Python利用pdfplumber+PyPDF2实现PDF文件自动化处理

pip install pdfplumber PyPDF2  # 两个库各有侧重，搭配使用

import pdfplumber

with pdfplumber.open("报告.pdf") as pdf:
    # 总页数
    print(f"共 {len(pdf.pages)} 页")

    full_text = ""
    for i, page in enumerate(pdf.pages):
        text = page.extract_text()
        if text:
            full_text += text + "\n"
            print(f"第 {i+1} 页: {len(text)} 字符")

# 保存成 txt
with open("输出.txt", "w", encoding="utf-8") as f:
    f.write(full_text)

import pdfplumber

with pdfplumber.open("报告.pdf") as pdf:
    # 提取第 3-5 页（页码从 0 开始）
    for i in range(2, 5):
        page = pdf.pages[i]
        text = page.extract_text()
        print(f"=== 第 {i+1} 页 ===")
        print(text)

import pdfplumber

with pdfplumber.open("报告.pdf") as pdf:
    for page in pdf.pages:
        # 方法1：直接提取
        text = page.extract_text()

        # 方法2：如果乱码，试试保留空白
        text = page.extract_text(x_tolerance=3, y_tolerance=3)

        # 方法3：按行提取
        lines = page.extract_text_lines()
        for line in lines:
            print(line["text"])

import pdfplumber
import pandas as pd

with pdfplumber.open("财务报表.pdf") as pdf:
    all_tables = []

    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            # table 是二维列表，第一行通常是表头
            df = pd.DataFrame(table[1:], columns=table[0])
            all_tables.append(df)
            print(f"找到 1 个表格，{len(table)} 行 × {len(table[0])} 列")

# 合并所有表格并导出
if all_tables:
    result = pd.concat(all_tables, ignore_index=True)
    result.to_excel("表格数据.xlsx", index=False)
    print(f"共提取 {len(result)} 行数据，已导出到 表格数据.xlsx")

from PyPDF2 import PdfMerger
import os

def merge_pdfs(input_dir, output_file):
    """合并一个文件夹下的所有 PDF"""
    merger = PdfMerger()

    # 按文件名排序，保证顺序
    files = sorted([f for f in os.listdir(input_dir) if f.endswith(".pdf")])

    for f in files:
        filepath = os.path.join(input_dir, f)
        merger.append(filepath)
        print(f"已添加: {f}")

    merger.write(output_file)
    merger.close()
    print(f"合并完成，共 {len(files)} 个文件 → {output_file}")

# 使用
merge_pdfs("要合并的PDF", "合并结果.pdf")

from PyPDF2 import PdfReader, PdfWriter

def split_pdf(input_file, output_dir, pages_per_file=10):
    """按每N页一组拆分 PDF"""
    reader = PdfReader(input_file)
    total_pages = len(reader.pages)

    os.makedirs(output_dir, exist_ok=True)

    file_index = 1
    for start in range(0, total_pages, pages_per_file):
        writer = PdfWriter()
        end = min(start + pages_per_file, total_pages)

        for page_num in range(start, end):
            writer.add_page(reader.pages[page_num])

        output_file = f"{output_dir}/第{file_index}部分({start+1}-{end}页).pdf"
        with open(output_file, "wb") as f:
            writer.write(f)

        print(f"已生成: {output_file}")
        file_index += 1

# 使用：每 20 页拆一份
split_pdf("大文件.pdf", "拆分输出", pages_per_file=20)

from PyPDF2 import PdfReader, PdfWriter

def encrypt_pdf(input_file, password, output_file=None):
    """给 PDF 加上密码保护"""
    reader = PdfReader(input_file)
    writer = PdfWriter()

    for page in reader.pages:
        writer.add_page(page)

    writer.encrypt(password)

    output = output_file or input_file.replace(".pdf", "_加密.pdf")
    with open(output, "wb") as f:
        writer.write(f)

    print(f"已加密: {output}")
    return output

# 使用
encrypt_pdf("合同.pdf", "123456", "合同_加密.pdf")

pip install pytesseract pillow
# 还需要安装 Tesseract-OCR 引擎（百度搜索下载）

import pytesseract
from PIL import Image
import pdfplumber
import io

def ocr_pdf(pdf_path):
    """OCR 识别扫描件 PDF"""
    with pdfplumber.open(pdf_path) as pdf:
        full_text = ""
        for i, page in enumerate(pdf.pages):
            # 把 PDF 页面转成图片
            img = page.to_image(resolution=300)
            img_path = f"temp_page_{i}.png"
            img.save(img_path)

            # OCR 识别
            text = pytesseract.image_to_string(
                Image.open(img_path), lang="chi_sim+eng"
            )
            full_text += text + "\n"
            print(f"第 {i+1} 页识别完成，{len(text)} 字符")

    with open("ocr_result.txt", "w", encoding="utf-8") as f:
        f.write(full_text)
    return full_text

# 使用（识别中文要下载中文语言包）
ocr_pdf("扫描件.pdf")

import pdfplumber
import pandas as pd
import os

def extract_invoice_info(pdf_path):
    """从发票 PDF 中提取关键信息"""
    info = {"文件名": os.path.basename(pdf_path)}

    with pdfplumber.open(pdf_path) as pdf:
        text = ""
        for page in pdf.pages:
            text += page.extract_text() or ""

    # 用正则提取关键信息（根据实际发票格式调整）
    import re

    # 发票号码
    match = re.search(r"发票号码[：:]\s*(\d+)", text)
    info["发票号码"] = match.group(1) if match else ""

    # 开票日期
    match = re.search(r"开票日期[：:]\s*(\d{4}[-年]\d{1,2}[-月]\d{1,2})", text)
    info["开票日期"] = match.group(1) if match else ""

    # 金额
    match = re.search(r"价税合计[：:]\s*[¥￥]?([\d,]+\.\d{2})", text)
    info["金额"] = match.group(1) if match else ""

    # 销售方名称
    match = re.search(r"销售方[名称]?[：:]\s*(.+?)(?:\n|$)", text)
    info["销售方"] = match.group(1).strip() if match else ""

    return info

# 批量处理所有 PDF
pdf_dir = "发票文件夹"
results = []

for f in os.listdir(pdf_dir):
    if f.endswith(".pdf"):
        try:
            info = extract_invoice_info(os.path.join(pdf_dir, f))
            results.append(info)
            print(f"已处理: {f}")
        except Exception as e:
            print(f"处理失败 {f}: {e}")

# 导出到 Excel
df = pd.DataFrame(results)
df.to_excel("发票汇总.xlsx", index=False)
print(f"共处理 {len(results)} 份发票")