How can I set proxy for the last urllib in Python 3.
I am doing the next
from urllib import request as urlrequest
ask = urlrequest.Request(url) # note that here Request has R not r as prev versions
open = urlrequest.urlopen(req)
open.read()
I tried adding proxy as follows :
ask=urlrequest.Request.set_proxy(ask,proxies,'http')
However I don't know how correct it is since I am getting the next error:
336 def set_proxy(self, host, type):
--> 337 if self.type == 'https' and not self._tunnel_host:
338 self._tunnel_host = self.host
339 else:
AttributeError: 'NoneType' object has no attribute 'type'
You should be calling set_proxy() on an instance of class Request, not on the class itself:
from urllib import request as urlrequest
proxy_host = 'localhost:1234' # host and port of your proxy
url = 'http://www.httpbin.org/ip'
req = urlrequest.Request(url)
req.set_proxy(proxy_host, 'http')
response = urlrequest.urlopen(req)
print(response.read().decode('utf8'))
I needed to disable the proxy in our company environment, because I wanted to access a server on localhost. I could not disable the proxy server with the approach from #mhawke (tried to pass {}, None and [] as proxies).
This worked for me (can also be used for setting a specific proxy, see comment in code).
import urllib.request as request
# disable proxy by passing an empty
proxy_handler = request.ProxyHandler({})
# alertnatively you could set a proxy for http with
# proxy_handler = request.ProxyHandler({'http': 'http://www.example.com:3128/'})
opener = request.build_opener(proxy_handler)
url = 'http://www.example.org'
# open the website with the opener
req = opener.open(url)
data = req.read().decode('utf8')
print(data)
Urllib will automatically detect proxies set up in the environment - so one can just set the HTTP_PROXY variable either in your environment e.g. for Bash:
export HTTP_PROXY=http://proxy_url:proxy_port
or using Python e.g.
import os
os.environ['HTTP_PROXY'] = 'http://proxy_url:proxy_port'
Note from the urllib docs: "HTTP_PROXY[environment variable] will be ignored if a variable REQUEST_METHOD is set; see the documentation on getproxies()"
import urllib.request
def set_http_proxy(proxy):
if proxy == None: # Use system default setting
proxy_support = urllib.request.ProxyHandler()
elif proxy == '': # Don't use any proxy
proxy_support = urllib.request.ProxyHandler({})
else: # Use proxy
proxy_support = urllib.request.ProxyHandler({'http': '%s' % proxy, 'https': '%s' % proxy})
opener = urllib.request.build_opener(proxy_support)
urllib.request.install_opener(opener)
proxy = 'user:pass#ip:port'
set_http_proxy(proxy)
url = 'https://www.httpbin.org/ip'
request = urllib.request.Request(url)
response = urllib.request.urlopen(request)
html = response.read()
html
Related
I'm behind a proxy and would like to use urllib2 to access external sites. If I set up the proxy in my environment, I can access external sites. When I set a proxy in urllib2, it seems to be ignored and the access fails.
The code I'm using is:
import urllib2
import os
import sys
uri = "https://www.python.org"
http_proxy_server = "192.168.12.20"
http_proxy_port = "8082"
http_proxy = "http://%s:%s" % (http_proxy_server, http_proxy_port)
def open_url_no_proxy():
sys.stdout.write('Proxy (none): ')
proxy_handler = urllib2.ProxyHandler({})
opener = urllib2.build_opener(proxy_handler)
try:
opener.open(uri)
sys.stdout.write('PASS\n')
except urllib2.URLError:
sys.stdout.write('FAIL\n')
def open_url_system_proxy():
sys.stdout.write('Proxy (system): ')
opener = urllib2.build_opener()
try:
opener.open(uri)
sys.stdout.write('PASS\n')
except urllib2.URLError:
sys.stdout.write('FAIL\n')
def open_url_installed_opener():
sys.stdout.write('Proxy (installed): ')
proxy_handler = urllib2.ProxyHandler({"http": http_proxy})
opener = urllib2.build_opener(proxy_handler)
try:
opener.open(uri)
sys.stdout.write('PASS\n')
except urllib2.URLError:
sys.stdout.write('FAIL\n')
if __name__ == "__main__":
os.environ['no_proxy'] = 'localhost,127.0.0.1'
os.environ['NO_PROXY'] = 'localhost,127.0.0.1'
os.environ['http_proxy'] = http_proxy
os.environ['HTTP_PROXY'] = http_proxy
open_url_system_proxy()
open_url_no_proxy()
open_url_system_proxy()
open_url_installed_opener()
open_url_system_proxy()
The response I get on my system is:
$ python proxytest2.py
Proxy (system): PASS
Proxy (none): FAIL
Proxy (system): PASS
Proxy (installed): FAIL
Proxy (system): PASS
What am I doing wrong?
