python 匿名代理访问浏览器

!/usr/bin/python

coding=utf-8

import mechanize import cookielib import random

class anonBrowser(mechanize.Browser): def init(self, proxies = [], user_agents = []): mechanize.Browser.init(self) self.set_handle_robots(False) # 可供用户使用的代理服务器列表 self.proxies = proxies # user_agent列表 self.user_agents = user_agents + ['Mozilla/4.0 ', 'FireFox/6.01','ExactSearch', 'Nokia7110/1.0'] self.cookie_jar = cookielib.LWPCookieJar() self.set_cookiejar(self.cookie_jar) self.anonymize()

# 清空cookie
def clear_cookies(self):
    self.cookie_jar = cookielib.LWPCookieJar()
    self.set_cookiejar(self.cookie_jar)

# 从user_agent列表中随机设置一个user_agent
def change_user_agent(self):
    index = random.randrange(0, len(self.user_agents) )
    self.addheaders = [('User-agent',  ( self.user_agents[index] ))]         
        
# 从代理列表中随机设置一个代理
def change_proxy(self):
    if self.proxies:
        index = random.randrange(0, len(self.proxies))
        self.set_proxies( {'http': self.proxies[index]} )

# 调用上述三个函数改变UA、代理以及清空cookie以提高匿名性，其中sleep参数可让进程休眠以进一步提高匿名效果
def anonymize(self, sleep = False):
    self.clear_cookies()
    self.change_user_agent()
    self.change_proxy()

    if sleep:
        time.sleep(60)

!/usr/bin/python

coding=utf-8

from anonBrowser import * from BeautifulSoup import BeautifulSoup import os import optparse import re

def printLinks(url): ab = anonBrowser() ab.anonymize() page = ab.open(url) html = page.read() # 使用re模块解析href链接 try: print '[+] Printing Links From Regex.' link_finder = re.compile('href="(.*?)"') links = link_finder.findall(html) for link in links: print link except: pass # 使用bs4模块解析href链接 try: print '\n[+] Printing Links From BeautifulSoup.' soup = BeautifulSoup(html) links = soup.findAll(name='a') for link in links: if link.has_key('href'): print link['href'] except: pass

def main(): parser = optparse.OptionParser('[*]Usage: python linkParser.py -u <target url>') parser.add_option('-u', dest='tgtURL', type='string', help='specify target url') (options, args) = parser.parse_args() url = options.tgtURL

if url == None:
    print parser.usage
    exit(0)
else:
    printLinks(url)

if name == 'main': main()