爬取信件信息（更新）

import requests
from bs4 import BeautifulSoup
from selenium import webdriver



url='http://www.beijing.gov.cn/hudong/hdjl/com.web.search.mailList.flow'
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:73.0) Gecko/20100101 Firefox/73.0'}

resp = requests.post(url, headers=headers)
#print(resp)
resp.encoding = resp.apparent_encoding  # 将网页返回的字符集类型设置为 自动判断的字符集类型
html = resp.text
# 解析成为beautiful对象
soup = BeautifulSoup(html, 'html.parser')
# print(soup)
result = soup.find('body').find('div', {'class': 'conouter'}).find('div', {'id': 'mailul'}).find_all('div', {
        'class': 'row clearfix my-2 list-group o-border-bottom2 p-3'})
# print(result)
for info in result:
     leixing = info.find('a').find('font').get_text()
     biaoti = info.find('a').find('span').get_text()
     shijian = info.find('div', {'class': 'o-font2 col-md-3 col-xs-12 text-muted'}).get_text()
     bumen = info.find('div', {'class': 'o-font2 col-md-5 col-xs-12 text-muted'}).get_text()
     str=('{} {} {} {}'.format(leixing[2:4],biaoti,shijian[5:],bumen[6:]))
     list=str.split()#分割空格
     #print(list)
#以字典格式输出
     dict={'leixing':'','biaoti':'','shijian':'','bumen':''}
     dict['leixing']=list[0]
     dict['biaoti'] = list[1]
     dict['shijian'] = list[2]
     dict['bumen'] = list[3]
     print(dict)
page=soup.find('body').find_all('div',{'id':'pageDiv1'})
print(page)

运行结果：

 现在只能爬一页，明天考虑翻页爬取，并提交到mysql数据库