我正在尝试抓取网站上的某些页面,但要查看页面,我需要连接到VPN。我的设置如下:
我想在通过VPN连接的pythonanywhere上运行一个脚本,以便流量似乎来自澳大利亚。
到目前为止,我找到的最接近的答案是:
答案 0 :(得分:14)
我看到https://www.privateinternetaccess.com/可以选择使用SOCKS5代理。 如果您使用请求模块进行抓取,则可以使用SOCKS5:
pip install -U requests[socks]
并在脚本中:
import requests
proxies = {'http': 'socks5://user:pass@host:port',
'https': 'socks5://user:pass@host:port'}
resp = requests.get('http://example.com', proxies=proxies )
答案 1 :(得分:1)
你应该具体说明你想要的东西。代理与VPN不同。
在Python中更容易创建代理。
以下是代码:
import socket
import select
import time
import sys
# Changing the buffer_size and delay, you can improve the speed and bandwidth.
# But when buffer get to high or delay go too down, you can broke things
buffer_size = 4096
delay = 0.0001
forward_to = ('smtp.zaz.ufsk.br', 25)
class Forward:
def __init__(self):
self.forward = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
def start(self, host, port):
try:
self.forward.connect((host, port))
return self.forward
except Exception, e:
print e
return False
class TheServer:
input_list = []
channel = {}
def __init__(self, host, port):
self.server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
self.server.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
self.server.bind((host, port))
self.server.listen(200)
def main_loop(self):
self.input_list.append(self.server)
while 1:
time.sleep(delay)
ss = select.select
inputready, outputready, exceptready = ss(self.input_list, [], [])
for self.s in inputready:
if self.s == self.server:
self.on_accept()
break
self.data = self.s.recv(buffer_size)
if len(self.data) == 0:
self.on_close()
break
else:
self.on_recv()
def on_accept(self):
forward = Forward().start(forward_to[0], forward_to[1])
clientsock, clientaddr = self.server.accept()
if forward:
print clientaddr, "has connected"
self.input_list.append(clientsock)
self.input_list.append(forward)
self.channel[clientsock] = forward
self.channel[forward] = clientsock
else:
print "Can't establish connection with remote server.",
print "Closing connection with client side", clientaddr
clientsock.close()
def on_close(self):
print self.s.getpeername(), "has disconnected"
#remove objects from input_list
self.input_list.remove(self.s)
self.input_list.remove(self.channel[self.s])
out = self.channel[self.s]
# close the connection with client
self.channel[out].close() # equivalent to do self.s.close()
# close the connection with remote server
self.channel[self.s].close()
# delete both objects from channel dict
del self.channel[out]
del self.channel[self.s]
def on_recv(self):
data = self.data
# here we can parse and/or modify the data before send forward
print data
self.channel[self.s].send(data)
if __name__ == '__main__':
server = TheServer('', 9090)
try:
server.main_loop()
except KeyboardInterrupt:
print "Ctrl C - Stopping server"
sys.exit(1)
希望你发现它很有用; - )