使用python lxml抓取多个页面的Glassdoor

pip install lxml

import requests
from lxml import etree

def scrape_glassdoor(url):
    response = requests.get(url)
    html = response.text
    tree = etree.HTML(html)
    # 在这里可以使用XPath表达式提取所需的数据
    # 例如：job_titles = tree.xpath('//div[@class="job-title"]/text()')
    #      company_names = tree.xpath('//div[@class="company-name"]/text()')
    #      ...
    # 返回提取的数据
    # return job_titles, company_names, ...

urls = ['https://www.glassdoor.com/page1', 'https://www.glassdoor.com/page2', 'https://www.glassdoor.com/page3']
results = []
for url in urls:
    data = scrape_glassdoor(url)
    results.append(data)