#!/usr/bin/env python # -*- coding: utf-8 -*- # Created by Fzy on 2019/1/22 13:35 import requests import re from bs4 import BeautifulSoup url = 'https://www.537uu.com/meinv/26089.html' headers = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) \ Chrome/70.0.3538.102 Safari/537.36' } r = requests.get(url, headers=headers) r.encoding = 'utf-8' # print(r.text) html = r.text # 方法一 us = re.findall(r'data-original="(.*?)"', html, re.S) # print(us) for u in us: # print(u) ur = u.split('/') # print(ur[-1]) filename = ur[-1] res = requests.get(u) with open(filename, 'wb') as file: file.write(res.content) print(filename+' 已下载完成!') # 方法二 # soup = BeautifulSoup(html, 'lxml') # us = soup.find_all('img', class_="videopic lazy") # for u in us: # u = u.get('data-original') # # print(u) # ur = u.split('/') # # print(ur[-1]) # filename = ur[-1] # res = requests.get(u) # with open(filename, 'wb') as file: # file.write(res.content) # print(filename+' 已下载完成!')