python crawl

最新推荐文章于 2024-10-02 00:15:00 发布

leiline

最新推荐文章于 2024-10-02 00:15:00 发布

阅读量2k

点赞数

分类专栏：爬虫文章标签： python 爬虫

本文链接：https://blog.csdn.net/leiline/article/details/54834769

版权

爬虫专栏收录该内容

3 篇文章 0 订阅

订阅专栏

python爬虫下载页面代码备用。

# -*- coding:utf-8 -*-
import requests
import re
import random

class download:

    def __init__(self):
        self.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"
        ]
        self.iplist = []

    def get(self, url, timeout, proxy=None, num_retries = 6):
        UA = random.choice(self.user_agent_list)
        headers = {
            'User-Agent': UA,
            'Accept': "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
            'Accept-Encoding': 'gzip, deflate, sdch',
        }

        if proxy == None:
            try:
                response = requests.get(url, headers = headers)
                return response
            except:
                if num_retries > 0:
                    time.sleep(10)
                    print(u'获取网页出错，10S后将获取倒数第：', num_retries, u'次')
                    return self.get(url, timeout, num_retries-1)
                else:
                    print(u'开始使用代理')
                    time.sleep(10)
                    IP = ''.join(str(random.choice(self.iplist)).strip())
                    proxy = {'http': IP}
                    return self.get(url, timeout, proxy,)
        else:
            try:
                IP = ''.join(str(random.choice(self.iplist)).strip())
                proxy = {'http': IP}
                response = requests.get(url, headers=headers, proxies = proxy)
                return response 
            except:
                if num_retries > 0:
                    time.sleep(10)
                    IP = ''.join(str(random.choice(self.iplist)).strip())
                    proxy = {'http': IP}
                    print(u'获取网页出错，10S后将获取倒数第：', num_retries, u'次')
                    print(u'开始使用代理')
                    return self.get(url, timeout, proxy, num_retries-1)
                else:
                    print(u'代理也不好使了！取消代理')
                    return self.get(url, 3)

    def analysis(self):

        html = self.get("http://haoip.cc/tiqu.htm", 3)
        iplistn = re.findall(r'r/>(.*?)<b', html.text, re.S)
        for ip in iplistn:
            i = re.sub('\n', '', ip)
            self.iplist.append(i.strip())
            print(i.strip())
        print (self.iplist)

Download = download()
Download.analysis()