# -*- coding=utf8 -*-

import urllib2
import re
import time
import random
import socket
import threading
from user_agents import agents
import sys

reload(sys)
sys.setdefaultencoding(‘utf8‘)

# 抓取代理IP
ip_totle = []
for page in range(1,10):
    # url = ‘http://ip84.com/dlgn/‘ + str(page)
    url=‘http://www.xicidaili.com/nn/‘+str(page) #西刺代理
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64)"}
    # proxy_handler = urllib2.ProxyHandler({‘http‘: ‘http://‘})
    # opener = urllib2.build_opener(proxy_handler)
    # urllib2.install_opener(opener)
    request = urllib2.Request(url=url, headers=headers)
    response = urllib2.urlopen(request)
    content = response.read().decode(‘utf-8‘)
    print(‘get page‘, page)
    pattern = re.compile(‘<td>(\d.*?)</td>‘)  # 截取<td>與</td>之間第一個數為數字的內容
    ip_page = re.findall(pattern, str(content))
    ip_totle.extend(ip_page)
    time.sleep(random.choice(range(3, 5)))
# 打印抓取內容
print(‘代理IP地址     ‘, ‘\t‘, ‘端口‘, ‘\t‘, ‘速度‘, ‘\t‘, ‘驗證時間‘)
for i in range(0, len(ip_totle), 4):
    print(ip_totle[i], ‘    ‘, ‘\t‘, ip_totle[i + 1], ‘\t‘, ip_totle[i + 2], ‘\t‘, ip_totle[i + 3])
# 整理代理IP格式
proxys = []
for i in range(0, len(ip_totle), 4):
    proxy_host = ip_totle[i] + ‘:‘ + ip_totle[i + 1]
    proxy_temp = {"http": proxy_host}
    proxys.append(proxy_temp)

proxy_ip = open(‘proxy_ip.txt‘, ‘w‘)  # 新建一個儲存有效IP的文檔
lock = threading.Lock()  # 建立一個鎖


# 驗證代理IP有效性的方法
def test(i):
    socket.setdefaulttimeout(5)  # 設置全局超時時間
    url = "http://www.dianping.com/shop/21143491"  # 打算爬取的網址
    try:
        headers = {
            ‘Host‘: ‘www.dianping.com‘,
            ‘User-Agent‘: random.choice(agents),
        }
        proxy_support = urllib2.ProxyHandler(proxys[i])
        opener = urllib2.build_opener(proxy_support)
        # opener.addheaders = [("User-Agent", "Mozilla/5.0 (Windows NT 10.0; WOW64)")]
        urllib2.install_opener(opener)
        request = urllib2.Request(url=url, headers=headers)
        response = urllib2.urlopen(request)
        content = response.read().decode(‘utf-8‘)
        lock.acquire()  # 獲得鎖
        print(proxys[i], ‘is OK‘)
        proxy_ip.write(‘%s\n‘ % str(proxys[i]))  # 寫入該代理IP
        lock.release()  # 釋放鎖
    except Exception as e:
        lock.acquire()
        print(proxys[i], e)
        lock.release()


# 單線程驗證
# for i in range(len(proxys)):
#     test(i)
# 多線程驗證
threads = []
for i in range(len(proxys)):
    thread = threading.Thread(target=test, args=[i])
    threads.append(thread)
    thread.start()
# 阻塞主進程，等待所有子線程結束
for thread in threads:
    thread.join()

proxy_ip.close()  # 關閉文件

獲取免費代理