Python 自动化办公中批量提取电子发票的信息，提升效率

  pip install pdfplumber pandas 

import pdfplumber
import re
import pandas as pd
import os

class InvoiceProcessor:
    def __init__(self, pdf_folder):
        self.pdf_folder = pdf_folder
        self.invoice_list = []

    def extract_text_from_pdf(self, pdf_path):
        full_text = ""
        try:
            with pdfplumber.open(pdf_path) as pdf:
                for page in pdf.pages:
                    text = page.extract_text()
                    if text:
                        full_text += text + "\n"
            return full_text
        except Exception as e:
            print(f"错误：无法读取文件 {pdf_path}，原因：{e}")
            return None

    def parse_invoice_info(self, text):
        data = {}

        invoice_no_match = re.search(r'发票号码[:：]?\s*([A-Za-z0-9]+)', text)
        data["发票号码"] = invoice_no_match.group(1) if invoice_no_match else "未识别"

        date_match = re.search(r'开票日期[:：]?\s*(\d{4}[年-]\d{1,2}[月-]\d{1,2}日?)', text)
        data["开票日期"] = date_match.group(1) if date_match else "未识别"

        seller_match = re.search(
            r'销\s*名称\s*[:：]?\s*([^\n,，:：\d]{4,}?(?:公司|有限))',
            text, re.MULTILINE
        )
        data["销售方名称"] = seller_match.group(1).strip() if seller_match else "未识别"

        tax_id_match = re.search(r'纳税人识别号[:：]?\s*([A-Za-z0-9]{18})', text)
        data["纳税人识别号"] = tax_id_match.group(1) if tax_id_match else "未识别"

        total_match = re.search(r'价税合计[^¥]*¥\s*([0-9.,]+)', text)
        data["价税合计"] = total_match.group(1).replace(',', '') if total_match else "未识别"

        return data

    def process_all_invoices(self):
        for filename in os.listdir(self.pdf_folder):
            if filename.endswith(".pdf"):
                pdf_path = os.path.join(self.pdf_folder, filename)
                print(f"处理文件：{filename}")
                text = self.extract_text_from_pdf(pdf_path)
                print(text)
                if text:
                    info = self.parse_invoice_info(text)
                    info["文件名"] = filename  # 记录来源文件
                    self.invoice_list.append(info)
                else:
                    print(f"跳过文件（读取失败）：{filename}")


    def save_to_excel(self, output_path="发票汇总.xlsx"):
        if self.invoice_list:
            df = pd.DataFrame(self.invoice_list)
            df.to_excel(output_path, index=False)
            print(f"数据已导出至：{output_path}")
        else:
            print("无数据可导出")


if __name__ == "__main__":
    processor = InvoiceProcessor("E:\BXTY2000000023102194")  # 指定发票PDF所在文件夹
    processor.process_all_invoices()
    processor.save_to_excel()

# 示例：兼容多种表述
tax_id_patterns = [
    r'纳税人识别号[:：]\s*(\w{18})',
    r'税号[:：]\s*(\w{18})',
    r'信用代码[:：]\s*(\w{18})'
]
for pattern in tax_id_patterns:
    match = re.search(pattern, text)
    if match:
        data["纳税人识别号"] = match.group(1)
        break