Python实现PDF信息的精准提取与结构化输出

# PyPDF2基础提取（适合简单文档）
from PyPDF2 import PdfReader

def extract_text_pypdf2(pdf_path):
    with open(pdf_path, 'rb') as file:
        reader = PdfReader(file)
        return "\n".join([page.extract_text() for page in reader.pages])

# pdfplumber进阶提取（支持坐标定位）
import pdfplumber

def extract_with_coordinates(pdf_path):
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            # 提取带坐标的文本块
            for text_block in page.extract_text(x_tolerance=3, y_tolerance=3):
                print(f"位置:({text_block['x0']},{text_block['top']}) 内容:{text_block['text']}")

# 完整OCR处理流程
from pdf2image import convert_from_path
import pytesseract
from PIL import Image

def ocr_pdf(pdf_path, lang='chi_sim+eng'):
    # 将PDF转为图片列表
    images = convert_from_path(pdf_path, dpi=300)
    
    full_text = []
    for i, img in enumerate(images):
        # 图片预处理（去噪、二值化）
        img = img.convert('L').point(lambda x: 0 if x < 140 else 255)
        text = pytesseract.image_to_string(img, lang=lang)
        full_text.append(f"--- Page {i+1} ---\n{text}")
    
    return "\n".join(full_text)

# Camelot表格提取（适合网格表格）
import camelot

def extract_tables_camelot(pdf_path):
    # lattice模式：基于表格线识别
    tables_lattice = camelot.read_pdf(pdf_path, flavor='lattice')
    
    # stream模式：基于空白分隔识别
    tables_stream = camelot.read_pdf(pdf_path, flavor='stream')
    
    # 合并结果并导出
    all_tables = tables_lattice.df + tables_stream.df
    for i, df in enumerate(all_tables):
        df.to_csv(f'table_{i}.csv', index=False)

# tabula-py备选方案
import tabula

def extract_tables_tabula(pdf_path):
    # 提取所有表格到DataFrame列表
    dfs = tabula.read_pdf(pdf_path, pages='all', multiple_tables=True)
    
    # 保存为Excel
    with pd.ExcelWriter('tables.xlsx') as writer:
        for i, df in enumerate(dfs):
            df.to_excel(writer, sheet_name=f'Table_{i}')

import re
from PyPDF2 import PdfReader

def extract_contract_info(pdf_path):
    text = extract_text_pypdf2(pdf_path)
    
    # 正则表达式匹配关键字段
    patterns = {
        '甲方': r'甲方[：:]\s*(\S+)',
        '乙方': r'乙方[：:]\s*(\S+)',
        '期限': r'租赁期限[：:]\s*(\d{4}年\d{1,2}月\d{1,2}日[\s至-]*\d{4}年\d{1,2}月\d{1,2}日)',
        '租金': r'租金[：:]\s*(\d+.?\d*)\s*元/月'
    }
    
    return {k: re.search(v, text).group(1) if re.search(v, text) else None 
            for k, v in patterns.items()}

import pdfplumber
import pandas as pd
from datetime import datetime

def process_invoice(pdf_path):
    with pdfplumber.open(pdf_path) as pdf:
        first_page = pdf.pages[0]
        
        # 提取发票头信息
        header_text = first_page.extract_text(x_tolerance=5, y_tolerance=5)[:200]
        invoice_no = re.search(r'发票号码[:：]\s*(\S+)', header_text).group(1)
        invoice_date = re.search(r'开票日期[:：]\s*(\d{4}-\d{2}-\d{2})', header_text).group(1)
        
        # 提取表格数据
        table = first_page.extract_table({
            'vertical_strategy': 'text',
            'horizontal_strategy': 'text'
        })
        
        # 转换为DataFrame并清洗
        df = pd.DataFrame(table[1:], columns=table[0])
        df['金额'] = df['单价'].astype(float) * df['数量'].astype(float)
        
        return {
            '发票编号': invoice_no,
            '开票日期': datetime.strptime(invoice_date, '%Y-%m-%d'),
            '商品明细': df.to_dict('records'),
            '总金额': df['金额'].sum()
        }

from PyPDF2 import PdfReader, PdfWriter

def decrypt_pdf(input_path, output_path, password):
    reader = PdfReader(input_path)
    if reader.is_encrypted:
        reader.decrypt(password)
    
    writer = PdfWriter()
    for page in reader.pages:
        writer.add_page(page)
    
    with open(output_path, 'wb') as f:
        writer.write(f)

import os
from concurrent.futures import ProcessPoolExecutor

def batch_process(pdf_folder, output_folder):
    os.makedirs(output_folder, exist_ok=True)
    
    def process_single(pdf_path):
        output_path = os.path.join(output_folder, os.path.basename(pdf_path).replace('.pdf', '.json'))
        data = extract_contract_info(pdf_path)  # 使用前文定义的提取函数
        with open(output_path, 'w') as f:
            json.dump(data, f, ensure_ascii=False, indent=2)
    
    pdf_files = [os.path.join(pdf_folder, f) for f in os.listdir(pdf_folder) if f.endswith('.pdf')]
    
    with ProcessPoolExecutor(max_workers=8) as executor:
        executor.map(process_single, pdf_files)