Python - 下載pdf文件（非.pdf）url

我想從一個有登錄名的站點下載20左右的pdf文件。這是我迄今爲止的，但它沒有下載任何有效的PDF文件（即它們都已損壞）。我也是python的新手。Python - 下載pdf文件（非.pdf）url

import mechanize 
import urllib2 

def download_file(download_url): 
    response = urllib2.urlopen(download_url) 
    print response.geturl() 
    print response.read() 
    file = open("document.pdf", 'wb') 
    file.write(response.read()) 
    file.close() 

brwser = mechanize.Browser() 
brwser.addheaders = [('User-agent', 'Firefox')] 
response = brwser.open(url) 

brwser.select_form(nr = 0) 
brwser.form['UserName'] = 'username' 
brwser.form['Password'] = 'password' 
nextpage = brwser.submit() 

# Navigate to the page I want 

for link in brwser.links(): 
    if link.text == 'Some pdf': 
     request = brwser.follow_link(link) 
     download_file(link.url)

我不知道該怎麼嘗試。對於PDF文件的URL都是這樣

https://example.com/something/source2.aspx?id=e9a9bfdc-7d97-e411-9e03-76439cf4d30e

另外，response.read（）如下：

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> 
<html xmlns="http://www.w3.org/1999/xhtml"> 
<head><title> 
Source 
</title> 
<script type='text/javascript'> 
    window.onload = function() { 
     var url = window.location.href.replace('source.aspx?', 'source2.aspx?'); 
     window.location = url; 
    }; 
</script> 
</head> 
<body> 
<div style='position:fixed; height:100%; width:100%; overflow:hidden; top:100px; left:100px;'>Loading, please wait.</div> 
</body> 
</html>

那麼，如何下載這些文件？

來源

2015-10-06 roger168168