, merge, info_only)
else:
raise Exception('Unknown pattern')
site_info = "miaopai"
download = miaopai_download