爬虫代理ip python:教你用爬虫通过代理自动刷网页的浏览量

但是, 在实际运行的时候, 发现了一个问题, 我怎么才能知道这些IP有用, 并且代理设置成功了呢? 当然, 也是有解决方案的,我们可以用代理访问这个网站http://httpbin.org/ip ,如果不正常会抛出异常, 如果是正常的就会返回如下信息

{ "origin": "106.38.91.34, 106.38.91.34"}

废话不多说，直接上代码：

from bs4 import BeautifulSoupimport requestsimport randomimport timedef download_page(url): print(url) try: #User Agent中文名为用户代理，简称 UA，它是一个特殊字符串头，使得服务器能够识别客户使用的操作系统及版本、CPU 类型、浏览器及版本、 #浏览器渲染引擎、浏览器语言、浏览器插件等。 header = { "User-Agent":"Mozilla/5.0 (windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.104 Safari/537.36" } data = requests.get(url,headers=header).text except HTTPError as err: print(err.__traceback__) except ConnectionError as err: print(err.__traceback__) except TimeoutError as err: print(err.__traceback__) return data#获取当前首页的内容def parse_proxy_html(html): try: #解析器html.parser lxml xml html5lib soup = BeautifulSoup(html, 'lxml') find_all = soup.find_all('tr') f = open("proxy", "w") for find_tr in find_all: find_tds = find_tr.find_all('td') if len(find_tds) == 0: continue ip_temp = find_tds[1].contents[0]+":"+find_tds[2].contents[0] try: #随机模拟一个用户 user_agent = {'User-Agent':random.choice(agent_list)} #随机获取一个代理ip proxies = {'http':ip_temp} #这样写没有问题,但是抓取出来的ip大都没有用 #判断代理ip是否有用,只保存有用的代理ip,两秒不响应就算无效的ip targetUrl = 'http://httpbin.org/ip' resp = requests.get(targetUrl, headers=user_agent,proxies=proxies,timeout=2) print(resp.status_code) print(resp.text) print('~~有效的~~代理ip和端口号%s'%ip_temp) f.write(ip_temp+"n") except Exception as e: print('~~异常:%s'%e) print('~~无效的~~代理ip和端口号%s'%ip_temp) #获取下个页面地址 next_a = soup.find('a',attrs={'rel': 'next'}) if next_a is None: print("~~None~~~") return ""; return next_a['href'] except Exception as ex: print('抓取信息异常:'+ex)#首页数据抓取HTTP = 'https://www.xicidaili.com'def to_proxy_page(): download_url = '/wt/1' num = 1 while download_url != 'JAVAscript:;' and download_url!='': if num == 3: print('~~~~够用了~~不抓取了~~~') break print("第%d次请求地址:%s"%(num,download_url)); #随机停顿几秒 i = random.randint(1, 3) time.sleep(i) #获取页面信息 html = download_page(HTTP + download_url) #解析和保存 download_url = parse_proxy_html(html) num = num+1; if __name__ == '__main__': to_proxy_page()

获取到的代理地址格式如下(想要多少, 代码自己设置下就好了):

163.204.243.4:9999

60.13.42.248:9999

二、通过代理地址去刷新网页

可以先写一个User-Agent列表, 模拟不同的浏览器信息。然后配置需要刷新的网页就好了。

import randomimport socketimport requests#定义需要刷新的页面集合refreshPage_list = [ #1062 'https://blog.csdn.net/dujianxiong/article/details/80844652', #153 'https://blog.csdn.net/super_DuoLa/article/details/90205512' ]#定义User-Agent集合agent_list = [ #Win7: 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1', #Win7: 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0', #Win7: 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50', #Win7: 'Opera/9.80 (Windows NT 6.1; U; zh-cn) Presto/2.9.168 Version/11.50', #Win7+ie9： 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 2.0.50727; SLCC2; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; Tablet PC 2.0; .NET4.0E)', #Win7+ie8： 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; InfoPath.3)', #WinXP+ie8： 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; GTB7.0)', #WinXP+ie7： 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)', #WinXP+ie6： 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1)', #傲游3.1.7在Win7+ie9,高速模式: 'Mozilla/5.0 (Windows; U; Windows NT 6.1; ) AppleWebKit/534.12 (KHTML, like Gecko) Maxthon/3.0 Safari/534.12', #傲游3.1.7在Win7+ie9,IE内核兼容模式: 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E)', #搜狗3.0在Win7+ie9,IE内核兼容模式: 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0)', #搜狗3.0在Win7+ie9,高速模式: 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.472.33 Safari/534.3 SE 2.X MetaSr 1.0', #360浏览器3.0在Win7+ie9: 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E)', #QQ浏览器6.9(11079)在Win7+ie9,极速模式: 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201', #QQ浏览器6.9(11079)在Win7+ie9,IE内核兼容模式: 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E) QQBrowser/6.9.11079.201', #阿云浏览器1.3.0.1724 Beta(编译日期2011-12-05)在Win7+ie9: 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)' ] #开始搞def to_refresh_page(): try: #获取代理信息 f = open("proxy",'r') lines = f.readlines() proxys = [] for line in lines: ip = line.strip() proxys.append(ip) #每个页面刷新10次 for i in range(10): for url in refreshPage_list: #随机模拟一个用户 user_agent = {'User-Agent':random.choice(agent_list)} #随机获取一个代理ip proxies = {'http':random.choice(proxys)} r = requests.get(url,headers=user_agent,proxies=proxies) print(r) print('刷新成功，请求地址url:%s返回状态status:%s'%(url,r.status_code)) except Exception as e: print('刷新页面异常:%s'%e) if __name__ == '__main__': to_refresh_page()

代码中我加了很多注解，就不长篇大论了，如果有不明白的可以评论。

三、思考问题

在实际测试中，发现刚才还有效的代理IP，当去刷新网页的时候就链接超时了呢？为什么请求了很多次，网页的浏览量并没有涨太多呢?

注: 文章所写代码仅用于技术交流