You've set up only a proxy for HTTP in the line below, but you're accessing an HTTPS site:
proxy_handler = urllib2.ProxyHandler({"http": http_proxy})
You need to modify this to
proxy_handler = urllib2.ProxyHandler({"http": http_proxy, "https": http_proxy})
According to the documentation, this is the format:
Request.set_proxy(host, type)
So what I have is this for example:
Request.set_proxy("localhost:8888","http")
What is the format if the proxy requires a username and password?
Two ways to do this if you must use a urllib2.Request object:
Set environment variables http_proxy and/or https_proxy either outside of the Python interpreter, or internally using os.environ['http_proxy'] before you import urllib2.
import os
os.environ['http_proxy'] = 'http://user:password#localhost:8888'
import urllib2
req = urllib2.Request('http://www.blah.com')
f = urllib2.urlopen(req)
Or manually set HTTP request header:
import urllib2
from base64 import urlsafe_b64encode
PROXY_USERNAME = 'user'
PROXY_PASSWORD = 'password'
req = urllib2.Request('http://www.blah.com')
req.set_proxy('localhost:8888', 'http')
proxy_auth = urlsafe_b64encode('%s:%s' % (PROXY_USERNAME, PROXY_PASSWORD))
req.add_header('Proxy-Authorization', 'Basic %s' % proxy_auth)
f = urllib2.urlopen(req)
I tried logging into quora using python. But it gives me the following error.
urllib2.HTTPError: HTTP Error 500: Internal Server Error
This is my code till now. I also work behind a proxy.
import urllib2
import urllib
import re
import cookielib
class Quora:
def __init__(self):
'''Initialising and authentication'''
auth = 'http://name:password#proxy:port'
cj = cookielib.CookieJar()
logindata = urllib.urlencode({'email' : 'email' , 'password' : 'password'})
handler = urllib2.ProxyHandler({'http' : auth})
opener = urllib2.build_opener(handler , urllib2.HTTPCookieProcessor(cj))
urllib2.install_opener(opener)
a = urllib2.urlopen('http://www.quora.com/' , logindata)
def main():
Quora()
Can someone please point out what is wrong?
if __name__ == '__main__':
main()
Try something like this:
# Load proxies
proxies = []
proxies_fp = open('proxies.txt', 'r') # A list of proxies
for proxy in proxies_fp:
proxies.append(proxy)
cookiejar = cookielib.CookieJar()
def perform_request(url, opener, credientials):
# Instantiate our request object
request = urllib2.Request(url)
# Perform the request, returning a pointer to the result set.
result = opener.urlopen(request, credentials)
return result
credentials ={
'username' : 'username',
'password' : 'password'
}
encoded_credentials = urllib.urlencode(credentials)
def main():
# Get random proxy
proxy = random.choice(proxies)
# Install our proxy
opener = urllib2.build_opener(
urllib2.ProxyHandler({'http': proxy}),
urllib2.HTTPRedirectHandler(),
urllib2.HTTPHandler(debuglevel=0),
urllib2.HTTPSHandler(debuglevel=0),
urllib2.HTTPCookieProcessor(cookiejar),
)
urllib2.install_opener(opener)
a = perform_request(url, opener, encoded_credentials)
--untested--
I've had to do something similar to this, and it worked for me this way. (Please note, that this is NOT an exact copy of code I used. I had to manipulate it a bit, and did NOT test)
I have this program that check a website, and I want to know how can I check it via proxy in Python...
this is the code, just for example
while True:
try:
h = urllib.urlopen(website)
break
except:
print '['+time.strftime('%Y/%m/%d %H:%M:%S')+'] '+'ERROR. Trying again in a few seconds...'
time.sleep(5)
By default, urlopen uses the environment variable http_proxy to determine which HTTP proxy to use:
$ export http_proxy='http://myproxy.example.com:1234'
$ python myscript.py # Using http://myproxy.example.com:1234 as a proxy
If you instead want to specify a proxy inside your application, you can give a proxies argument to urlopen:
proxies = {'http': 'http://myproxy.example.com:1234'}
print("Using HTTP proxy %s" % proxies['http'])
urllib.urlopen("http://www.google.com", proxies=proxies)
Edit: If I understand your comments correctly, you want to try several proxies and print each proxy as you try it. How about something like this?
