Python爬虫：selenium+xpath爬取腾讯招聘

#selenium 爬取javascript编写的网页
#使用xpath
#爬取职位名称以及基本介绍

直接上代码！！！

from selenium import webdriver
from lxml import etree

# 创建tecent类
class tencent(object):
    # 构造函数带参数url
    def __init__(self, url):
        self.url = url

    # 保存文件为doc格式
    def save(self, content):
        with open('tencent.doc', 'a+', encoding='utf-8')as file:
            file.write(content+'\n')

    # 主程序编写
    def driver(self):
        driver = webdriver.PhantomJS()#自动驱动PhantonJS获取源代码
        driver.get(url)
        response = driver.page_source#获取原码
        items = etree.HTML(response)#xapth提取数据
        tables = items.xpath('//div[@class="recruit-list"]')
        for table in tables:
            title = table.xpath('.//a/h4/text()')[0]#提取岗位名
            info = table.xpath('.//a/p[2]/text()')[0]#提取简介信息
            information = [title, info]
            content = '\n'.join(information)#列表转成字符串
            self.save(content)#调用保存函数
            print(title)#控制台显示
            print(info)

if __name__ == '__main__':
    for i in range(1, 417):         #翻页构造url
        url = 'https://careers.tencent.com/search.html?&index=%s' % str(i)
        main = tencent(url)         #创建类对象main
        main.driver()               #调用类函数
        print('***'*50)             #控制台没输出一页信息打印50组***

 爬取结果截图：：