当前位置：首页 » python爬虫 » 正文

Python使用requests xpath 并开启多线程爬取西刺代理ip实例

看: 834次  时间：2020-08-07  分类 : python爬虫

我就废话不多说啦，大家还是直接看代码吧！

import requests,random
from lxml import etree
import threading
import time

angents = [
  "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
  "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
  "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
  "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
  "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
  "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
  "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
  "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
  "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
  "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
  "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
  "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
  "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
  "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
  "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
]

def get_all_xici_urls(start_num,stop_num):
  xici_urls = []
  for num in range(start_num,len(stop_num)+1):
    xici_http_url = 'http://www.xicidaili.com/wt/'
    xici_http_url += str(num)
    xici_urls.append(xici_http_url)
  print('获取所有待爬取xici url 已完成...')
  return xici_urls
def get_all_http_ip(xici_http_url,headers,proxies_list):
  try:
    all_ip_xpath = '//table//tr/child::*[2]/text()'
    all_prot_xpath = '//table//tr/child::*[3]/text()'
    response = requests.get(url=xici_http_url,headers=headers)
    html_tree = etree.HTML(response.text)
    ip_list = html_tree.xpath(all_ip_xpath)
    port_list = html_tree.xpath(all_prot_xpath)
    # print(ip_list)
    # print(prot_list)
    new_proxies_list = []
    for index in range(1,len(ip_list)):
      # print('http://{}:{}'.format(ip_list[index],port_list[index]))
      proxies_dict = {}
      proxies_dict['http'] = 'http://{}:{}'.format(str(ip_list[index]),str(port_list[index]))
      new_proxies_list.append(proxies_dict)
    proxies_list += new_proxies_list
    return proxies_list
  except Exception as e:
    print('发生了错误：url为 ',xici_http_url,'错误为 ',e)

if __name__ == '__main__':
  start_num = int(input('请输入起始页面：').strip())
  stop_num = int(input('请输入结束页面：').strip())
  print('开始爬取...')
  t_list = []
  # 容纳需要使用的西刺代理ip
  proxies_list = []
  # 使用多线程
  xici_urls = get_all_xici_urls(start_num,stop_num)
  for xici_get_url in xici_urls:
    #随机筛选一个useragent
    headers = {'User-Agent': random.choice(angents)}
    t = threading.Thread(target=get_all_http_ip,args=(xici_get_url,headers,proxies_list))
    t.start()
    t_list.append(t)
  for j in t_list:
    j.join()
  print('所有需要的代理ip已爬取完成...')
  print(proxies_list)
  print(len(proxies_list))

补充知识：python爬取xici的免费代理、并验证(重点、清楚)

网上爬取xici的帖子很多，但是验证都说的不是很清楚，这里我会认真给大家解释

这里我写了一个代理类proxy，写了四个方法（个人写法不必在意），get_user_agent（得到随机use-agent,请求头中最重要的一个）、get_proxy(爬取代理IP)、test_proxy(验证代理可用性）、store_txt(将可用的代理保存到txt文件中。

1.爬取：headers是请求头，choice是可以选择是爬取Http代理还是https代理，first、end为开始和结束的页码（结束不包含最后一页）

 def get_proxy(self, headers, choice='http', first=1, end=2):
    """
    获取代理
    :param choice:
    :param first: 开始爬取的页数
    :param end: 结束爬取的后一页
    :return:
    """

    ip_list = []
    base_url = None

    # 选择爬取的网站，一个是http、一个是https的
    if choice == 'http':
      base_url = 'http://www.xicidaili.com/wt/'
    elif choice == 'https':
      base_url = 'http://www.xicidaili.com/wn/'

    # 控制页码用正则匹配，并将爬取的IP和端口号用:链接
    for n in range(first, end):
      actual_url = base_url + str(n)
      html = requests.get(url=actual_url, headers=headers).text
      pattern = '(\d+\.\d+\.\d+\.\d+)</td>\s*<td>(\d+)'
      re_list = re.findall(pattern, html)

      for ip_port in re_list:
        ip_port = ip_port[0] + ':' + ip_port[1]
        ip_list.append(ip_port)
    return ip_list

2. 验证：网上大部分是用request直接请求一个网址看是否通过或者看状态码是否是200， 但是有一个问题是即使你设置了代理IP。可能会通过，但通过的不是用你设置的代理IP而是用你自己公网下的IP（大部分时候我们用ifconfig查询的是我们所在局域网下的IP，及私网IP）。

linux下你可以用这些命令的其中任何一个查看你的公网IP：

curl icanhazip.com
curl ifconfig.me
curl curlmyip.com
curl ip.appspot.com
curl ipinfo.io/ip
curl ipecho.net/plain
curl www.trackip.net/i

