获取不同的IP

使用不同的user-agent


#!/usr/bin/python
# coding:utf-8

import re
import random
import sys
import time
import datetime
import threading
from random import choice
import requests
import bs4

#从代理网站获取代理IP
def get_ip():
	url="http://www.xicidaili.com/nn"
	headers = {"Accecpt":"text/html,application/xhtml+xml,application/xml",
				"Accept-Encoding":"gzip,deflate,sdch",
				"Accept-Language":"zh-CN,zh;q=0.8,en;q=0.6",
				"Referer":"http://www.xicidaili.com",
				"User-Agent":"Mozilla/5.0(Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36"
				}
	r = requests.get(url,headers=headers)
	soup =bs4.BeautifulSoup(r.text,'html.parser')
	data=soup.table.find_all("td")
	ip_compile=re.compile(r'<td>(\d+\.\d+\.\d+\.\d+)</td>')
	port_compile=re.compile(r"<td>(\d+)</td>")
	ip=re.findall(ip_compile,str(data))
	port=re.findall(port_compile,str(data))
	return [":".join(i) for i in zip(ip,port)]

#打印代理IP 
def printIP(ip):
	myip=ip
	for ips in myip:
		print ips
	print "print end"
	
#agent 池
agents = [
 	"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0; Baiduspider-ads) Gecko/17.0 Firefox/17.0",
    "Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Avant Browser/1.2.789rel1 (http://www.avantbrowser.com)",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5",
    "Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.9 (KHTML, like Gecko) Chrome/5.0.310.0 Safari/532.9",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.514.0 Safari/534.7",
    "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/9.0.601.0 Safari/534.14",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/10.0.601.0 Safari/534.14",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.20 (KHTML, like Gecko) Chrome/11.0.672.2 Safari/534.20",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.27 (KHTML, like Gecko) Chrome/12.0.712.0 Safari/534.27",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.24 Safari/535.1",
    "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
    "Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9b4) Gecko/2008030317 Firefox/3.0b4",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.10) Gecko/2009042316 Firefox/3.0.10",
    "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-GB; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)",
    "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6 GTB5",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; tr; rv:1.9.2.8) Gecko/20100722 Firefox/3.6.8 ( .NET CLR 3.5.30729; .NET4.0E)",
    "Mozilla/5.0 (Windows; U; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727; BIDUBrowser 7.6)",
    "Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko",
    "Mozilla/5.0 (Windows NT 6.3; WOW64; rv:46.0) Gecko/20100101 Firefox/46.0",
    "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.99 Safari/537.36",
    "Mozilla/5.0 (Windows NT 6.3; Win64; x64; Trident/7.0; Touch; LCJB; rv:11.0) like Gecko",
    "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Mozilla/5.0 (Windows NT 5.1; rv:5.0) Gecko/20100101 Firefox/5.0",
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0a2) Gecko/20110622 Firefox/6.0a2",
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0.1) Gecko/20100101 Firefox/7.0.1",
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:2.0b4pre) Gecko/20100815 Minefield/4.0b4pre",
    "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0 )",
    "Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Win 9x 4.90)",
    "Mozilla/5.0 (Windows; U; Windows XP) Gecko MultiZilla/1.6.1.0a",
    "Mozilla/2.02E (Win95; U)",
    "Mozilla/3.01Gold (Win95; I)",
    "Mozilla/4.8 [en] (Windows NT 5.1; U)",
    "Mozilla/5.0 (Windows; U; Win98; en-US; rv:1.4) Gecko Netscape/7.1 (ax)",
    "HTC_Dream Mozilla/5.0 (Linux; U; Android 1.5; en-ca; Build/CUPCAKE) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
    "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.2; U; de-DE) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/234.40.1 Safari/534.6 TouchPad/1.0",
    "Mozilla/5.0 (Linux; U; Android 1.5; en-us; sdk Build/CUPCAKE) AppleWebkit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
    "Mozilla/5.0 (Linux; U; Android 2.1; en-us; Nexus One Build/ERD62) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
    "Mozilla/5.0 (Linux; U; Android 2.2; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Mozilla/5.0 (Linux; U; Android 1.5; en-us; htc_bahamas Build/CRB17) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
    "Mozilla/5.0 (Linux; U; Android 2.1-update1; de-de; HTC Desire 1.19.161.5 Build/ERE27) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
    "Mozilla/5.0 (Linux; U; Android 2.2; en-us; Sprint APA9292KT Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Mozilla/5.0 (Linux; U; Android 1.5; de-ch; HTC Hero Build/CUPCAKE) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
    "Mozilla/5.0 (Linux; U; Android 2.2; en-us; ADR6300 Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Mozilla/5.0 (Linux; U; Android 2.1; en-us; HTC Legend Build/cupcake) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
    "Mozilla/5.0 (Linux; U; Android 1.5; de-de; HTC Magic Build/PLAT-RC33) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1 FirePHP/0.3",
    "Mozilla/5.0 (Linux; U; Android 1.6; en-us; HTC_TATTOO_A3288 Build/DRC79) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
    "Mozilla/5.0 (Linux; U; Android 1.0; en-us; dream) AppleWebKit/525.10  (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
    "Mozilla/5.0 (Linux; U; Android 1.5; en-us; T-Mobile G1 Build/CRB43) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari 525.20.1",
    "Mozilla/5.0 (Linux; U; Android 1.5; en-gb; T-Mobile_G2_Touch Build/CUPCAKE) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
    "Mozilla/5.0 (Linux; U; Android 2.0; en-us; Droid Build/ESD20) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
    "Mozilla/5.0 (Linux; U; Android 2.2; en-us; Droid Build/FRG22D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Mozilla/5.0 (Linux; U; Android 2.0; en-us; Milestone Build/ SHOLS_U2_01.03.1) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
    "Mozilla/5.0 (Linux; U; Android 2.0.1; de-de; Milestone Build/SHOLS_U2_01.14.0) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
    "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/525.10  (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
    "Mozilla/5.0 (Linux; U; Android 0.5; en-us) AppleWebKit/522  (KHTML, like Gecko) Safari/419.3",
    "Mozilla/5.0 (Linux; U; Android 1.1; en-gb; dream) AppleWebKit/525.10  (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
    "Mozilla/5.0 (Linux; U; Android 2.0; en-us; Droid Build/ESD20) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
    "Mozilla/5.0 (Linux; U; Android 2.1; en-us; Nexus One Build/ERD62) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
    "Mozilla/5.0 (Linux; U; Android 2.2; en-us; Sprint APA9292KT Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Mozilla/5.0 (Linux; U; Android 2.2; en-us; ADR6300 Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Mozilla/5.0 (Linux; U; Android 2.2; en-ca; GT-P1000M Build/FROYO) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
    "Mozilla/5.0 (Linux; U; Android 3.0.1; fr-fr; A500 Build/HRI66) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
    "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/525.10  (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
    "Mozilla/5.0 (Linux; U; Android 1.6; es-es; SonyEricssonX10i Build/R1FA016) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
    "Mozilla/5.0 (Linux; U; Android 1.6; en-us; SonyEricssonX10i Build/R1AA056) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
]

