爬取站长素材的免费简历模板代码分享

欢迎大家交流学习，来自B站 路飞学城IT 的“2020年Python爬虫全套课程（学完可做项目）” P28作业分享。

	# 导入使用的库
	import requests,os
	from lxml import etree
    # 网站和UA伪装
    url = 'https://sc.chinaz.com/jianli/free.html'
    headers = { 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.67 Safari/537.36',
        }
    # 调用request 和 etree 爬取并解析
    page_text = requests.get(url=url, headers=headers).content.decode('utf-8')
    tree = etree.HTML(page_text)
    ppt_list = tree.xpath('//div[@]//div/a')

    # 创建一个文件夹
    if not os.path.exists('./Cralwer_ppts'):
        os.mkdir('./Cralwer_ppts')
        
    # 爬取ppt的信息
    for ppt in ppt_list: # ppt = ppt_list[0]
        ppt_jpg_url = 'https:' + ppt.xpath('./img/@src')[0]
        ppt_title = ppt.xpath('./img/@alt')[0]
        ppt_url = 'https:'+ ppt.xpath('@href')[0]
        
        # 爬取ppt 压缩包的连接
        ppt_text = requests.get(url=ppt_url, headers=headers).content.decode('utf-8')
        tree = etree.HTML(ppt_text)
        ppt_rar = requests.get(tree.xpath('//div[@]/ul/li/a/@href')[0]).content
        
        # 保存文件到文件夹
        with open('./Cralwer_ppts/%s.zip'% ppt_title,'wb') as fp:
            fp.write(ppt_rar)
        print('下载完成——%s'% ppt_title)