android 点击查看更多,Pyhton爬取“点击查看更多”后的隐藏内容

[Python] 纯文本查看 复制代码# -*- coding: utf-8 -*-

"""

[url=home.php?mod=space&uid=238618]@Time[/url] ： 2020/11/4 22:10

@Auth ： Ne-21

[url=home.php?mod=space&uid=267492]@file[/url] ：gp.py

@IDE ：PyCharm

@Motto：Another me.

"""

import re

import requests

url = 'http://guba.eastmoney.com/remenba.aspx?type=1&tab=2'

header = {

'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8',

'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1'

}

respond = requests.get(url, headers=header)

ggb = re.findall('

(.*?)

', respond.text)

match = re.compile('(.*?)')

shuju = re.findall(match, str(ggb))

with open('./msg.txt', 'a', encoding='utf-8') as f:

for i in shuju:

link = 'http://guba.eastmoney.com/'+str(i[0])

name = str(i[1])

text = name+'\t'+link+'\n'

print(text)

f.write(text)

print('完成')