动图爬取

居然搞笑网https://www.zbjuran.com

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/4/21 14:24
# @Author  : Xinru

import requests
import re,os,time
import threading
from lxml import etree

new_flie = '动态图'
if not os.path.exists(new_flie):
    os.mkdir(new_flie)

def download(filename,img):
    try:
        i = requests.get(img, timeout=(3, 7))
        with open('./' + new_flie + '/{}'.format(filename), 'wb') as f:
            f.write(i.content)
            f.close()
            print(filename)
    except:
        print('error','URL打不开',img)

def main(url,ii):
    start_time = time.time()
    html = requests.get(url)
    html.encoding = 'gb2312'
    div = etree.HTML(html.text)  
    imgs = div.xpath('//div[@class="text"]/p/img/@src')  
    names = div.xpath('//div[@class="item"]/h3/a/b/text()')
    for img, name in zip(imgs, names):
        # print(img, name)
        img = 'https://www.zbjuran.com'+img
        filename = name + '.' + img.split('.')[-1]
        # print(filename)
        download(filename, img)
    end_time = time.time()
    print('第-----'+str(ii)+'-----页下载完毕',round(end_time - start_time,1),'秒')
if __name__ == '__main__':
    for ii in range(34,2527):
        url = 'https://www.zbjuran.com/dongtai/list_4_'+str(ii)+'.html'
        print('第-----%d-----页 准备' % ii)
        main(url,ii)