【】20250527PDF文件拆分成多个pdf（两页一份，用幼儿班级姓名命名文件）

背景需求：

今天春游，上海海昌公园。路上保健老师收到前几天幼儿的屈光视力检查单PDF。

她说：所有孩子的通知都做在一个PDF里，我没法单独发给班主任。你有什么办法拆开来？

我说：“没问题，问deep seek，它会写拆分代码

设计过程：

PDF拆分成2页一个PDF

代码展示

'''
屈光PDF按照2张一份，拆分成多个编号
deepseek 阿夏
20250527
'''
from PyPDF2 import PdfReader, PdfWriter
import osdef split_pdf_every_2_pages(input_pdf_path, output_folder):# 创建输出文件夹（如果不存在）if not os.path.exists(output_folder):os.makedirs(output_folder)# 读取PDF文件reader = PdfReader(input_pdf_path)total_pages = len(reader.pages)print(f"总页数: {total_pages}")# 计算需要分割的文件数量num_files = (total_pages + 1) // 2for i in range(num_files):writer = PdfWriter()# 计算当前文件的起始和结束页码start_page = i * 2end_page = min(start_page + 2, total_pages)# 添加页面到新PDFfor page_num in range(start_page, end_page):writer.add_page(reader.pages[page_num])# 生成输出文件名output_filename = os.path.join(output_folder, f"{i+1:003}_P{start_page+1}-P{end_page}.pdf")# 写入新PDF文件with open(output_filename, "wb") as out:writer.write(out)print(f"已创建: {output_filename}")# 使用示例
path=r'C:\Users\jg2yXRZ\OneDrive\桌面\20250527视力复诊屈光拆分'
input_pdf =path + r"\复诊通知XXXx.pdf"  # 替换为你的PDF文件路径
output_dir = path + r"\拆分文件"  # 输出文件夹
os.makedirs(output_dir,exist_ok=True)split_pdf_every_2_pages(input_pdf, output_dir)

