HR Process Automation Scripts: Resume Parsing, Interview Emails, Pay‑Slip Generation, and Data Analysis

This guide provides a series of Python automation scripts for common HR workflows.

1. Resume Parsing : Extracts name and email from a resume file using regular expressions.

import re
from os import path

def parse_resume(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        content = file.read()
    name_pattern = re.compile(r"(?<=Name:|姓名：).*?(?=\n|$)", re.IGNORECASE)
    email_pattern = re.compile(r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}", re.IGNORECASE)
    name = re.findall(name_pattern, content)
    email = re.findall(email_pattern, content)
    print(f"Name: {name}\nEmail: {email}")

# Example usage
parse_resume('path_to_your_resume.txt')

2. Interview Invitation Email Sending : Reads a CSV of candidates and sends personalized interview invitations via SMTP.

import smtplib
from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart
import csv

def send_interview_email(subject, body, candidates_file, smtp_server, port, sender, password):
    with open(candidates_file, newline='', encoding='utf-8') as csvfile:
        reader = csv.reader(csvfile)
        next(reader)  # Skip header
        for row in reader:
            name, email = row
            msg = MIMEMultipart()
            msg['From'] = sender
            msg['To'] = email
            msg['Subject'] = subject
            msg.attach(MIMEText(body.format(name=name), 'plain'))
            server = smtplib.SMTP(smtp_server, port)
            server.starttls()
            server.login(sender, password)
            server.sendmail(sender, email, msg.as_string())
            server.quit()

# Example usage
send_interview_email(
    "Interview Invitation",
    "Dear {name}, you are invited for an interview.",
    "candidates.csv",
    "smtp.example.com",
    587,
    "[email protected]",
    "your_password"
)

3. Pay‑Slip Generation : Reads an Excel file of employee salaries and creates individual text pay‑slip files.

import pandas as pd

def generate_pay_slips(data_path, output_path):
    df = pd.read_excel(data_path)
    for idx, row in df.iterrows():
        slip_content = f"""
        Employee ID: {row['Employee ID']}
        Name: {row['Name']}
        Salary: {row['Salary']}
        Month: {row['Month']}
        Year: {row['Year']}
        """
        with open(f"{output_path}/{row['Employee ID']}_pay_slip.txt", 'w') as file:
            file.write(slip_content)

# Example usage
generate_pay_slips("employees_salary.xlsx", "pay_slips")

4. Hiring‑Channel Data Analysis : Summarizes hiring results per source and calculates hire rates.

import pandas as pd

def analyze_hiring_channels(channel_data_path):
    df = pd.read_csv(channel_data_path)
    channel_summary = df.groupby('Source')['Hired'].sum().reset_index()
    channel_summary.rename(columns={'Hired': 'Total Hires'}, inplace=True)
    channel_summary['Hire Rate'] = (channel_summary['Total Hires'] / df['Hired'].sum()) * 100
    print(channel_summary.sort_values('Total Hires', ascending=False))

# Example usage
analyze_hiring_channels("hiring_channels.csv")

5. Turnover Rate Calculation : Computes overall employee turnover percentage.

import pandas as pd

def calculate_turnover_rate(employee_data_path):
    df = pd.read_csv(employee_data_path)
    total_employees = len(df)
    resigned = df[df['Status'] == 'Resigned'].shape[0]
    turnover_rate = (resigned / total_employees) * 100
    print(f"Turnover Rate: {turnover_rate:.2f}%")

# Example usage
calculate_turnover_rate("employee_records.csv")

6. Employee Satisfaction Survey Analysis : Calculates average satisfaction score and distribution.

import pandas as pd

def analyze_satisfaction_survey(survey_data_path):
    df = pd.read_csv(survey_data_path)
    avg_satisfaction = df['Satisfaction Score'].mean()
    print(f"Average Satisfaction Score: {avg_satisfaction:.2f}")
    satisfaction_counts = df['Satisfaction Score'].value_counts(normalize=True) * 100
    print(satisfaction_counts)