注意：那这样要怎么办，其实我们可以向上述命令一样先用你爬下的代理IP访问 http://icanhazip.com/， 它可以返回你电脑发送请求时的公网IP（此时如果你设置代理IP了就会是返回你所发送请求的代理IP），然后你将它爬取下来（直接获取返回的值的文本就可以了），并和你发送请求时的代理IP作比较，如果不相等说明此代理IP不能用，因为虽然你设置了代理Ip，但是电脑在你代理IP请求不同的情况下，直接又使用了你公网的IP去请求，当然成功了，但不代表你的代理IP可以用。如果相等，那就证明此网站就是你所用的代理IP访问请求成功的，所以此IP可用。

def test_proxy(self, ip_port, choice='http'):
    """
    测试代理是否能用
    :param ip_port:
    :param choice:
    :return:
    """
    proxies = None

    # 这个网站可以返回你公网下的IP，如果你加代理请求后，返回的就是你代理的IP（这样做是防止你虽然用的是代理IP，但实际是用你自己的公网IP访问的请求）
    tar_url = "http://icanhazip.com/"

    # 获取随机User-agent
    user_agent = self.get_user_agent()

    # 将user-agent放在headers中
    headers = {'User-Agent': user_agent}

    # 选择验证的是http、还是https
    if choice == 'http':
      proxies = {
        "http": "http://"+ip_port,
      }

    elif choice == 'https':
      proxies = {
        "https": "https://" + ip_port,
      }

    try:
      # 将IP从IP和端口号连起来的分出来
      thisIP = "".join(ip_port.split(":")[0:1])
      res = requests.get(tar_url, proxies=proxies, headers=headers, timeout=8)

      # 爬取下来返回的值，一定要用strip去除空格
      proxyIP = res.text.strip()

      # 三个状态，如过直接通不过，那就返回false，如果通过但是不是代理的IP，也返回false
      if proxyIP == thisIP:
        return proxyIP
      else:
        return False
    except:
      return False

最后附上整段代码：

import requests
import re
import random
import codecs
from urllib import parse


class proxy:
  """
  代理类
  """
  def __init__(self):
    pass

  def get_user_agent(self):
    """
    得到随机user-agent
    :return:
    """
    user_agents = [
      "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
      "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
      "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
      "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
      "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
      "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
      "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
      "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
      "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
      "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
      "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
      "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
      "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
      "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
      "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
      "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; .NET4.0C; .NET4.0E; LBBROWSER)",
      "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
      "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; .NET4.0C; .NET4.0E)",
      "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; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
      "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
      "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
      "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
      "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; .NET4.0C; .NET4.0E)",
      "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
      "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
      "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
      "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
      "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
      "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10"
    ]
    user_agent = random.choice(user_agents)
    return user_agent


  def get_proxy(self, headers, choice='http', first=1, end=2):
    """
    获取代理
    :param choice:
    :param first: 开始爬取的页数
    :param end: 结束爬取的后一页
    :return:
    """

    ip_list = []
    base_url = None
    if choice == 'http':
      base_url = 'http://www.xicidaili.com/wt/'
    elif choice == 'https':
      base_url = 'http://www.xicidaili.com/wn/'

    for n in range(first, end):
      actual_url = base_url + str(n)
      html = requests.get(url=actual_url, headers=headers).text
      pattern = '(\d+\.\d+\.\d+\.\d+)</td>\s*<td>(\d+)'
      re_list = re.findall(pattern, html)

      for ip_port in re_list:
        ip_port = ip_port[0] + ':' + ip_port[1]
        ip_list.append(ip_port)
    return ip_list


  def test_proxy(self, ip_port, choice='http'):
    """
    测试代理是否能用
    :param ip_port:
    :param choice:
    :return:
    """
    proxies = None
    # 这个网站可以返回你公网下的IP，如果你加代理请求后，返回的就是你代理的IP（这样做是防止你虽然用的是代理IP，但实际是用你自己的公网IP访问的请求）
    tar_url = "http://icanhazip.com/"
    user_agent = self.get_user_agent()
    headers = {'User-Agent': user_agent}
    if choice == 'http':
      proxies = {
        "http": "http://"+ip_port,
      }

    elif choice == 'https':
      proxies = {
        "https": "https://" + ip_port,
      }
    try:
      thisIP = "".join(ip_port.split(":")[0:1])
      res = requests.get(tar_url, proxies=proxies, headers=headers, timeout=8)
      proxyIP = res.text.strip()
      if proxyIP == thisIP:
        return proxyIP
      else:
        return False
    except:
      return False

  def store_txt(self, choice='http', first=1, end=2):
    """
    将测试通过的ip_port保存为txt文件
    :param choice:
    :param first:
    :param end:
    :return:
    """
    user_agent = self.get_user_agent()
    headers = {'User-Agent': user_agent}
    ip_list = self.get_proxy(headers=headers, choice=choice, first=first, end=end)
    with codecs.open("Http_Agent.txt", 'a', 'utf-8') as file:
      for ip_port in ip_list:
        ip_port = self.test_proxy(ip_port, choice=choice)
        print(ip_port)
        if ip_port:
          file.write('\'' + ip_port + "\'\n")

以上这篇Python使用requests xpath 并开启多线程爬取西刺代理ip实例就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持python博客。

标签：requests  urllib  

<< 上一篇 下一篇 >>

搜索

推荐资源

  Powered By python教程网   鲁ICP备18013710号
python博客 - 小白学python最友好的网站!