互联网企业裁员潮背后的就业危机与机遇-采集招聘信息

# 导入模块
import csv
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.proxy import Proxy, ProxyType

# 设置爬虫代理标准版的代理IP和端口，以及用户名和密码
proxy_ip = "www.16yun.cn:3111"
proxy_user = "16YUN"
proxy_pwd = "16IP"

# 创建一个Proxy对象，并设置其属性
prox = Proxy()
prox.proxy_type = ProxyType.MANUAL
prox.http_proxy = f"http://{proxy_user}:{proxy_pwd}@{proxy_ip}"
prox.https_proxy = f"https://{proxy_user}:{proxy_pwd}@{proxy_ip}"
prox.ftp_proxy = f"ftp://{proxy_user}:{proxy_pwd}@{proxy_ip}"
prox.ssl_proxy = f"https://{proxy_user}:{proxy_pwd}@{proxy_ip}"

# 创建一个webdriver.DesiredCapabilities.CHROME字典，并将Proxy对象添加到其capabilities属性中
capabilities = webdriver.DesiredCapabilities.CHROME
prox.add_to_capabilities(capabilities)

# 设置chromedriver路径，并传入capabilities字典作为desired_capabilities参数
driver = webdriver.Chrome(executable_path='./chromedriver.exe', desired_capabilities=capabilities)

# 打开linkedin招聘页面
url = 'https://www.linkedin.com/jobs/search?keywords=Data%20Scientist&location=Toronto%2C%20Ontario%2C%20Canada&geoId=100025096&trk=public_jobs_jobs-search-bar_search-submit&redirect=false&position=1&pageNum=0'
driver.get(url)

# 获取网页源代码
job_src = driver.page_source

# 创建beautifulsoup对象
soup = BeautifulSoup(job_src, 'lxml')

# 提取所有职位信息的标签
jobs = soup.find_all('li', class_='result-card job-result-card result-card--with-hover-state')

# 创建空列表存储数据
job_id = []
job_title = []
company_name = []
location = []
date = []
job_link = []

# 遍历每个职位标签，提取数据并添加到列表中
for job in jobs:
    # 提取职位id
    job_id.append(job['data-id'])
    # 提取职位标题
    job_title.append(job.find('h3', class_='result-card__title job-result-card__title').text)
    # 提取公司名称
    company_name.append(job.find('h4', class_='result-card__subtitle job-result-card__subtitle').text)
    # 提取地点
    location.append(job.find('span', class_='job-result-card__location').text)
    # 提取日期
    date.append(job.find('time', class_='job-result-card__listdate')['datetime'])
    # 提取链接
    job_link.append(job.find('a', class_='result-card__full-card-link')['href'])

# 创建csv文件并写入数据    
with open('linkedin_jobs.csv', 'w', newline='', encoding='utf-8') as f:
    writer = csv.writer(f)
    writer.writerow(['Job ID', 'Job Title', 'Company Name', 'Location', 'Date', 'Job Link'])
    for i in range(len(job_id)):
        writer.writerow([job_id[i], job_title[i], company_name[i], location[i], date[i], job_link[i]])

# 关闭浏览器        
driver.close()