python爬取站长之家植物图片

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

 def handle_request(url,page):
     if page == 1:
         url = url.format('')
     else:
         url = url.format('_'+str(page))
     headers = {
         "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36"
     }
     request = urllib.request.Request(url=url,headers=headers)

     return request

 def download_img(image_src):
     dirpath = r'G:/untitled/zhiwu'
     if not os.path.exists(dirpath):
         os.mkdir(dirpath)
     # 文件名
     filename= os.path.basename(image_src)
     # 文件路径
     filepath = os.path.join(dirpath, filename)
     # 发送请求保存图片
     headers = {
         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36"
     }
     request = urllib.request.Request(url=image_src, headers=headers)
     response = urllib.request.urlopen(request)
     print(response)
     with open(filepath,'wb') as fp:
         fp.write(response.read())

 def parse_content(content):
     # 解析内容,获取图片
     tree = etree.HTML(content)
     image_list = tree.xpath('//div[@id="container"]/div/div/a/img/@src')
     for image_src1 in image_list:
         image_src = image_src1.split('/')[-1]
         download_img(image_src)

 def main():
     url = 'http://sc.chinaz.com/tupian/huadetupian{}.html'
     start_page = int(input('请输入起始页码:'))
     end_page = int(input('请输入结束页码:'))
     for page in range(start_page, end_page + 1):
         request = handle_request(url, page)
         content = urllib.request.urlopen(request).read().decode()
         parse_content(content)
         time.sleep(1)

 if __name__ == '__main__':
     main()