学习进度08

今天完成了北京市政百姓信件分析的一部分：

可以爬取网址，爬取信件内容，但是是静态的，只爬取一页

import urllib.request
import random
import json
import re
#取消证书验证
import ssl
ssl._create_default_https_context = ssl._create_unverified_context

def moni():
    #模拟请求头
    agentList=[
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36"
        "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0"
        "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)"
        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)"
    ]
    agentStr= random.choice(agentList)
    return agentStr


def urlCrawler(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', moni())
    response = urllib.request.urlopen(req)
    pattern = re.compile('', re.S)
    results = pattern.findall(response.read().decode('utf-8'))
    with open("E:/A.txt", "wb")as f:
        for result in results:
            a, b=result
            b=re.sub("\s","",b)
            if(a=="建议"):
                c="http://www.beijing.gov.cn/hudong/hdjl/com.web.suggest.suggesDetail.flow?originalId="+b
            elif(a=="咨询"):
                c="http://www.beijing.gov.cn/hudong/hdjl/com.web.consult.consultDetail.flow?originalId="+b
            f.write(c.encode("utf-8")+"\n".encode("utf-8"))

def htmlCrawler():
    for line in open("E:/A.txt"):
        req = urllib.request.Request(line)
        req.add_header('User-Agent', moni())
        response = urllib.request.urlopen(req)
        pattern = re.compile('
(.*?)', re.S)
        results = pattern.findall(response.read().decode('utf-8'))
        with open("E:/B.txt", "ab")as f:
            for result in results:
                result = re.sub("\s", "", result)
                f.write(result.encode("utf-8")+"\n".encode("utf-8"))

url="http://www.beijing.gov.cn/hudong/hdjl/com.web.search.replyMailList.flow"
urlCrawler(url)
htmlCrawler()

 效果：