photos

#需求：抓取xx网图片

import requests  #对目标网址发起get请求
from lxml import etree   #解析路径

# 分析一下网址（每一页网址的规律）
"""
https://pic.netbian.com/4kmeishi/
https://pic.netbian.com/4kmeishi/index_2.html
https://pic.netbian.com/4kmeishi/index_3.html
"""
headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36'
    }
# 暂时只抓取第一页的内容
url = 'https://pic.netbian.com/4kmeishi/'
# 使用requests库对目标url发起get请求
response = requests.get(url=url,headers = headers)
# 将响应的内容转成html标签
root =etree.HTML(response.content)

#使用xpath来解析路径获取最终的目标数据
# 获取图片的网址
# //:表示全局变量
img_src_list = root.xpath('//ul[@class="clearfix"]/li/a/img/@src')
# print(img_src_list)

#获取每张图片的名称
img_name_list = root.xpath('//ul[@class="clearfix"]/li/a/b/text()')
# print(img_name_list)

for src,name in zip(img_src_list,img_name_list):
    #拼接完整的网址
    src = 'https://pic.netbian.com' + src
    #对单个图片的网址发起get请求
    img_response = requests.get(url=src,headers =headers )
    #保存图片
    file = open(name+'.jpg','wb')
    file.write(img_response.content)
    file.close()