python爬取论坛图片_python爬取某网站妹子图集

import requests

from lxml import etree

import time

import os

import re

def huoquyuanma(url = 'https://www.tujigu.com/'):

headers = {

'Accept': '*/*',

'Accept-Language': 'en-US,en;q=0.8',

'Cache-Control': 'max-age=0',

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36',

'Connection': 'keep-alive',

'Referer': 'http://www.baidu.com/'

}

try:

new = requests.get(url , headers=headers , timeout = 16)  #获取源码

time.sleep(2)                                       #等待

new.encoding = new.apparent_encoding   #防乱码

t = new.text

t = etree.HTML(t)   #转换成xml格式

return