首页 > 技术文章 > python+selenium+无头浏览器,爬取猎聘python职位名称+详情页url

yangxh 2020-10-06 23:26 原文

 1 from selenium.webdriver.chrome.options import Options
 2 from selenium import webdriver
 3 from selenium.webdriver import ChromeOptions
 4 
 5 
 6 if __name__ == '__main__':
 7    
 8     url = 'https://www.liepin.com/zhaopin/?sfrom=click-pc_homepage-centre_searchbox-search_new&d_sfrom=search_fp&key=python'
 9    
10     chrome_options = Options()
11     chrome_options.add_argument('--headless')
12     chrome_options.add_argument('--disable-gpu')
13 
14     option = ChromeOptions()
15     option.add_experimental_option('excludeSwitches', ['enable-automation'])
16 
17     driver = webdriver.Chrome(chrome_options=chrome_options, options=option)
18     driver.get(url)
19     li_list = driver.find_elements_by_xpath('//*[@id="sojob"]/div[2]/div/div[1]/div[1]/ul/li')
20     for li in li_list:
21         name = li.find_element_by_xpath('./div/div[1]/h3/a').text
22         detail_url = li.find_element_by_xpath('./div/div[1]/h3/a').get_attribute('href')
23         print(name)
24         print(detail_url)

 

推荐阅读