顺利实现两页一份PDF

但是我还希望提取姓名、年级、班级号，作为文件名。

经过反复测试后，我发现姓名固定在第6行，年级固定在第7行，但是班级号的位置是不确定，可能在68，69和某些不确定的行上。

deepseek晚上总是容易断网，所以改用了星火讯飞写

代码展示：

'''
屈光PDF按照2张一份，拆分成多个。提取单数页上的姓名（6）年级（7），班级（68、69或不确定的位置）
将大班七班改成大7班。做成文件名
deepseek 阿夏
20250527
'''import fitz  # PyMuPDF
import os
import re
import pandas as pd  # 确保已安装pandas库
from PyPDF2 import PdfReader, PdfWriterdef chinese_to_digit(chinese_num):"""将中文数字转换为阿拉伯数字。支持一到十的转换。"""chinese_dict = {'一': 1, '二': 2, '三': 3, '四': 4,'五': 5, '六': 6, '七': 7, '八': 8, '九': 9, '十': 10}return chinese_dict.get(chinese_num, chinese_num)def extract_student_info(input_pdf_path, target_pages):"""动态提取学生姓名、年级和班级信息。:param input_pdf_path: PDF文件路径:param target_pages: 需要处理的页面列表（例如，单数页）:return: 包含学生信息的字典列表"""doc = fitz.open(input_pdf_path)results = []# 定义匹配“X班”的正则表达式，X为阿拉伯数字或中文数字，可能带括号class_pattern = re.compile(r'[（(]?(\d+|[一二三四五六七八九十]+)班[）)]?')  # 根据实际格式调整括号和数字类型for page_num in target_pages:page = doc.load_page(page_num - 1)  # fitz的页码从0开始text = page.get_text("text")lines = [line.strip() for line in text.split('\n') if line.strip()]# 初始化变量name = Nonegrade = Noneclasses = []# 从第6行和第7行提取姓名和年级if len(lines) >= 6:name = lines[5].strip()  # 第6行（索引5）if len(lines) >= 7:grade = lines[6].strip()  # 第7行（索引6）# 遍历所有行查找班级信息for line in lines:matches = class_pattern.findall(line)for match in matches:# 将中文数字转换为阿拉伯数字converted_match = ''.join([str(chinese_to_digit(char)) if char in '一二三四五六七八九十' else char for char in match])class_name = converted_match  # match 已经是字符串，无需调用 group()if class_name not in classes:classes.append(class_name)# 将提取的信息添加到结果中if name and grade:result = {"page_num": page_num,"name": name,"grade": grade[0],"class": classes}results.append(result)else:print(f"第{page_num}页缺少必要的信息。")return resultsdef convert_students_info(students):"""将学生信息转换为 "大7班_陈宇阳" 格式的字符串列表。:param students: 包含学生信息的字典列表:return: 格式化后的字符串列表"""formatted_list = []for student in students:grade = student.get('grade', '')class_list = student.get('class', [])name = student.get('name', '')class_str = ''.join(class_list)formatted_str = f"{grade}{class_str}班_{name}"formatted_list.append(formatted_str)return formatted_listdef split_pdf_every_2_pages(input_pdf_path, output_folder, formatted_names):"""将PDF每两页分割成一个新的PDF文件，并使用formatted_names列表中的名称命名文件。:param input_pdf_path: 输入PDF文件路径:param output_folder: 输出文件夹路径:param formatted_names: 用于命名的文件名列表:return: None"""# 创建输出文件夹（如果不存在）if not os.path.exists(output_folder):os.makedirs(output_folder)# 读取PDF文件reader = PdfReader(input_pdf_path)total_pages = len(reader.pages)print(f"总页数: {total_pages}")# 计算需要分割的文件数量num_files = (total_pages + 1) // 2print(f"需要创建的文件数量: {num_files}")# 确保formatted_names的长度足够if len(formatted_names) < num_files:print("警告: formatted_names列表长度小于需要创建的文件数量。多余的文件将使用默认命名。")for i in range(num_files):writer = PdfWriter()# 计算当前文件的起始和结束页码start_page = i * 2end_page = min(start_page + 2, total_pages)# 添加页面到新PDFfor page_num in range(start_page, end_page):writer.add_page(reader.pages[page_num])# 获取对应的文件名，如果不足则使用默认命名if i < len(formatted_names):filename = f"{formatted_names[i]}.pdf"else:filename = f"{i+1:003}_P{start_page+1}-P{end_page}.pdf"# 生成输出文件路径output_filename = os.path.join(output_folder, filename)# 写入新PDF文件with open(output_filename, "wb") as out:writer.write(out)print(f"已创建: {output_filename}")def main():# 设置PDF文件路径path = r'C:\Users\jg2yXRZ\OneDrive\桌面\20250527视力复诊屈光拆分'input_pdf = os.path.join(path, "复诊通知XXXX.pdf")output_dir = os.path.join(path, "拆分文件")  # 输出文件夹os.makedirs(output_dir, exist_ok=True)# 获取所有单数页（假设页码从1开始）doc = fitz.open(input_pdf)all_pages = list(range(1, len(doc) + 1))odd_pages = [p for p in all_pages if p % 2 != 0]print(f"处理的单数页: {odd_pages}")# 提取内容students_info = extract_student_info(input_pdf, odd_pages)print(f"提取到的学生信息数量: {len(students_info)}")# 转换并打印格式化后的列表formatted_list = convert_students_info(students_info)print("格式化后的学生列表:")for item in formatted_list:print(item)# 分割PDF并使用formatted_list命名文件split_pdf_every_2_pages(input_pdf, output_dir, formatted_list)print("PDF分割完成。")if __name__ == "__main__":main()

