运行代码前记得先翻墙！！！，还有你使用的账号得开通领英会员，否则员工具体信息看不到！
1、所需的环境如下
pyjson
selenium
2、代码中需要导入`chromedriver.exe`驱动，我会放在文章后最后
3、总代码如下。
#需要翻墙才能登陆领英国际版
import json
import math
from selenium import webdriver
from selenium.webdriver.common.by import By
import time
import re
from selenium.webdriver.chrome.options import Options
#不弹出浏览器，无头操作，可选择使用
# chrome_options = Options()
# chrome_options.add_argument('--headless')
chrome = webdriver.Chrome(executable_path=r'chromedriver.exe')#导入驱动路径
#在领英上搜索的公司，点击'查看全部会员结果'后的链接网址
chrome.get('https://www.linkedin.com/search/results/people/?keywords=%E5%8C%BB%E8%8D%AF%E7%8C%8E%E5%A4%B4&origin=SWITCH_SEARCH_VERTICAL&page=1&sid=CkF')#请求网址
time.sleep(2)
#定位到密码登陆按钮
password_login = chrome.find_element(By.XPATH,'/html/body/div[1]/main/p[1]/a')
#点击密码登陆
password_login.click()
time.sleep(2)
#定位用户名框并输入
user_name = chrome.find_element(By.XPATH,'//*[@id="username"]')
user_name.clear()#先清空
user_name.send_keys('***')#你的账号
time.sleep(2)
#定位密码框并输入
pass_word = chrome.find_element(By.XPATH,'//*[@id="password"]')
pass_word.clear()#先清空
pass_word.send_keys('***')#你的密码
time.sleep(2)
#点击登录键
login_icon = chrome.find_element(By.XPATH,'//*[@id="organic-div"]/form/div[3]/button')
login_icon.click()
time.sleep(2)
#获得总页数
total_page = chrome.find_element(By.XPATH,'//*[@id="main"]/div/div/h2').text#定位
a = re.findall('\d*',total_page)#利用正则提取字符串中数字，人物数字此时为str
a = ''.join(a)
total_page = math.ceil(int(a)/10)#向上取整，得到总页数
if total_page > 100:#最多显示一百页
total_page = 100
time.sleep(2)
item={}#定义空字典
for i in range(1,total_page+1):
chrome.get(f'https://www.linkedin.com/search/results/people/?keywords=%E5%8C%BB%E8%8D%AF%E7%8C%8E%E5%A4%B4&origin=SWITCH_SEARCH_VERTICAL&page={i}')#翻页操作
node_list= chrome.find_element(By.XPATH,'//*[@id="main"]/div/div/div[1]/ul/li/div/div/div[2]/div[1]/div[1]/div/span[1]/span/a')#存储人物信息href列表
#循环爬取节点列表中的内容
for node in node_list:
#得到跳转链接，重新加载页面
node = node_list.get_attribute('href')#提取出每个href
time.sleep(2)
chrome.get(node)#用浏览器重新get href
time.sleep(2)
name = chrome.find_element(By.XPATH,'//*[@id="main"]/section[1]/div[2]/div[2]/div[1]/div[1]/h1').text#姓名
title = chrome.find_element(By.XPATH,'//*[@id="main"]//section[1]/div[2]/div[2]/div[1]/div[2]').text#职位
location = chrome.find_element(By.XPATH,'//*[@id="main"]/section[1]/div[2]/div[2]/div[2]/span[1]').text#地点
#个人简介
try:
individual_resume = chrome.find_element(By.XPATH,'//*[@id="about"]/../div[3]').text
individual_resume = individual_resume.split('\n')[1::2] # 简介重复2次，只取偶数，按偶数分割列表
individual_resume = ','.join(individual_resume)
except:
individual_resume = 'None'
# 工作经历
try:
work_experience = chrome.find_element(By.XPATH,'//*[@id="experience"]/../div[3]').text
work_experience = work_experience.split('\n')[1::2] # 按偶数分割列表
work_experience = ','.join(work_experience)
except:
work_experience = 'None'
#教育经历
try:
education_experience = chrome.find_element(By.XPATH,'//*[@id="education"]/../div[3]').text
education_experience = education_experience.split('\n')[1::2] # 按偶数分割列表
education_experience = ','.join(education_experience)
except:
education_experience = 'None'
#技能
try:
ability = chrome.find_element(By.XPATH,'//*[@id="skills"]/../div[3]').text
ability = ability.split('\n')[1::2] # 按偶数分割列表
ability = ','.join(ability)
except:
ability = 'None'
#用字典存储信息
item['name'] = name
item['title'] = title
item['location'] = location
item['info'] = individual_resume
item['experience'] = work_experience
item['education'] = education_experience
item['ability'] = ability
try:
path = r'data/'#保存路径
#用人名给每个人的信息做保存文件的名字
set2 = r'[?*/\|:><"]'#利用正则表达去掉不能命名的字符
name = re.sub(set2,"",name)
with open(path+f'{name}.json','a',encoding='utf-8') as f:
f.write(json.dumps(item,ensure_ascii=False)+ ',\n')
except IOError as err:
print('error:' + str(err))
finally:
f.close()
time.sleep(3)
time.sleep(2)
#休息5秒关闭浏览器
time.sleep(5)
chrome.quit()7、chromedriver.exe驱动的下载地址：
链接：https://pan.baidu.com/s/1ATLdFEQfVvCzLpSqd2W3Mg?pwd=5555&_at_=1662003753714
提取码：5555