Introduction to pdfminer.six

pdfminer.six is a powerful library in Python for extracting text, images, and other information from PDF documents. It provides a range of APIs that allow developers to perform various operations on PDF files, making it an indispensable tool for those who need to automate PDF processing tasks.

Getting Started with pdfminer.six

To get started with pdfminer.six, you need to first install it using pip:

pip install pdfminer.six

Extracting Text with pdfminer.six

To extract text from a PDF, you can use the following code snippet:

from pdfminer.high_level import extract_text

def extract_text_from_pdf(pdf_path):
    text = extract_text(pdf_path)
    return text

pdf_path = 'sample.pdf'
extracted_text = extract_text_from_pdf(pdf_path)
print(extracted_text)

Extracting Images from PDF

pdfminer.six also allows you to extract images from PDF files. Here is an example:

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTImage
from pdfminer.pdfpage import PDFPage

def extract_images_from_pdf(pdf_path):
    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    images = []
    with open(pdf_path, 'rb') as fp:
        for page in PDFPage.get_pages(fp):
            interpreter.process_page(page)
            layout = device.get_result()
            for element in layout:
                if isinstance(element, LTImage):
                    images.append(element)
    return images

pdf_path = 'sample.pdf'
extracted_images = extract_images_from_pdf(pdf_path)
for img in extracted_images:
    print(f'Image: {img.name}')

Extracting Metadata from PDF

Here is how you can extract metadata from a PDF file:

from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser

def extract_metadata(pdf_path):
    with open(pdf_path, 'rb') as fp:
        parser = PDFParser(fp)
        document = PDFDocument(parser)
        metadata = document.info[0] if document.info else {}
    return metadata

pdf_path = 'sample.pdf'
metadata = extract_metadata(pdf_path)
for key, value in metadata.items():
    print(f'{key}: {value}')

PDFMiner Example Application

Let’s create a small application that uses the above APIs to extract text, images, and metadata from a PDF file.

from pdfminer.high_level import extract_text
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTImage
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser

def extract_text_from_pdf(pdf_path):
    return extract_text(pdf_path)

def extract_metadata(pdf_path):
    with open(pdf_path, 'rb') as fp:
        parser = PDFParser(fp)
        document = PDFDocument(parser)
        return document.info[0] if document.info else {}

def extract_images_from_pdf(pdf_path):
    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    images = []
    with open(pdf_path, 'rb') as fp:
        for page in PDFPage.get_pages(fp):
            interpreter.process_page(page)
            layout = device.get_result()
            for element in layout:
                if isinstance(element, LTImage):
                    images.append(element)
    return images

def main(pdf_path):
    text = extract_text_from_pdf(pdf_path)
    metadata = extract_metadata(pdf_path)
    images = extract_images_from_pdf(pdf_path)

    print("Text extracted:")
    print(text)
    print("\nMetadata extracted:")
    for key, value in metadata.items():
        print(f"{key}: {value}")
    print("\nImages extracted:")
    for img in images:
        print(f"Image: {img.name}")

if __name__ == "__main__":
    pdf_path = 'sample.pdf'
    main(pdf_path)

Hash: 92cceb5b922ca708645242b172030aa73ba58a0dd1e26a08d65048d07c02d94b