Automate Extraction of Meeting Details from Word Docs to Excel with Python in 30 Lines

A reader needed to process thousands of meeting‑notice Word documents and extract four key fields—study time, study content, study format, and host—into an Excel sheet. The article demonstrates a concise Python solution that automates this repetitive task.

Basic Logic

Use glob to collect all .docx files in the Notice folder.

Parse each Word file with python-docx to locate the four pieces of information.

Write the extracted data into an Excel workbook using openpyxl.

The workflow can be broken down into three steps: file discovery, data extraction, and Excel output.

Code Implementation

First, import the required libraries:

from docx import Document
from openpyxl import load_workbook
import glob

Load the Excel template:

path = r'C:\Users\xxx'  # adjust to your actual path
workbook = load_workbook(path + r'\Meeting_temp.xlsx')
sheet = workbook.active

Parse a single document to understand its structure (each paragraph corresponds to a line of text):

wordfile = Document(path + r'\Notice\会议通知 1.docx')
for paragraph in wordfile.paragraphs:
    print(paragraph)

Extract the four fields from each paragraph:

for paragraph in wordfile.paragraphs:
    if paragraph.text[0:5] == '学习时间：':
        study_time = paragraph.text[5:]
    if paragraph.text[0:4] == '主持人：':
        host = paragraph.text[4:]
    if paragraph.text[0:5] == '学习形式：':
        study_type = paragraph.text[5:]
    if len(paragraph.text) >= 2:
        if paragraph.text[0].isdigit() and paragraph.text[1] == '、':
            content_lst.append(paragraph.text)
content = ' '.join(content_lst)

Append the extracted data to the Excel sheet:

number = 0
number += 1
sheet.append([number, study_time, content, study_type, host])

Combine everything to process all files in the folder:

from docx import Document
from openpyxl import load_workbook
import glob

path = r'C:\Users\xxx'
workbook = load_workbook(path + r'\Meeting_temp.xlsx')
sheet = workbook.active
number = 0

for file in glob.glob(path + r'\Notice\*.docx'):
    wordfile = Document(file)
    content_lst = []
    for paragraph in wordfile.paragraphs:
        if paragraph.text[0:5] == '学习时间：':
            study_time = paragraph.text[5:]
        if paragraph.text[0:4] == '主持人：':
            host = paragraph.text[4:]
        if paragraph.text[0:5] == '学习形式：':
            study_type = paragraph.text[5:]
        if len(paragraph.text) >= 2:
            if paragraph.text[0].isdigit() and paragraph.text[1] == '、':
                content_lst.append(paragraph.text)
    content = ' '.join(content_lst)
    number += 1
    sheet.append([number, study_time, content, study_type, host])

workbook.save(path + r'\Meeting_notice.xlsx')

The solution processes each document in a few seconds and writes all extracted rows to Meeting_notice.xlsx with only about thirty lines of code.