PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-11 12:42:29 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

Solve HTTP redirect

Browse Source 
Hot fix this problem
This commit is contained in:
cnbeining 2015-09-11 03:24:31 -04:00
parent 100d1c5b75
commit 3503eb12da
1 changed files with 26 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
src/you_get/extractors/tv66wz.py
View File

@ -5,6 +5,28 @@ __all__ = ['tv66wz_download']
from ..common import * from ..common import *
import re import re
import urllib.parse as urlparse
import http.client as httplib
#----------------------------------------------------------------------
def resolve_http_redirect(url, depth=0):
"""http://www.zacwitte.com/resolving-http-redirects-in-python
"""
if depth > 10:
raise Exception("Redirected "+depth+" times, giving up.")
o = urlparse.urlparse(url,allow_fragments=True)
conn = httplib.HTTPConnection(o.netloc)
path = o.path
if o.query:
path +='?'+o.query
conn.request("HEAD", path)
res = conn.getresponse()
headers = dict(res.getheaders())
if 'Location' in headers and headers['Location'] != url:
return resolve_http_redirect(headers['Location'], depth+1)
else:
return url
#---------------------------------------------------------------------- #----------------------------------------------------------------------
def tv66wz_download(url, output_dir = '.', merge = False, info_only = False): def tv66wz_download(url, output_dir = '.', merge = False, info_only = False):
@ -38,17 +60,15 @@ def tv66wz_download_by_id(id, title, output_dir = '.', merge = False, info_only
p = re.compile(r'.+filevalue=(.+)&copyvalue') p = re.compile(r'.+filevalue=(.+)&copyvalue')
for m in p.finditer(html): for m in p.finditer(html):
url = m.group(1) url_temp = m.group(1)
break break
#print(url) url = resolve_http_redirect(url_temp)
print('This will take very very long...')
type_, ext, size = url_info(url) type_, ext, size = url_info(url)
print_info('66wz', title, 'flv', 0) print_info('66wz', title, 'flv', size)
if not info_only: if not info_only:
download_urls([url], title, 'flv', total_size=None, output_dir=output_dir, merge=merge) download_urls([url], title, ext, total_size=None, output_dir=output_dir, merge=merge)
site_info = "66wz" site_info = "66wz"
download = tv66wz_download download = tv66wz_download