# Example usage
analyze_satisfaction_survey("satisfaction_survey.csv")

7. Salary Competitiveness Comparison : Merges company and market salary data to compute a competitive ratio.

import pandas as pd

def compare_salaries(company_salaries_path, market_salaries_path):
    company_df = pd.read_csv(company_salaries_path)
    market_df = pd.read_csv(market_salaries_path)
    merged_df = pd.merge(company_df, market_df, on='Job Title', how='outer')
    merged_df['Competitive Ratio'] = merged_df['Company Salary'] / merged_df['Market Salary']
    print(merged_df[['Job Title', 'Company Salary', 'Market Salary', 'Competitive Ratio']])

# Example usage
compare_salaries("company_salaries.csv", "market_salaries.csv")

8. Bulk Employee Information Update : Updates an employee CSV with changes from another file.

import pandas as pd

def update_employee_info(input_file, updates_file, output_file):
    df = pd.read_csv(input_file)
    updates = pd.read_csv(updates_file)
    df.update(updates, overwrite=True)
    df.to_csv(output_file, index=False)

# Example usage
update_employee_info("employees.csv", "updates.csv", "updated_employees.csv")

9. Word Document Automation : Fills a Word template with employee data to generate personalized documents.

from docx import Document
import pandas as pd

def fill_word_template(template_path, data_path, output_path):
    df = pd.read_csv(data_path)
    doc = Document(template_path)
    for index, row in df.iterrows():
        for paragraph in doc.paragraphs:
            for run in paragraph.runs:
                if '{' in run.text and '}' in run.text:
                    field_name = run.text.strip('{} ')
                    if field_name in row:
                        run.text = str(row[field_name])
    doc.save(f"{output_path}/employee_{row['Employee ID']}.docx")

# Example usage
fill_word_template("template.docx", "employee_data.csv", "generated_docs")

10. Leave‑Request Email Automation : Connects to an IMAP server, detects unread leave‑request emails, extracts dates (placeholder logic), and sends a confirmation reply.

import imaplib
import email
from email.mime.text import MIMEText
import smtplib

def fetch_emails(imap_server, username, password):
    mail = imaplib.IMAP4_SSL(imap_server)
    mail.login(username, password)
    mail.select('inbox')
    _, data = mail.search(None, 'UNSEEN')
    mail_ids = data[0].split()
    for id in mail_ids:
        _, msg_data = mail.fetch(id, '(RFC822)')
        msg = email.message_from_bytes(msg_data[0][1])
        process_email(msg)

def process_email(msg):
    from_email = email.utils.parseaddr(msg['From'])[1]
    subject = msg['Subject']
    if "休假申请" in subject:
        body = ""
        if msg.is_multipart():
            for part in msg.walk():
                ctype = part.get_content_type()
                cdispo = str(part.get('Content-Disposition'))
                if ctype == 'text/plain' and 'attachment' not in cdispo:
                    body = part.get_payload(decode=True).decode('utf-8')
                    break
        else:
            body = msg.get_payload(decode=True).decode('utf-8')
        date_start, date_end = extract_dates(body)
        send_confirmation_email(from_email, date_start, date_end)

def send_confirmation_email(to_email, start_date, end_date):
    sender_email = "[email protected]"
    sender_password = "your_email_password"
    smtp_server = "smtp.example.com"
    port = 587
    subject = "休假申请已收到"
    body = f"您好，\n\n您的休假申请（从{start_date}至{end_date}）已收到。我们将尽快处理并回复您。\n\n祝好，\n人力资源部"
    msg = MIMEText(body)
    msg['Subject'] = subject
    msg['From'] = sender_email
    msg['To'] = to_email
    server = smtplib.SMTP(smtp_server, port)
    server.starttls()
    server.login(sender_email, sender_password)
    server.sendmail(sender_email, to_email, msg.as_string())
    server.quit()

def extract_dates(text):
    # Placeholder: implement actual date extraction logic
    date_start = "需要解析的起始日期"
    date_end = "需要解析的结束日期"
    return date_start, date_end

# Example usage (replace with real credentials)
fetch_emails("imap.example.com", "your_username", "your_password")

Each script is self‑contained, uses standard Python libraries, and can be adapted to specific organizational needs, offering a practical toolkit for automating repetitive HR processes.