Extract metadata from files with Python

Extracting metadata from files using Python depends on the file type you’re working with—documents, images, videos, PDFs, or audio files each have their own libraries and formats. Here’s a comprehensive guide on how to extract metadata from various types of files using Python.

1. Extracting Metadata from Images

You can use the Pillow and exifread libraries to extract EXIF data.

python
CopyEdit
from PIL import Image
from PIL.ExifTags import TAGS

def extract_image_metadata(file_path):
    image = Image.open(file_path)
    exif_data = image._getexif()
    metadata = {}
    if exif_data:
        for tag_id, value in exif_data.items():
            tag = TAGS.get(tag_id, tag_id)
            metadata[tag] = value
    return metadata

# Usage
metadata = extract_image_metadata('image.jpg')
for key, value in metadata.items():
    print(f"{key}: {value}")

For more detailed EXIF data:

bash
CopyEdit
pip install exifread

python
CopyEdit
import exifread

def extract_exifread_metadata(file_path):
    with open(file_path, 'rb') as file:
        tags = exifread.process_file(file)
    return tags

tags = extract_exifread_metadata('image.jpg')
for tag in tags:
    print(f"{tag}: {tags[tag]}")

2. Extracting Metadata from PDFs

Use the PyPDF2 or pdfplumber libraries.

bash
CopyEdit
pip install PyPDF2

python
CopyEdit
import PyPDF2

def extract_pdf_metadata(file_path):
    with open(file_path, 'rb') as file:
        reader = PyPDF2.PdfReader(file)
        info = reader.metadata
    return info

metadata = extract_pdf_metadata('document.pdf')
for key, value in metadata.items():
    print(f"{key}: {value}")

3. Extracting Metadata from Audio Files

Use mutagen for MP3, FLAC, etc.

bash
CopyEdit
pip install mutagen

python
CopyEdit
from mutagen import File

def extract_audio_metadata(file_path):
    audio = File(file_path)
    return audio

metadata = extract_audio_metadata('song.mp3')
for key, value in metadata.items():
    print(f"{key}: {value}")

4. Extracting Metadata from Video Files

Use ffprobe through ffmpeg-python or pymediainfo.

bash
CopyEdit
pip install pymediainfo

python
CopyEdit
from pymediainfo import MediaInfo

def extract_video_metadata(file_path):
    media_info = MediaInfo.parse(file_path)
    for track in media_info.tracks:
        for key, value in track.to_data().items():
            print(f"{key}: {value}")

extract_video_metadata('video.mp4')

5. Extracting Metadata from Office Documents

For Microsoft Word, Excel, and PowerPoint files, use python-docx, openpyxl, or python-pptx.

bash
CopyEdit
pip install python-docx openpyxl python-pptx

Word documents (.docx):

python
CopyEdit
from docx import Document

def extract_docx_metadata(file_path):
    doc = Document(file_path)
    props = doc.core_properties
    metadata = {
        'title': props.title,
        'author': props.author,
        'subject': props.subject,
        'created': props.created,
        'last_modified_by': props.last_modified_by
    }
    return metadata

metadata = extract_docx_metadata('file.docx')
for key, value in metadata.items():
    print(f"{key}: {value}")

Excel (.xlsx):

python
CopyEdit
import openpyxl

def extract_excel_metadata(file_path):
    wb = openpyxl.load_workbook(file_path)
    props = wb.properties
    metadata = {
        'title': props.title,
        'author': props.creator,
        'created': props.created,
        'modified': props.modified
    }
    return metadata

metadata = extract_excel_metadata('file.xlsx')
for key, value in metadata.items():
    print(f"{key}: {value}")

6. Extracting File System Metadata

Use Python’s os and pathlib modules.

python
CopyEdit
import os
from pathlib import Path
import time

def extract_file_system_metadata(file_path):
    file = Path(file_path)
    metadata = {
        "name": file.name,
        "size_bytes": file.stat().st_size,
        "created": time.ctime(file.stat().st_ctime),
        "modified": time.ctime(file.stat().st_mtime),
        "accessed": time.ctime(file.stat().st_atime)
    }
    return metadata

metadata = extract_file_system_metadata('example.txt')
for key, value in metadata.items():
    print(f"{key}: {value}")

7. Extracting Metadata from Emails (EML Files)

bash
CopyEdit
pip install extract-msg

python
CopyEdit
import extract_msg

def extract_email_metadata(file_path):
    msg = extract_msg.Message(file_path)
    metadata = {
        'subject': msg.subject,
        'sender': msg.sender,
        'date': msg.date,
        'to': msg.to,
        'cc': msg.cc
    }
    return metadata

metadata = extract_email_metadata('email.eml')
for key, value in metadata.items():
    print(f"{key}: {value}")

Conclusion

Extracting metadata with Python is straightforward using the appropriate libraries for each file type. These tools provide access to everything from image EXIF data and video codecs to PDF properties and document authorship. By modularizing the approach based on file type, you can automate metadata extraction across various file formats efficiently.