看之前其他人写的爬站长图片代码,自己下载 后不能下载。经过反复调试,原来站长图片已对源代码做了修改,今天将自己调试成功的代码发表如下:
# 下载前十页的地址 # https://sc.chinaz.com/tupian/qinglvtupian.html 第一页 # https://sc.chinaz.com/tupian/qinglvtupian_2.html 第二页 import urllib.request from lxml import etree def create_request(page): if (page == 1): url = 'https://sc.chinaz.com/tupian/qinglvtupian.html' else: url = 'https://sc.chinaz.com/tupian/qinglvtupian_' + str(page) + '.html' headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36' } request = urllib.request.Request(url=url,headers=headers) return request def get_content(request): response = urllib.request.urlopen(request) content = response.read().decode('utf-8') return content def down_load(content): # 下载图片 # urllib.request.urlretrieve('图片名字','图片地址') tree = etree.HTML(content) name_list = tree.xpath('//div[@class="container"]//img/@alt') src_list = tree.xpath('//div[@class="container"]//img/@data-original') for i in range(len(name_list)): name = name_list[i] src =src_list[i] url = 'https:' + src urllib.request.urlretrieve(url=url,filename='./loveimg/' + name +'.jpg') if __name__== '__main__': start_page = int(input('请输入起始的页码:')) end_page = int(input('请输入结束的页码:')) for page in range(start_page,end_page+1): # 请求对象的定制 request = create_request(page) # 获取网页的源码 content = get_content(request) # 下载 down_load(content)