前言
在前程無憂上投遞簡歷發現有競爭力分析，免費能看到匹配度評價和綜合競爭力分數，可以做投遞參考
計算方式
綜合競爭力得分應該越高越好，匹配度評語也應該評價越高越好
抓取所有職位關鍵字搜索結果并獲取綜合競爭力得分和匹配度評語，最后篩選得分評語自動投遞合適的簡歷
登陸獲取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°reefrom=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需要在相應域名寫入cookie，所以轉到職位搜索頁面
def get_cookie():
driver.get("https://login.51job.com/login.php?loginway=1&lang=c&url=")
sleep(2)
phone=input("輸入手機號：")
driver.find_element_by_id("loginname").send_keys(phone)
driver.find_element_by_id("btn7").click()
sleep(1)
code=input("輸入短信：")
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))
檢查cookie文件是否存在，如果不存在執行get_cookie把cookie寫入文件，在登陸的時候最好不用無頭模式，偶爾有滑動驗證碼
前程無憂手機短信一天只能發送三條，保存cookie下次登陸用
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°reefrom=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("輸入職位：")
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
在職位搜索獲取職位搜索結果，需要返回頁面源碼和地址
分析頁碼結構html前的是頁碼，全部頁碼數量通過共XX頁得到
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
獲取全部頁碼
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
獲取職位id
修改id請求網址到競爭力分析頁面
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],"職位":gongsi[0],"匹配度":pingjia,fenshu[3]:fenshu[2],"鏈接":url,"_id":job_id}
抓取競爭力分析頁面，返回一個字典
主程序
if not os.path.exists("cookie.json"):
get_cookie()
f=open("cookie.json","r")
cookies=json.loads(f.read())
f.close()
檢查cookie文件載入cookie，不存在執行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寫入cookie登陸
獲取第一頁和url后webdriver就可以關掉了
code=[] for i in get_pages(url,page): code=code+get_job_code(i)
獲取的職位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)
龜速爬取，用MongDB保存結果，職位id作為索引id，插入之前檢查id是否存在簡單去重減少訪問
吃完飯已經抓到8000個職位了，篩選找到127個匹配度好的，開始批量投遞
登陸狀態點擊申請職位，用wevdriver做
for i in job_info.find({"匹配度":{$regex:"排名很好"},"綜合競爭力得分":{$gte:"80"}}):
print(i)
try:
driver.get(i)
driver.find_element_by_id("app_ck").click()
sleep(2)
except:
pass
用cookie登陸簡單for循環投遞，在Mongodb里查表，正則篩選匹配度和競爭力得分獲取所有匹配結果
投遞成功
代碼
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°reefrom=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("輸入手機號：")
driver.find_element_by_id("loginname").send_keys(phone)
driver.find_element_by_id("btn7").click()
sleep(1)
code=input("輸入短信：")
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°reefrom=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("輸入職位：")
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],"職位":gongsi[0],"匹配度":pingjia,fenshu[3]:fenshu[2],"鏈接":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)
總結
以上就是這篇文章的全部內容了，希望本文的內容對大家的學習或者工作具有一定的參考學習價值，謝謝大家對億速云的支持。
免責聲明：本站發布的內容（圖片、視頻和文字）以原創、轉載和分享為主，文章觀點不代表本網站立場，如果涉及侵權請聯系站長郵箱：is@yisu.com進行舉報，并提供相關證據，一經查實，將立刻刪除涉嫌侵權內容。
