Python爬虫风景素材爬取

最新推荐文章于 2024-07-04 23:15:41 发布

m0_53460357

最新推荐文章于 2024-07-04 23:15:41 发布

阅读量1k

点赞数

文章标签： python 爬虫风景

本文链接：https://blog.csdn.net/m0_53460357/article/details/133221926

版权

import urllib.request
from  lxml import  etree
urlbig='https://sc.chinaz.com/'


def create_page(page):
    if page==1:
        url = 'https://sc.chinaz.com/tupian/fengjing.html'
    else:
        url = f'https://sc.chinaz.com/tupian/fengjing_'+str(page)+'.html'#页面上url


    headers = {'User-Agent':
	'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/117.0'}

    request = urllib.request.Request(url=url,headers=headers)


    return request

#解析源码
def get_content(request):
    respones = urllib.request.urlopen(request)
    content = respones.read().decode('utf-8')
    # print(content)
    return content


def down_load(content):
    tree = etree.HTML(content)#下载图片
    name_list=tree.xpath ( '//div[@data-waterfall="true"]/div/img/@alt' )
    src_data = tree.xpath ( '//div[@data-waterfall="true"]/div/div/a/@href' )#详情页URL
    # print(name_list,src_data)

    # print(name_list,src_data)
    for i in range(len(name_list)):
        name = name_list[i]
        src  = src_data[i]
        url = urlbig+src
        headers = {'User-Agent':
                       'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/117.0'}
        request = urllib.request.Request ( url=url, headers=headers )
        respones = urllib.request.urlopen ( request )
        content = respones.read ( ).decode ( 'utf-8' )
        tree_1 = etree.HTML(content)
        url_big = tree_1.xpath("//p[@class='bg-bull btn-p com-right-down-btn']/a/@href")
        url_big = url_big[0]

        urllib.request.urlretrieve(url=url_big,filename=name +'.jpg')
        print(name,url_big,'下载成功')
        #

        #拼起来的详情页地址


if __name__ == '__main__':
    start_page =int(input('请输入初始页面'))
    end_page = int(input('请输入结束页面'))

    for page in range(start_page,end_page+1):
        #1.请求对象的定制
        request = create_page(page)
        #2.网页获取源码
        content=get_content (request)
        # 3.下载图片
        down_load(content)