簡(jiǎn)單使用IP代理池和用戶代理池的爬蟲

成都創(chuàng)新互聯(lián)服務(wù)項(xiàng)目包括天心網(wǎng)站建設(shè)、天心網(wǎng)站制作、天心網(wǎng)頁(yè)制作以及天心網(wǎng)絡(luò)營(yíng)銷策劃等。多年來，我們專注于互聯(lián)網(wǎng)行業(yè)，利用自身積累的技術(shù)優(yōu)勢(shì)、行業(yè)經(jīng)驗(yàn)、深度合作伙伴關(guān)系等，向廣大中小型企業(yè)、政府機(jī)構(gòu)等提供互聯(lián)網(wǎng)行業(yè)的解決方案，天心網(wǎng)站推廣取得了明顯的社會(huì)效益與經(jīng)濟(jì)效益。目前，我們服務(wù)的客戶以成都為中心已經(jīng)輻射到天心省份的部分城市，未來相信會(huì)繼續(xù)擴(kuò)大服務(wù)區(qū)域并繼續(xù)獲得客戶的支持與信任！

import re
import random
import urllib.request as urlreq
import urllib.error as urlerr

#用戶代理池
uapools = [
    "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0",
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36",
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.79 Safari/537.36 Edge/14.14393"
]
#ip代理池
ipools = []

#獲取用戶代理
def get_ua(uapools):
    thisua = random.choice(uapools)
    header = ("User-Agent", thisua)
    url_opener = urlreq.build_opener()
    url_opener.addheaders = [header]
    urlreq.install_opener(url_opener)

#獲取ip池，這里從西刺獲取首頁(yè)IP保存到列表中
def get_ipools(ipurl):
    get_ua(uapools)
    data = urlreq.urlopen(ipurl).read().decode("utf-8","ignore")
    pat = "/>.*?(.*?).*?(.*?)"
    ret = re.compile(pat, re.S).findall(data)
    # print(ret)
    for i in ret:
        ips = i[0] + ":" + i[1]
        ipools.append(ips)
    return ipools

#解析糗事百科的文章
def get_article(data):
    pat = '
.*?(.*?).*?
'
    rst = re.compile(pat, re.S).findall(data)
    print(rst)
    # down_file(rst, i)

def get_html(urlweb):
    for i in range(1, 6):     #爬取前五頁(yè)文章
        while 1:
            try:
                page = urlweb + str(i)
                thisua = random.choice(uapools)
                header = ("User-Agent", thisua)               #構(gòu)建用戶代理
                ip = random.choice(ipools)
                print("當(dāng)前使用的ip為" + ip)
                proxy = urlreq.ProxyHandler({"http": ip})   #構(gòu)建IP代理
                url_opener = urlreq.build_opener(proxy, urlreq.HTTPHandler)   #添加IP代理頭
                url_opener.addheaders = [header]                           #添加用戶代理頭
                urlreq.install_opener(url_opener)                             #設(shè)為全局變量
                data = urlreq.urlopen(page).read().decode("utf-8","ignore")
            except Exception as e:
                print(e)
                ipools.remove(ip)   #爬取失敗時(shí)，從IP池中刪除IP，重新爬取文章
                continue
            get_article(data)   #解析文章
            break                    #完成一頁(yè)的爬取

if __name__ == "__main__":
    ipurl = "https://www.xicidaili.com/nn/"
    ipools = get_ipools(ipurl)        #獲取ip池
    urlweb = "https://www.qiushibaike.com/text/page/"
    get_html(urlweb)