python 爬虫表情包爬取自编

#!/usr/bin/env python# -*- coding: utf-8 -*-# @Time: 2020/12/7 19:12# @Author: huni# @File: 表情包单函数.py# @Software: PyCharmimport requestsfrom lxml import etreeimport osfrom urllib import parseif __name

m0_50944918

331917人浏览 · 2020-12-08 09:27:40

m0_50944918 · 2020-12-08 09:27:40 发布

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2020/12/7 19:12
# @Author  : huni
# @File    : 表情包单函数.py
# @Software: PyCharm
import requests
from lxml import etree
import os
from urllib import parse

if __name__ == '__main__':
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36'
    }
    page = 2
    title_path = './表情包'
    if not os.path.exists(title_path):
        os.mkdir(title_path)

    for i in range(1,page+1):
        url = f'https://fabiaoqing.com/biaoqing/lists/page/{i}.html'
        resp = requests.get(url=url,headers=headers).text
        tree = etree.HTML(resp)
        div_list = tree.xpath('//div[@class="ui segment imghover"]/div')
        for div in div_list:
            src = div.xpath('./a/img/@data-original')[0].replace('bmiddle','large')
            name = div.xpath('./a/img/@title')[0]
            jpgdata = requests.get(url=src,headers=headers).content
            jpgname = name[:20] + '.' +src.split('.')[-1]
            jpgname = jpgname.replace(':','')
            jpgpath = title_path + '/' + jpgname.replace('?','')

            with open(jpgpath,'wb') as fp:
                fp.write(jpgdata)
                print(jpgname,'下载完成')