PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-02 16:24:00 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[miaopai] fix weibo.com download error

Browse Source
This commit is contained in:
lniwn 2018-12-06 21:24:10 +08:00
parent 58e806d72e
commit 7dbfece21f
1 changed files with 51 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -2,9 +2,12 @@
__all__ = ['miaopai_download']
import string
import random
from ..common import *
import urllib.error
import urllib.parse
from ..util import fs
fake_headers_mobile = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
@ -20,6 +23,10 @@ def miaopai_download_by_fid(fid, output_dir = '.', merge = False, info_only = Fa
mobile_page = get_content(page_url, headers=fake_headers_mobile)
url = match1(mobile_page, r'<video id=.*?src=[\'"](.*?)[\'"]\W')
if url is None:
wb_mp = re.search(r'<script src=([\'"])(.+?wb_mp\.js)\1>', mobile_page).group(2)
return miaopai_download_by_wbmp(wb_mp, fid, output_dir=output_dir, merge=merge,
info_only=info_only, total_size=None, **kwargs)
title = match1(mobile_page, r'<title>((.|\n)+?)</title>')
if not title:
title = fid
@ -29,7 +36,47 @@ def miaopai_download_by_fid(fid, output_dir = '.', merge = False, info_only = Fa
if not info_only:
download_urls([url], title, ext, total_size=None, output_dir=output_dir, merge=merge)
#----------------------------------------------------------------------
def miaopai_download_by_wbmp(wbmp_url, fid, info_only=False, **kwargs):
headers = {}
headers.update(fake_headers_mobile)
headers['Host'] = 'imgaliyuncdn.miaopai.com'
wbmp = get_content(wbmp_url, headers=headers)
appid = re.search(r'appid:\s*?([^,]+?),', wbmp).group(1)
jsonp = re.search(r'jsonp:\s*?([\'"])(\w+?)\1', wbmp).group(2)
population = [i for i in string.ascii_lowercase] + [i for i in string.digits]
info_url = '{}?{}'.format('http://p.weibo.com/aj_media/info', parse.urlencode({
'appid': appid.strip(),
'fid': fid,
jsonp.strip(): '_jsonp' + ''.join(random.sample(population, 11))
}))
headers['Host'] = 'p.weibo.com'
jsonp_text = get_content(info_url, headers=headers)
jsonp_dict = json.loads(match1(jsonp_text, r'\(({.+})\)'))
if jsonp_dict['code'] != 200:
log.wtf('[Failed] "%s"' % jsonp_dict['msg'])
video_url = jsonp_dict['data']['meta_data'][0]['play_urls']['l']
title = jsonp_dict['data']['description']
title = title.replace('\n', '_')
ext = 'mp4'
headers['Host'] = 'f.us.sinaimg.cn'
print_info(site_info, title, ext, url_info(video_url, headers=headers)[2])
if not info_only:
download_urls([video_url], fs.legitimize(title), ext, headers=headers, **kwargs)
def miaopai_download_direct(url, info_only, **kwargs):
mobile_page = get_content(url, headers=fake_headers_mobile)
title = re.search(r'([\'"])title\1:\s*([\'"])(.+?)\2,', mobile_page).group(3)
title = title.replace('\n', '_')
stream_url = re.search(r'([\'"])stream_url\1:\s*([\'"])(.+?)\2,', mobile_page).group(3)
ext = 'mp4'
print_info(site_info, title, ext, url_info(stream_url, headers=fake_headers_mobile)[2])
if not info_only:
download_urls([stream_url], fs.legitimize(title), ext, total_size=None, headers=fake_headers_mobile, **kwargs)
# ----------------------------------------------------------------------
def miaopai_download(url, output_dir = '.', merge = False, info_only = False, **kwargs):
fid = match1(url, r'\?fid=(\d{4}:\w+)')
if fid is not None:
@ -37,6 +84,8 @@ def miaopai_download(url, output_dir = '.', merge = False, info_only = False, **
elif '/p/230444' in url:
fid = match1(url, r'/p/230444(\w+)')
miaopai_download_by_fid('1034:'+fid, output_dir, merge, info_only)
elif re.match(r'^http[s]://weibo\.com/\d+/.+', url):
miaopai_download_direct(url, info_only=info_only, output_dir=output_dir, merge=merge, **kwargs)
else:
mobile_page = get_content(url, headers = fake_headers_mobile)
hit = re.search(r'"page_url"\s*:\s*"([^"]+)"', mobile_page)
@ -46,6 +95,7 @@ def miaopai_download(url, output_dir = '.', merge = False, info_only = False, **
escaped_url = hit.group(1)
miaopai_download(urllib.parse.unquote(escaped_url), output_dir=output_dir, merge=merge, info_only=info_only, **kwargs)
site_info = "miaopai"
download = miaopai_download
download_playlist = playlist_not_supported('miaopai')