我要更多好玩的表情包——python3实现简单循环抓取并下载图片(二)

一、项目简介

1.内容：抓取 斗图啦   的表情包保存在本地

2.解析：xpath

3.涉及类库：lxml、requests

二、代码

# python
# -*- coding:utf-8 -*-
# author:Only time:2019/8/19


import requests
from lxml import etree


def get_url():
    urllist = []
    for url in range(1,3):
        URL = 'https://www.doutula.com/photo/list/?page=' + str(url)
        urllist.append(URL)
    return urllist


def url_html_parse_save():

    header = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360SE'
    }
    number = 0
    for url in get_url():
        number += 1
        response = requests.get(url,headers=header)
        print(response.status_code)
        response = response.text

        html = etree.HTML(response)
        divs = html.xpath('//div[@class="page-content text-center"]//a')

        for div in divs:
            name = div.xpath('.//p/text()')[0]
            img = div.xpath('.//img[@referrerpolicy="no-referrer"]/@data-original')[0]
            print(name)
            image = requests.get(img).content  # 照片的二进制编码

            with open('./图片/%s.jpg' % name, 'wb') as f:
                f.write(image)
        print('第'+str(number)+'页保存成功')


def run():
    url_html_parse_save()


if __name__ == "__main__":
    run()

三、运行结果