#主要测试程序
def get_url(code,ips=[]):
    """
        投票
        如果因为代理IP不可用造成投票失败,则会自动换一个代理IP后继续投
    """
    try:
        ip = choice(ips)                            #在IPS里面产生随机挑选一个返回
    except:
        return False
    else:
        proxies = {
            "http":ip,
        }
        headers2 = { "Accept":"text/html,application/xhtml+xml,application/xml;",
                        "Accept-Encoding":"gzip, deflate, sdch",
                        "Accept-Language":"zh-CN,zh;q=0.8,en;q=0.6",
                        "Referer":"",
                        "User-Agent":choice(agents),
                        }
    try:
        hz_url = "https://www.baidu.com"   # 某网站的地址,用于测试
        hz_r = requests.get(hz_url,headers=headers2,proxies=proxies)
        if (int(hz_r.status_code) == 200):
            print datetime.datetime.now().strftime('%H:%M:%S')+':当前状态是'+str(hz_r.status_code)
        else:
            print  datetime.datetime.now().strftime('%H:%M:%S')+'访问错误'
    except requests.exceptions.ConnectionError:
        print "ConnectionError"
        if not ips:
            print "not ip"
            sys.exit()
        # 删除不可用的代理IP
        if ip in ips:
            ips.remove(ip)
        # 重新请求URL
        get_url(code,ips)
    else:
        date = datetime.datetime.now().strftime('%H:%M:%S')
        print u"第%s次 时间: [%s] :当前IP:[%s] (剩余可用代理IP数:%s)" % (code,date,ip,len(ips))


ips = []
for i in xrange(6000):
    # 每隔1000次重新获取一次最新的代理IP,每次可获取最新的100个代理IP
    if i % 1000 == 0:
        ips.extend(get_ip())
    # 启用线程,隔1秒产生一个线程,可控制时间加快投票速度 ,time.sleep的最小单位是毫秒
    t1 = threading.Thread(target=get_url,args=(i,ips))
    t1.start()
    time.sleep(2)	




Logo

CSDN联合极客时间,共同打造面向开发者的精品内容学习社区,助力成长!

更多推荐