使用request+lxml实现简单的爬虫爬取简历模版

import requests
from lxml import etree

if __name__ == '__main__':
    #被爬取的url地址
    url = 'http://jianlimb.cn/biaogejianlimoban/'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:95.0) Gecko/20100101 Firefox/95.0'
    }
    page_text = requests.get(url=url,headers=headers).text
    #实例化类对象
    tree = etree.HTML(page_text)

    li_list = tree.xpath('//div[@class="pic-item-list oh"]//li')
    #获取读取到的li列表，重列表中拼接url地址，并保存文件到本地
    for li in li_list:
        img_url = li.xpath('./a/@href')[0]
        img_title = li.xpath('./a/div[@class="pic-item-image pr"]/span/img/@alt')[0]
        img_down = li.xpath('./a/div[@class="pic-item-image pr"]/span/img/@data-original')[0]
        # print(img_url,img_title)

        data = requests.get(url=img_url,headers=

标签：__,xpath,lxml,img,url,request,li,爬取,headers
来源： https://blog.csdn.net/qq_39885923/article/details/122511317