使用Python处理PDF文件的常见操作与实战

pip install PyPDF2 pdfminer.six reportlab

import PyPDF2

def read_pdf(file_path):
    # 使用二进制只读模式打开文件
    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)
            page_text = page.extract_text()
            if page_text:
                text += page_text + '\n'
        return text

# 替换为你的实际文件路径
pdf_text = read_pdf('example.pdf')
print(pdf_text[:200])  # 打印前200个字符核对结果

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)
            resources = page.get('/Resources', {})
            x_object = resources.get('/XObject', {})
            if not x_object:
                continue
            for obj_key in x_object:
                obj = x_object[obj_key]
                # 判断是否为图像对象
                if obj.get('/Subtype') == '/Image':
                    images.append(obj)
        return images

# 执行提取
pdf_images = extract_images('example.pdf')
for i, img_obj in enumerate(pdf_images):
    img_data = img_obj.getData()
    # 根据实际压缩类型决定后缀名（例如 /DCTDecode 为 .jpg）
    with open(f'image_raw_{i}.bin', 'wb') as f:
        f.write(img_data)

from reportlab.pdfgen import canvas

def create_pdf(file_path):
    c = canvas.Canvas(file_path)
    # 设置字体与字号
    c.setFont("Helvetica", 12)
    # 坐标原点默认在左下角(100, 700)处绘制标题
    c.drawString(100, 700, "Hello, Generated PDF!")
    
    # 添加内嵌图片占位测试
    image_path = "cover.jpg"
    c.drawImage(image_path, 100, 500, width=200, height=150, preserveAspectRatio=True)
    
    # 保存并关闭文件句柄
    c.save()

# 生成输出
create_pdf("output_new.pdf")

import PyPDF2
import os

def merge_pdfs(input_files, output_file):
    # 备份风险提醒：若output_file已存在将被完全覆盖
    if os.path.exists(output_file):
        print(f"警告：{output_file} 已存在，即将被覆盖。")
    merger = PyPDF2.PdfFileMerger()
    for f_path in input_files:
        if os.path.isfile(f_path):
            merger.append(f_path)
        else:
            print(f"跳过不存在的路径：{f_path}")
    with open(output_file, 'wb') as f_out:
        merger.write(f_out)

def split_pdf(input_file, output_prefix):
    with open(input_file, 'rb') as f_in:
        reader = PyPDF2.PdfFileReader(f_in)
        total = reader.numPages
        for idx in range(total):
            writer = PyPDF2.PdfFileWriter()
            writer.addPage(reader.getPage(idx))
            part_name = f"{output_prefix}_page_{idx+1}.pdf"
            with open(part_name, 'wb') as f_part:
                writer.write(f_part)

# 执行合并与拆分
merge_pdfs(['part_a.pdf', 'part_b.pdf'], 'combined.pdf')
split_pdf('large_report.pdf', 'split_output')