web爬虫讲解—urllib库爬虫—实战爬取搜狗微信公众号—抓包软件安装Fiddler4讲解

封装模块

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import urllib
from urllib import request
import json
import random
import re
import urllib.error
def hq_html(hq_url):
    """
    hq_html()封装的爬虫函数，自动启用了用户代理和ip代理
    接收一个参数url,要爬取页面的url，返回html源码
    """
    def yh_dl():    #创建用户代理池
        yhdl = [
            'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
            'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0',
            'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
            'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
            'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
            'Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11',
            'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
            'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)',
            'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)',
            'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)',
            'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)',
            'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',
            'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)',
            'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)',
            'Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5',
            'User-Agent:Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5',
            'Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5',
            'Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1',