结果展示

感觉必须添加序号（数据编码）

'''
屈光PDF按照2张一份，拆分成多个。提取单数页上的姓名（6）年级（7），班级（68、69或不确定的位置）
将大班七班改成大7班。做成文件名、有编号（先中班、再大班）
deepseek 阿夏
20250527
'''# 导入必要的依赖项
import os
from fpdf import FPDF
import re
import pandas as pd  # 确保已安装pandas库
from PyPDF2 import PdfReader, PdfWriter
import fitz  # PyMuPDFdef chinese_to_digit(chinese_num):"""将中文数字转换为阿拉伯数字。支持一到十的转换。"""chinese_dict = {'一': 1, '二': 2, '三': 3, '四': 4,'五': 5, '六': 6, '七': 7, '八': 8, '九': 9, '十': 10}return chinese_dict.get(chinese_num, chinese_num)def extract_student_info(input_pdf_path, target_pages):"""动态提取学生姓名、年级和班级信息。:param input_pdf_path: PDF文件路径:param target_pages: 需要处理的页面列表（例如，单数页）:return: 包含学生信息的字典列表"""doc = fitz.open(input_pdf_path)results = []# 定义匹配“X班”的正则表达式，X为阿拉伯数字或中文数字，可能带括号class_pattern = re.compile(r'[（(]?(\d+|[一二三四五六七八九十]+)班[）)]?')  # 根据实际格式调整括号和数字类型for page_num in target_pages:page = doc.load_page(page_num - 1)  # fitz的页码从0开始text = page.get_text("text")lines = [line.strip() for line in text.split('\n') if line.strip()]# 初始化变量name = Nonegrade = Noneclasses = []# 从第6行和第7行提取姓名和年级if len(lines) >= 6:name = lines[5].strip()  # 第6行（索引5）if len(lines) >= 7:grade = lines[6].strip()  # 第7行（索引6）# 遍历所有行查找班级信息for line in lines:matches = class_pattern.findall(line)for match in matches:# 将中文数字转换为阿拉伯数字converted_match = ''.join([str(chinese_to_digit(char)) if char in '一二三四五六七八九十' else char for char in match])class_name = converted_match  # match 已经是字符串，无需调用 group()if class_name not in classes:classes.append(class_name)# 将提取的信息添加到结果中if name and grade:result = {"page_num": page_num,"name": name,"grade": grade[0],"class": classes}results.append(result)else:print(f"第{page_num}页缺少必要的信息。")return resultsdef convert_students_info(students):"""将学生信息转换为 "大7班_陈宇阳" 格式的字符串列表。:param students: 包含学生信息的字典列表:return: 格式化后的字符串列表"""formatted_list = []for student in students:grade = student.get('grade', '')class_list = student.get('class', [])name = student.get('name', '')class_str = ''.join(class_list)formatted_str = f"{grade}{class_str}班_{name}"formatted_list.append(formatted_str)return formatted_listdef split_pdf_every_2_pages(input_pdf_path, output_folder, formatted_names):"""将PDF每两页分割成一个新的PDF文件，并使用formatted_names列表中的名称命名文件。同时在文件名前添加三位数的序号前缀。:param input_pdf_path: 输入PDF文件路径:param output_folder: 输出文件夹路径:param formatted_names: 用于命名的文件名列表:return: None"""# 创建输出文件夹（如果不存在）if not os.path.exists(output_folder):os.makedirs(output_folder)# 读取PDF文件reader = PdfReader(input_pdf_path)total_pages = len(reader.pages)print(f"总页数: {total_pages}")# 计算需要分割的文件数量num_files = (total_pages + 1) // 2print(f"需要创建的文件数量: {num_files}")# 确保formatted_names的长度足够if len(formatted_names) < num_files:print("警告: formatted_names列表长度小于需要创建的文件数量。多余的文件将使用默认命名。")for i in range(num_files):writer = PdfWriter()# 计算当前文件的起始和结束页码start_page = i * 2end_page = min(start_page + 2, total_pages)# 添加页面到新PDFfor page_num in range(start_page, end_page):writer.add_page(reader.pages[page_num])# 获取对应的文件名，如果不足则使用默认命名if i < len(formatted_names):base_filename = formatted_names[i]else:base_filename = f"P{start_page+1}-P{end_page}"# 添加三位数的序号前缀numbered_filename = f"{i+1:03}_{base_filename}_202505屈光复查通知.pdf"# 生成输出文件路径output_filename = os.path.join(output_folder, numbered_filename)# 写入新PDF文件with open(output_filename, "wb") as out:writer.write(out)print(f"已创建: {output_filename}")def main():# 设置PDF文件路径path = r'C:\Users\jg2yXRZ\OneDrive\桌面\20250527视力复诊屈光拆分'input_pdf = os.path.join(path, "复诊通知XXXX.pdf")output_dir = os.path.join(path, "拆分文件")  # 输出文件夹os.makedirs(output_dir, exist_ok=True)# 获取所有单数页（假设页码从1开始）doc = fitz.open(input_pdf)all_pages = list(range(1, len(doc) + 1))odd_pages = [p for p in all_pages if p % 2 != 0]print(f"处理的单数页: {odd_pages}")# 提取内容students_info = extract_student_info(input_pdf, odd_pages)print(f"提取到的学生信息数量: {len(students_info)}")# 转换并打印格式化后的列表formatted_list = convert_students_info(students_info)print("格式化后的学生列表:")for item in formatted_list:print(item)# 分割PDF并使用formatted_list命名文件，同时在文件名前添加序号前缀split_pdf_every_2_pages(input_pdf, output_dir, formatted_list)print("PDF分割完成。")if __name__ == "__main__":main()

