爬取防盗链图片福利你懂得

爬取防盗链图片

import urllib.request
from lxml import etree
import time
import os

headers = {
       'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',
       #防盗链图片必须填写首页地址信息
       'Referer': 'http://www.mmjpg.com/',
   }
#随机名字函数
def random_string(length=5):
    import random
    base_dir = 'zxcvbnmasdfghjkqwertyuio123456789'
    return ''.join(random.choice(base_dir) for i in range(length))
def parse_img(img,page):
    tree = etree.HTML(img)
    img_urls = tree.xpath('//div[@class="main"]/div[@class="pic"]/ul/li/a/img/@src')
    for url in img_urls:
        print("开始爬取...")
        # 构建请求对象
        request = urllib.request.Request(url=url, headers=headers)
        #发送请求，得到响应
        response = urllib.request.urlopen(request)
        #图片名
        image_name = random_string()
        #拼接文件名，图片名+后缀
        filename = image_name + '.' + url.split('.')[-1]
        #存入文件夹路径
        dirname = 'meitu'
        #拼接路径
        path = os.path.join(dirname, filename)
        #写入
        with open(path, 'wb') as fp:
            fp.write(response.read())
            print("结束爬取",filename)
            #停留2秒，过快可能导致封IP
            time.sleep(2)
    time.sleep(1)
#构建请求对象
def handle_request(url,page):
    url= url.format(page)
    request = urllib.request.Request(url=url,headers=headers)
    return request
#主函数
def main():
    start_page = int(input("起始页输入2"))
    end_page = int(input('结束页，每页15张图片，目前不知有多少页'))
    #换页路径
    url = 'http://www.mmjpg.com/home/{}'
    for page in range(start_page,end_page+1):
        request = handle_request(url,page)
        img = urllib.request.urlopen(request).read()
        img_urls = parse_img(img,page)

if __name__ == '__main__':
    main()