获取多个PDF文件的内容并保存到excel上

# shuang
# 开发时间：2023/12/9 22:03import pdfplumber
import re
import os
import pandas as pd
import datetimedef re_text(bt, text):# re 搜索正则匹配 包含re.compile包含的文字内容m1 = re.search(bt, text)if m1 is not None:return re_block(m1[0])return Nonedef re_block(text):# 去掉空格、中英文小括号、中文冒号变英文冒号；去掉中文全角空格return text.replace(' ', '').replace('　', '').replace('）', '').replace(')', '').replace('：', ':')def get_pdf(dir_path):pdf_file = []for root, sub_dirs, file_names in os.walk(dir_path):for name in file_names:if name.endswith('.pdf'):filepath = os.path.join(root, name)pdf_file.append(filepath)return pdf_filedef read(xlsx_path, pdf_root):# 构建excel writer 写入器writer = pd.ExcelWriter(xlsx_path)# 如果字段不通用 则需要单独拎出来判断，这里我全部拎出来做了if判断all_fields = {"序号": [],"服务商": [],"车型": [],"上车日期": [],"上车时间": [],"城市": [],"起点": [],"终点": [],"金额(元)": [],}filenames = get_pdf(pdf_root)for filename in filenames:print(f"正在读取：{filename}")with pdfplumber.open(filename) as pdf:first_page = pdf.pages[0]pdf_text = first_page.extract_text()print(pdf_text)table = first_page.extract_tables()[0]# 纳税人识别号 购买方for (id, t) in enumerate(table):if id > 0:curr1 = t[0].split(' ')curr = []for item in curr1:curr.append(item.replace('\n', ''))# t_ = str(t).replace(" ", "")all_fields["序号"].append(curr[0])all_fields["服务商"].append(curr[1])all_fields["车型"].append(curr[2])all_fields["上车时间"].append(curr[3])all_fields["上车日期"].append(curr[4])all_fields["城市"].append(curr[5])all_fields["起点"].append(curr[6])all_fields["终点"].append(curr[7])if len(curr) > 8:all_fields["金额(元)"].append(curr[8])else:all_fields["金额(元)"].append(curr[7])df = pd.DataFrame(all_fields)df.to_excel(writer)writer._save()returnpdf_root = r"行程单"
now = datetime.datetime.now()
now = str(now).split(' ')[0]
print(now)
xlsx_path = f"行程单{now}.xlsx"read(xlsx_path, pdf_root)