用python在前程无忧高效投递简历

网络爬虫

浏览数:128

2019-5-10

 在前程无忧上投递简历发现有竞争力分析,免费能看到匹配度评价和综合竞争力分数,可以做投递参考

计算方式

 综合竞争力得分应该越高越好,匹配度评语也应该评价越高越好

抓取所有职位关键字搜索结果并获取综合竞争力得分和匹配度评语,最后筛选得分评语自动投递合适的简历

登陆获取cookie

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
chrome_options = Options()
# chrome_options.add_argument('--headless')
from time import sleep
import re
from lxml import etree
import requests
import os
import json

driver = webdriver.Chrome(chrome_options=chrome_options,executable_path = 'D:\python\chromedriver.exe')
headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"}
driver.get("https://search.51job.com/list/020000,000000,0000,00,9,99,%2520,2,1.html?lang=c&stype=&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&providesalary=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=&dibiaoid=0&address=&line=&specialarea=00&from=&welfare=")

webdriver需要在相应域名写入cookie,所以转到职位搜索页面

def get_cookie():
driver.get("https://login.51job.com/login.php?loginway=1&lang=c&url=")
sleep(2)
phone=input("输入手机号:")
driver.find_element_by_id("loginname").send_keys(phone)
driver.find_element_by_id("btn7").click()
sleep(1)
code=input("输入短信:")
driver.find_element_by_id("phonecode").send_keys(code)
driver.find_element_by_id("login_btn").click()
sleep(2)
cookies = driver.get_cookies()
with open("cookie.json", "w")as f:
f.write(json.dumps(cookies))

检查cookie文件是否存在,如果不存在执行get_cookie把cookie写入文件,在登陆的时候最好不用无头模式,偶尔有滑动验证码

前程无忧手机短信一天只能发送三条,保存cookie下次登陆用

def get_job():
    driver.get("https://search.51job.com/list/020000,000000,0000,00,9,99,%2520,2,1.html?lang=c&stype=&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&providesalary=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=&dibiaoid=0&address=&line=&specialarea=00&from=&welfare=")
    sleep(2)
    job=input("输入职位:")
    driver.find_element_by_id("kwdselectid").send_keys(job)
    driver.find_element_by_xpath('//button[@class="p_but"]').click()
    url=driver.current_url
    page=driver.page_source
    return url,page

在职位搜索获取职位搜索结果,需要返回页面源码和地址

 

分析页码结构html前的是页码,全部页码数量通过共XX页得到

def get_pages(url,page):
    tree=etree.HTML(page)
    href=[]
    x = tree.xpath('//span[@class="td"]/text()')[0]
    total_page=int(re.findall("(\d+)", x)[0])
    for i in range(1,total_page+1):
        href.append(re.sub("\d.html", f'{i}.html', url))
    return href

获取全部页码

 

def get_job_code(url):
    headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"}
    r=session.get(url,headers=headers)
    tree=etree.HTML(r.text)
    divs=tree.xpath('//div[@class="el"]/p/span/a/@href')
    job=str(divs)
    job_id=re.findall("\/(\d+).html",job)
    return job_id

获取职位id

修改id请求网址到竞争力分析页面

def get_info(job_id):
    href=f"https://i.51job.com/userset/bounce_window_redirect.php?jobid={job_id}&redirect_type=2"
    r=session.get(href,headers=headers)
    r.encoding=r.apparent_encoding
    tree=etree.HTML(r.text)
    pingjia=tree.xpath('//div[@class="warn w1"]//text()')[0].strip()
    gongsi=[]
    for i in tree.xpath('//div[@class="lf"]//text()'):
        if i.strip():
            gongsi.append(i.strip())
    fenshu=[]
    for i in tree.xpath('//ul[@class="rt"]//text()'):
        if i.strip():
            fenshu.append(i.strip())
    url=f"https://jobs.51job.com/shanghai/{job_id}.html?s=03&t=0"
    return {"公司":gongsi[1],"职位":gongsi[0],"匹配度":pingjia,fenshu[3]:fenshu[2],"链接":url,"_id":job_id}

抓取竞争力分析页面,返回一个字典

主程序

if not os.path.exists(“cookie.json”):
  get_cookie()
f=open(“cookie.json”,”r”)
cookies=json.loads(f.read())
f.close()

检查cookie文件载入cookie,不存在执行get_cookie()把cookie保存到文件

session = requests.Session()
  for cookie in cookies: 
  driver.add_cookie(cookie)
session.cookies.set(cookie['name'],cookie['value'])
url, page = get_job()
driver.close()

在session和webdriver写入cookie登陆

获取第一页和url后webdriver就可以关掉了

code=[]
for i in get_pages(url,page):
    code=code+get_job_code(i)

