【python3】如何創建爬蟲代理ip池

1、爲何須要創建爬蟲代理ip池

              在衆多的網站防爬措施中，有一種是根據ip的訪問頻率進行限制的，在某段時間內，當某個ip的訪問量達到必定的閥值時，該ip會被拉黑、在一段時間內被禁止訪問。

      這種時候，能夠經過下降爬蟲的頻率，或者更改ip來應對。後者就須要有一個可用的代理ip池，以供爬蟲工做時切換。

2、如何創建一個爬蟲代理ip池         

      思路：   一、找到一個免費的ip代理網站(如：西刺代理)

                 二、爬取ip（常規爬取requests+BeautifulSoup）

                 三、驗證ip有效性（攜帶爬取到的ip，去訪問指定的url，看返回的狀態碼是否是200）

                 四、記錄ip （寫到文檔）

      代碼以下：

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import requests,threading,datetime
from bs4 import BeautifulSoup
import random

"""
一、抓取西刺代理網站的代理ip
二、並根據指定的目標url,對抓取到ip的有效性進行驗證
三、最後存到指定的path
"""

# ------------------------------------------------------文檔處理--------------------------------------------------------
# 寫入文檔
def write(path,text):
    with open(path,'a', encoding='utf-8') as f:
        f.writelines(text)
        f.write('\n')
# 清空文檔
def truncatefile(path):
    with open(path, 'w', encoding='utf-8') as f:
        f.truncate()
# 讀取文檔
def read(path):
    with open(path, 'r', encoding='utf-8') as f:
        txt = []
        for s in f.readlines():
            txt.append(s.strip())
    return txt
# ----------------------------------------------------------------------------------------------------------------------
# 計算時間差,格式: 時分秒
def gettimediff(start,end):
    seconds = (end - start).seconds
    m, s = divmod(seconds, 60)
    h, m = divmod(m, 60)
    diff = ("%02d:%02d:%02d" % (h, m, s))
    return diff
# ----------------------------------------------------------------------------------------------------------------------
# 返回一個隨機的請求頭 headers
def getheaders():
    user_agent_list = [ \
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1" \
        "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", \
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", \
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", \
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", \
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", \
        "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", \
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", \
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", \
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
    ]
    UserAgent=random.choice(user_agent_list)
    headers = {'User-Agent': UserAgent}
    return headers
# -----------------------------------------------------檢查ip是否可用----------------------------------------------------
def checkip(targeturl,ip):
    headers =getheaders()  # 定製請求頭
    proxies = {"http": "http://"+ip, "https": "http://"+ip}  # 代理ip
    try:
        response=requests.get(url=targeturl,proxies=proxies,headers=headers,timeout=5).status_code
        if response == 200 :
            return True
        else:
            return False
    except:
        return False

#-------------------------------------------------------獲取代理方法----------------------------------------------------
# 免費代理 XiciDaili
def findip(type,pagenum,targeturl,path): # ip類型,頁碼,目標url,存放ip的路徑
    list={'1': 'http://www.xicidaili.com/nt/', # xicidaili國內普通代理
          '2': 'http://www.xicidaili.com/nn/', # xicidaili國內高匿代理
          '3': 'http://www.xicidaili.com/wn/', # xicidaili國內https代理
          '4': 'http://www.xicidaili.com/wt/'} # xicidaili國外http代理
    url=list[str(type)]+str(pagenum) # 配置url
    headers = getheaders() # 定製請求頭
    html=requests.get(url=url,headers=headers,timeout = 5).text
    soup=BeautifulSoup(html,'lxml')
    all=soup.find_all('tr',class_='odd')
    for i in all:
        t=i.find_all('td')
        ip=t[1].text+':'+t[2].text
        is_avail = checkip(targeturl,ip)
        if is_avail == True:
            write(path=path,text=ip)
            print(ip)

#-----------------------------------------------------多線程抓取ip入口---------------------------------------------------
def getip(targeturl,path):
     truncatefile(path) # 爬取前清空文檔
     start = datetime.datetime.now() # 開始時間
     threads=[]
     for type in range(4):   # 四種類型ip,每種類型取前三頁,共12條線程
         for pagenum in range(3):
             t=threading.Thread(target=findip,args=(type+1,pagenum+1,targeturl,path))
             threads.append(t)
     print('開始爬取代理ip')
     for s in threads: # 開啓多線程爬取
         s.start()
     for e in threads: # 等待全部線程結束
         e.join()
     print('爬取完成')
     end = datetime.datetime.now() # 結束時間
     diff = gettimediff(start, end)  # 計算耗時
     ips = read(path)  # 讀取爬到的ip數量
     print('一共爬取代理ip: %s 個,共耗時: %s \n' % (len(ips), diff))

#-------------------------------------------------------啓動-----------------------------------------------------------
if __name__ == '__main__':
    path = 'ip.txt' # 存放爬取ip的文檔path
    targeturl = 'http://www.cnblogs.com/TurboWay/' # 驗證ip有效性的指定url
    getip(targeturl,path)

 

 

結果：