Python：爬虫爬取妹子网图片-文件爬取

import requests

 

import os

 

from lxml import etree

headers = {

 

    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36',

 

    'Referer': 'http://www.mzitu.com'}

 

# URL列表

 

urls = ["https://www.mzitu.com/page/{}".format(str(i)) for i in range(2, 11)]

 

# 路径，可以更改成你的路径

 

path = 'G:/photo/'

 

 

# 获取图片并写入本地文件

 

def get_girlphoto(url):

    data = requests.get(url, headers=headers)

 

    selector = etree.HTML(data.text)

 

    # 获取图片的URL列表

 

    girlphoto_urls = selector.xpath('//div/ul/li/a/img/@data-original')

 

    print(girlphoto_urls)

 

    # 循环每个图片链接并写入本地文件，写入要用二进制

 

    for item in girlphoto_urls:

        data = requests.get(item, headers=headers)

        with open(path + item[-10:], 'wb') as f:

            f.write(data.content)

 

            f.close()

 

 

if __name__ == '__main__':  # 主函数

 

    # 循环URL

 

    for url in urls:

        get_girlphoto(url)