按照先中班、后大班的顺序

为了明确文件内容，再添加了一个说明

最后是把所有PDF按班级合并文件夹，打包

'''
屈光PDF按照2张一份，拆分成多个。提取单数页上的姓名（6）年级（7），班级（68、69或不确定的位置）
将大班七班改成大7班。做成文件名、有编号（先中班、再大班）、
按班级分别保存，并打包，便于发送
deepseek 阿夏
20250527
'''
、import os
import re
import shutil
import zipfile
from PyPDF2 import PdfReader, PdfWriter
import fitz  # PyMuPDFdef chinese_to_digit(chinese_num):"""将中文数字转换为阿拉伯数字。支持一到十的转换。"""chinese_dict = {'一': 1, '二': 2, '三': 3, '四': 4,'五': 5, '六': 6, '七': 7, '八': 8, '九': 9, '十': 10}return chinese_dict.get(chinese_num, chinese_num)def extract_student_info(input_pdf_path, target_pages):"""从PDF中提取学生信息（姓名、年级、班级）"""doc = fitz.open(input_pdf_path)results = []class_pattern = re.compile(r'[（(]?(\d+|[一二三四五六七八九十]+)班[）)]?')for page_num in target_pages:page = doc.load_page(page_num - 1)text = page.get_text("text")lines = [line.strip() for line in text.split('\n') if line.strip()]name = lines[5].strip() if len(lines) >= 6 else Nonegrade = lines[6].strip() if len(lines) >= 7 else Noneclasses = []for line in lines:matches = class_pattern.findall(line)for match in matches:converted_match = ''.join([str(chinese_to_digit(char)) if char in '一二三四五六七八九十' else char for char in match])if converted_match not in classes:classes.append(converted_match)if name and grade:results.append({"page_num": page_num,"name": name,"grade": grade[0],"class": classes})else:print(f"第{page_num}页缺少必要的信息。")return resultsdef convert_students_info(students):"""格式化学生信息为'大7班_陈宇阳'格式"""return [f"{s['grade']}{''.join(s['class'])}班_{s['name']}" for s in students]def split_pdf_every_2_pages(input_pdf_path, output_folder, formatted_names):"""将PDF每两页分割成单独文件"""if not os.path.exists(output_folder):os.makedirs(output_folder)reader = PdfReader(input_pdf_path)total_pages = len(reader.pages)num_files = (total_pages + 1) // 2for i in range(num_files):writer = PdfWriter()start_page = i * 2end_page = min(start_page + 2, total_pages)for page_num in range(start_page, end_page):writer.add_page(reader.pages[page_num])base_filename = formatted_names[i] if i < len(formatted_names) else f"P{start_page+1}-P{end_page}"output_filename = os.path.join(output_folder, f"{i+1:03}_{base_filename}_屈光复查202505.pdf")with open(output_filename, "wb") as out:writer.write(out)print(f"已创建: {output_filename}")def classify_pdfs_by_class(source_folder):"""将PDF文件按班级分类到不同文件夹"""pdf_files = [f for f in os.listdir(source_folder) if f.lower().endswith('.pdf')]if not pdf_files:print(f"在文件夹 {source_folder} 中没有找到PDF文件")returnclass_stats = {}for pdf_file in pdf_files:match = re.search(r'(中\d+班|大\d+班)', pdf_file)if match:class_name = match.group(1)class_folder = os.path.join(source_folder, class_name)os.makedirs(class_folder, exist_ok=True)src_path = os.path.join(source_folder, pdf_file)dest_path = os.path.join(class_folder, pdf_file)shutil.move(src_path, dest_path)print(f"移动文件: {pdf_file} -> {class_folder}")class_stats[class_name] = class_stats.get(class_name, 0) + 1else:print(f"无法从文件名 {pdf_file} 中提取班级信息")print("\n分类完成，统计结果:")for class_name, count in class_stats.items():print(f"{class_name}: {count}个文件")return class_stats.keys()def zip_class_folders(source_folder, class_folders):"""将班级文件夹打包为ZIP压缩包"""print("\n=== 开始打包班级文件夹 ===")for folder_name in class_folders:folder_path = os.path.join(source_folder, folder_name)zip_path = os.path.join(source_folder, f"{folder_name}.zip")with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:for root, dirs, files in os.walk(folder_path):for file in files:file_path = os.path.join(root, file)arcname = os.path.relpath(file_path, folder_path)zipf.write(file_path, arcname)print(f"已创建压缩包: {zip_path}")def main():# 设置路径base_path = r'C:\Users\jg2yXRZ\OneDrive\桌面\20250527视力复诊屈光拆分'input_pdf = os.path.join(base_path, "复诊通知XXXX.pdf")output_dir = os.path.join(base_path, "拆分文件")# 第一步：拆分PDFprint("=== 开始拆分PDF ===")os.makedirs(output_dir, exist_ok=True)doc = fitz.open(input_pdf)odd_pages = [p for p in range(1, len(doc) + 1) if p % 2 != 0]students_info = extract_student_info(input_pdf, odd_pages)formatted_list = convert_students_info(students_info)split_pdf_every_2_pages(input_pdf, output_dir, formatted_list)print("PDF拆分完成！\n")# 第二步：分类PDFprint("=== 开始分类PDF ===")class_folders = classify_pdfs_by_class(output_dir)print("PDF分类完成！")# 第三步：打包文件夹zip_class_folders(output_dir, class_folders)if __name__ == "__main__":main()