获取的职位id添加到列表

import pymongo
client=pymongo.MongoClient("localhost",27017)
db=client["job_he"]
job_info=db["job_info"]
for i in code:
    try:
        if not job_info.find_one({"_id":i}):
            info=get_info(i)
            sleep(1)
            job_info.insert_one(info)
            print(info,"插入成功")
  except: print(code)

龟速爬取,用MongDB保存结果,职位id作为索引id,插入之前检查id是否存在简单去重减少访问

吃完饭已经抓到8000个职位了,筛选找到127个匹配度好的,开始批量投递

登陆状态点击申请职位,用wevdriver做

for i in job_info.find({"匹配度":{$regex:"排名很好"},"综合竞争力得分":{$gte:"80"}}):
    print(i)
    try:
        driver.get(i)
        driver.find_element_by_id("app_ck").click()
        sleep(2)
    except:
        pass

用cookie登陆简单for循环投递,在Mongodb里查表,正则筛选匹配度和竞争力得分获取所有匹配结果

 

投递成功

代码

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
chrome_options = Options()
# chrome_options.add_argument('--headless')
from time import sleep
import re
from lxml import etree
import requests
import os
import json

driver = webdriver.Chrome(chrome_options=chrome_options,executable_path = 'D:\python\chromedriver.exe')
headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"}
driver.get("https://search.51job.com/list/020000,000000,0000,00,9,99,%2520,2,1.html?lang=c&stype=&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&providesalary=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=&dibiaoid=0&address=&line=&specialarea=00&from=&welfare=")

def get_cookie():
    driver.get("https://login.51job.com/login.php?loginway=1&lang=c&url=")
    sleep(2)
    phone=input("输入手机号:")
    driver.find_element_by_id("loginname").send_keys(phone)
    driver.find_element_by_id("btn7").click()
    sleep(1)
    code=input("输入短信:")
    driver.find_element_by_id("phonecode").send_keys(code)
    driver.find_element_by_id("login_btn").click()
    sleep(2)
    cookies = driver.get_cookies()
    with open("cookie.json", "w")as f:
        f.write(json.dumps(cookies))

def get_job():
    driver.get("https://search.51job.com/list/020000,000000,0000,00,9,99,%2520,2,1.html?lang=c&stype=&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&providesalary=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=&dibiaoid=0&address=&line=&specialarea=00&from=&welfare=")
    sleep(2)
    job=input("输入职位:")
    driver.find_element_by_id("kwdselectid").send_keys(job)
    driver.find_element_by_xpath('//button[@class="p_but"]').click()
    url=driver.current_url
    page=driver.page_source
    return url,page

def close_driver():
    driver.close()

def get_pages(url,page):
    tree=etree.HTML(page)
    href=[]
    x = tree.xpath('//span[@class="td"]/text()')[0]
    total_page=int(re.findall("(\d+)", x)[0])
    for i in range(1,total_page+1):
        href.append(re.sub("\d.html", f'{i}.html', url))
    return href

def get_job_code(url):
    headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"}
    r=session.get(url,headers=headers)
    tree=etree.HTML(r.text)
    divs=tree.xpath('//div[@class="el"]/p/span/a/@href')
    job=str(divs)
    job_id=re.findall("\/(\d+).html",job)
    return job_id

def get_info(job_id):
    href=f"https://i.51job.com/userset/bounce_window_redirect.php?jobid={job_id}&redirect_type=2"
    r=session.get(href,headers=headers)
    r.encoding=r.apparent_encoding
    tree=etree.HTML(r.text)
    pingjia=tree.xpath('//div[@class="warn w1"]//text()')[0].strip()
    gongsi=[]
    for i in tree.xpath('//div[@class="lf"]//text()'):
        if i.strip():
            gongsi.append(i.strip())
    fenshu=[]
    for i in tree.xpath('//ul[@class="rt"]//text()'):
        if i.strip():
            fenshu.append(i.strip())
    url=f"https://jobs.51job.com/shanghai/{job_id}.html?s=03&t=0"
    return {"公司":gongsi[1],"职位":gongsi[0],"匹配度":pingjia,fenshu[3]:fenshu[2],"链接":url,"_id":job_id}


if not os.path.exists("cookie.json"): get_cookie() f=open("cookie.json","r") cookies=json.loads(f.read()) f.close() session = requests.Session() for cookie in cookies: driver.add_cookie(cookie) session.cookies.set(cookie['name'], cookie['value']) url, page = get_job() driver.close() code=[] for i in get_pages(url,page): code=code+get_job_code(i) import pymongo client=pymongo.MongoClient("localhost",27017) db=client["job_he"] job_info=db["job_info"] for i in code: try: if not job_info.find_one({"_id":i}): info=get_info(i) sleep(1) job_info.insert_one(info) print(info) print("插入成功") except: print(code)

 

作者:神一样了