python 爬虫 表情包爬取自编-爱代码爱编程
#!/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')
版权声明:本文为博主原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。 本文链接: https://blog.csdn.net/m0_50944918/article/details/110850328