Python实现定时拉取&汇总招聘信息发送到个人邮箱（附源代码）

因为一个一个的查看各个省份的招聘信息比较麻烦，且有的时候公告发布后一周内要报名，时常出现错过报名的情况o(╥﹏╥)o，故写个脚本每天查询一下各个官网有没有更新招聘公告，然后发送到我的邮箱内！

步骤：

1：拉取对应官网的招聘信息

2：对获得的信息进行抽取和处理成自己想要的格式

3：发送到自己的个人邮箱

4：放到服务器上持续运行（记得打开端口号）

效果如图：

具体代码如下，你只需更改一下发送和接受的邮箱地址，以及有个自己的服务器就可以了。

import requests
import schedule
from bs4 import BeautifulSoup
import smtplib
from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart
from datetime import datetime, timedelta


AllDataDict = {}


def getHuBeiData():
    url = "http://rst.hubei.gov.cn/bmdt/ztzl/ywzl/hbsszsydwgkzp/zpgg/"
    response = requests.get(url)
    soup = BeautifulSoup(response.content, 'html.parser')
    now = datetime.now().date()
    three_days_ago = now - timedelta(days=3)
    announcements = soup.find('div', class_='col-xs-12 col-md-12').find('ul', class_='list-t border6').find_all('li')
    recruitment_info_list = []
    for announcement in announcements:
        date_str = announcement.find('span', class_='date hidden-xs').text
        date = datetime.strptime(date_str, '%Y-%m-%d').date()
        title = announcement.find('a')['title']
        link = announcement.find('a')['href']
        if date >= three_days_ago:
            recruitment_info_list.append({"date": date, "title": title, "link": link})
    huBeiList = []
    printed_titles = set()
    for info in recruitment_info_list:
        if info["title"] not in printed_titles:
            huBeiList.append(f"发布日期: {info['date']}, 标题: {info['title']}, 链接: http://rst.hubei.gov.cn/bmdt/ztzl/ywzl/hbsszsydwgkzp/zpgg/{info['link']}")
            printed_titles.add(info["title"])
    AllDataDict["湖北地区"] = huBeiList


def getHunanData():
    import urllib3
    urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
    HuNanUrl = "https://rst.hunan.gov.cn/rst/xxgk/zpzl/sydwzp/index.html"
    response = requests.get(HuNanUrl, verify=False)
    soup = BeautifulSoup(response.content, 'html.parser')
    now = datetime.now()
    three_days_ago = now - timedelta(days=5)
    tbody = soup.find('tbody', class_='table_list_st')
    rows = tbody.find_all('tr')
    hunanlist = []
    for row in rows:
        cells = row.find_all('td')
        date_str = cells[2].text.strip()
        date = datetime.strptime(date_str, '%Y-%m-%d')
        if date >= three_days_ago:
            href = cells[1].find('a')['href']
            title = cells[1].find('a')['title']
            hunanlist.append(f"发布日期: {date_str}, 标题: {title}, 链接: https://rst.hunan.gov.cn/{href}")
    AllDataDict["湖南地区"] = hunanlist


def getHeNanData():
    url = "https://ywzl.hrss.henan.gov.cn/viewCmsCac.do?cacId=4aef1408279926e601279e53eac517a5"
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
    }
    response = requests.get(url, headers=headers)
    soup = BeautifulSoup(response.content, 'html.parser')
    now = datetime.now().date()
    three_days_ago = now - timedelta(days=3)
    rows = soup.find_all('tr')
    recruitment_info_list = []
    henanlist = []
    for row in rows:
        cells = row.find_all('td')
        if len(cells) > 2:
            date_str = cells[2].text.strip().replace('[', '').replace(']', '')
            try:
                date = datetime.strptime(date_str, '%Y-%m-%d').date()
            except ValueError:
                continue
            title = cells[1].find('a')['title']
            link = cells[1].find('a')['href']
            if date >= three_days_ago:
                recruitment_info_list.append({"date": date, "title": title, "link": link})
    printed_titles = set()
    for info in recruitment_info_list:
        if info["title"] not in printed_titles:
            henanlist.append(f"发布日期: {info['date']}, 标题: {info['title']}, 链接: https://ywzl.hrss.henan.gov.cn/{info['link']}")
            printed_titles.add(info["title"])
    AllDataDict["河南地区"] = henanlist


def getAllData():
    getHeNanData()
    getHunanData()
    getHuBeiData()


def sendAngle():
    sender_email = 'XXX@qq.com'
    receiver_email = 'XXX@163.com'
    password = '这里是邮箱授权码'
    message = MIMEMultipart()
    message['From'] = sender_email
    message['To'] = receiver_email
    message['Subject'] = 'Angle：前三天招聘公告信息'
    body = ""
    for region, announcements in AllDataDict.items():
        body += f"地区：{region}\n"
        for announcement in announcements:
            body += announcement + "\n"
        body += "\n"
    message.attach(MIMEText(body, 'plain'))
    try:
        server = smtplib.SMTP('smtp.qq.com', 587)
        server.starttls()
        server.login(sender_email, password)
        server.sendmail(sender_email, receiver_email, message.as_string())
        print("邮件发送成功！")
    except Exception as e:
        print(f"邮件发送失败：{e}")
    finally:
        server.quit()

def job_task():
    getAllData()
    sendAngle()


schedule.every().day.at("09:30").do(job_task)

while True:
    schedule.run_pending()
    time.sleep(60)

希望大家都有一个光明的未来！