使用Python处理PDF文件的实践分享

pip install PyPDF2
pip install pdfminer.six

import PyPDF2

def read_pdf(file_path):
    with open(file_path, 'rb') as file:
        pdf_reader = PyPDF2.PdfFileReader(file)
        num_pages = pdf_reader.numPages
        text = ''
        for page_num in range(num_pages):
            page = pdf_reader.getPage(page_num)
            text += page.extract_text()
        return text

pdf_text = read_pdf('example.pdf')
print(pdf_text)

import PyPDF2
def extract_images(file_path):
    with open(file_path, 'rb') as file:
        pdf_reader = PyPDF2.PdfFileReader(file)
        num_pages = pdf_reader.numPages
        images = []
        for page_num in range(num_pages):
            page = pdf_reader.getPage(page_num)
            if '/XObject' in page['/Resources']:
                x_object = page['/Resources']['/XObject'].getObject()
                for obj in x_object:
                    if x_object[obj]['/Subtype'] == '/Image':
                        image = x_object[obj]
                        images.append(image)
        return images
pdf_images = extract_images('example.pdf')
for i, image in enumerate(pdf_images):
    image_data = image._data
    image_name = f'image_{i}.png'
    with open(image_name, 'wb') as img_file:
        img_file.write(image_data)

from reportlab.pdfgen import canvas

def create_pdf(file_path):
    c = canvas.Canvas(file_path)
    c.setFont("Helvetica", 12)
    c.drawString(100, 700, "Hello, World!")
    
    image_path = "image.png"
    c.drawImage(image_path, 100, 500, width=200, height=200)
    
    c.save()

create_pdf("example.pdf")

import PyPDF2

def merge_pdfs(input_files, output_file):
    pdf_merger = PyPDF2.PdfFileMerger()
    for file in input_files:
        with open(file, 'rb') as f:
            pdf_merger.append(f)
    with open(output_file, 'wb') as f:
        pdf_merger.write(f)

def split_pdf(input_file, output_prefix):
    with open(input_file, 'rb') as file:
        pdf_reader = PyPDF2.PdfFileReader(file)
        num_pages = pdf_reader.numPages
        for page_num in range(num_pages):
            pdf_writer = PyPDF2.PdfFileWriter()
            pdf_writer.addPage(pdf_reader.getPage(page_num))
            output_file = f'{output_prefix}_{page_num}.pdf'
            with open(output_file, 'wb') as output:
                pdf_writer.write(output)

# 合并两个PDF文件
input_files = ['file1.pdf', 'file2.pdf']
merge_pdfs(input_files, 'merged.pdf')

# 拆分一个PDF文件
split_pdf('input.pdf', 'split')