candidate_proxies = ['http://proxy1.example.com:1234',
'http://proxy2.example.com:1234',
'http://proxy3.example.com:1234']
for proxy in candidate_proxies:
print("Trying HTTP proxy %s" % proxy)
try:
result = urllib.urlopen("http://www.google.com", proxies={'http': proxy})
print("Got URL using proxy %s" % proxy)
break
except:
print("Trying next proxy in 5 seconds")
time.sleep(5)
Python 3 is slightly different here. It will try to auto detect proxy settings but if you need specific or manual proxy settings, think about this kind of code:
#!/usr/bin/env python3
import urllib.request
proxy_support = urllib.request.ProxyHandler({'http' : 'http://user:pass#server:port',
'https': 'https://...'})
opener = urllib.request.build_opener(proxy_support)
urllib.request.install_opener(opener)
with urllib.request.urlopen(url) as response:
# ... implement things such as 'html = response.read()'
Refer also to the relevant section in the Python 3 docs
Here example code guide how to use urllib to connect via proxy:
authinfo = urllib.request.HTTPBasicAuthHandler()
proxy_support = urllib.request.ProxyHandler({"http" : "http://ahad-haam:3128"})
# build a new opener that adds authentication and caching FTP handlers
opener = urllib.request.build_opener(proxy_support, authinfo,
urllib.request.CacheFTPHandler)
# install it
urllib.request.install_opener(opener)
f = urllib.request.urlopen('http://www.google.com/')
"""
For http and https use:
proxies = {'http':'http://proxy-source-ip:proxy-port',
'https':'https://proxy-source-ip:proxy-port'}
more proxies can be added similarly
proxies = {'http':'http://proxy1-source-ip:proxy-port',
'http':'http://proxy2-source-ip:proxy-port'
...
}
usage
filehandle = urllib.urlopen( external_url , proxies=proxies)
Don't use any proxies (in case of links within network)
filehandle = urllib.urlopen(external_url, proxies={})
Use proxies authentication via username and password
proxies = {'http':'http://username:password#proxy-source-ip:proxy-port',
'https':'https://username:password#proxy-source-ip:proxy-port'}
Note: avoid using special characters such as :,# in username and passwords
What's the best way to specify a proxy with username and password for an http connection in python?
This works for me:
import urllib2
proxy = urllib2.ProxyHandler({'http': 'http://
username:password#proxyurl:proxyport'})
auth = urllib2.HTTPBasicAuthHandler()
opener = urllib2.build_opener(proxy, auth, urllib2.HTTPHandler)
urllib2.install_opener(opener)
conn = urllib2.urlopen('http://python.org')
return_str = conn.read()
Use this:
import requests
proxies = {"http":"http://username:password#proxy_ip:proxy_port"}
r = requests.get("http://www.example.com/", proxies=proxies)
print(r.content)
I think it's much simpler than using urllib. I don't understand why people love using urllib so much.
Setting an environment var named http_proxy like this: http://username:password#proxy_url:port
The best way of going through a proxy that requires authentication is using urllib2 to build a custom url opener, then using that to make all the requests you want to go through the proxy. Note in particular, you probably don't want to embed the proxy password in the url or the python source code (unless it's just a quick hack).
import urllib2
def get_proxy_opener(proxyurl, proxyuser, proxypass, proxyscheme="http"):
password_mgr = urllib2.HTTPPasswordMgrWithDefaultRealm()
password_mgr.add_password(None, proxyurl, proxyuser, proxypass)
proxy_handler = urllib2.ProxyHandler({proxyscheme: proxyurl})
proxy_auth_handler = urllib2.ProxyBasicAuthHandler(password_mgr)
return urllib2.build_opener(proxy_handler, proxy_auth_handler)
if __name__ == "__main__":
import sys
if len(sys.argv) > 4:
url_opener = get_proxy_opener(*sys.argv[1:4])
for url in sys.argv[4:]:
print url_opener.open(url).headers
else:
print "Usage:", sys.argv[0], "proxy user pass fetchurls..."
In a more complex program, you can seperate these components out as appropriate (for instance, only using one password manager for the lifetime of the application). The python documentation has more examples on how to do complex things with urllib2 that you might also find useful.
Or if you want to install it, so that it is always used with urllib2.urlopen (so you don't need to keep a reference to the opener around):
import urllib2
url = 'www.proxyurl.com'
username = 'user'
password = 'pass'
password_mgr = urllib2.HTTPPasswordMgrWithDefaultRealm()
# None, with the "WithDefaultRealm" password manager means
# that the user/pass will be used for any realm (where
# there isn't a more specific match).
password_mgr.add_password(None, url, username, password)
auth_handler = urllib2.HTTPBasicAuthHandler(password_mgr)
opener = urllib2.build_opener(auth_handler)
urllib2.install_opener(opener)
print urllib2.urlopen("http://www.example.com/folder/page.html").read()
Here is the method use urllib
import urllib.request
# set up authentication info
authinfo = urllib.request.HTTPBasicAuthHandler()
proxy_support = urllib.request.ProxyHandler({"http" : "http://ahad-haam:3128"})
# build a new opener that adds authentication and caching FTP handlers
opener = urllib.request.build_opener(proxy_support, authinfo,
urllib.request.CacheFTPHandler)
# install it
urllib.request.install_opener(opener)
f = urllib.request.urlopen('http://www.python.org/')
"""