我看到终端显示了每个班级有几份，我还想标明文件内容是“屈光复查”

最终代码

'''
屈光PDF按照2张一份，拆分成多个。提取单数页上的姓名（6）年级（7），班级（68、69或不确定的位置）
将大班七班改成大7班。做成文件名、有编号（先中班、再大班）
按照班级转移PDF，班级文件名包括人数、屈光
deepseek 阿夏
20250527
'''import os
import re
import shutil
import zipfile
from PyPDF2 import PdfReader, PdfWriter
import fitz  # PyMuPDFdef chinese_to_digit(chinese_num):"""将中文数字转换为阿拉伯数字。支持一到十的转换。"""chinese_dict = {'一': 1, '二': 2, '三': 3, '四': 4,'五': 5, '六': 6, '七': 7, '八': 8, '九': 9, '十': 10}return chinese_dict.get(chinese_num, chinese_num)def extract_student_info(input_pdf_path, target_pages):"""从PDF中提取学生信息（姓名、年级、班级）"""doc = fitz.open(input_pdf_path)results = []class_pattern = re.compile(r'[（(]?(\d+|[一二三四五六七八九十]+)班[）)]?')for page_num in target_pages:page = doc.load_page(page_num - 1)text = page.get_text("text")lines = [line.strip() for line in text.split('\n') if line.strip()]name = lines[5].strip() if len(lines) >= 6 else Nonegrade = lines[6].strip() if len(lines) >= 7 else Noneclasses = []for line in lines:matches = class_pattern.findall(line)for match in matches:converted_match = ''.join([str(chinese_to_digit(char)) if char in '一二三四五六七八九十' else char for char in match])if converted_match not in classes:classes.append(converted_match)if name and grade:results.append({"page_num": page_num,"name": name,"grade": grade[0],"class": classes})else:print(f"第{page_num}页缺少必要的信息。")return resultsdef convert_students_info(students):"""格式化学生信息为'大7班_陈宇阳'格式"""return [f"{s['grade']}{''.join(s['class'])}班_{s['name']}" for s in students]def split_pdf_every_2_pages(input_pdf_path, output_folder, formatted_names):"""将PDF每两页分割成单独文件"""if not os.path.exists(output_folder):os.makedirs(output_folder)reader = PdfReader(input_pdf_path)total_pages = len(reader.pages)num_files = (total_pages + 1) // 2for i in range(num_files):writer = PdfWriter()start_page = i * 2end_page = min(start_page + 2, total_pages)for page_num in range(start_page, end_page):writer.add_page(reader.pages[page_num])base_filename = formatted_names[i] if i < len(formatted_names) else f"P{start_page+1}-P{end_page}"output_filename = os.path.join(output_folder, f"{i+1:03}_{base_filename}_屈光复查202505.pdf")with open(output_filename, "wb") as out:writer.write(out)print(f"已创建: {output_filename}")def classify_pdfs_by_class(source_folder):"""将PDF文件按班级分类到不同文件夹，并在文件夹名中加入人数统计"""pdf_files = [f for f in os.listdir(source_folder) if f.lower().endswith('.pdf')]if not pdf_files:print(f"在文件夹 {source_folder} 中没有找到PDF文件")returnclass_stats = {}# 第一次遍历：统计每个班级的人数for pdf_file in pdf_files:match = re.search(r'(中\d+班|大\d+班)', pdf_file)if match:class_name = match.group(1)class_stats[class_name] = class_stats.get(class_name, 0) + 1# 第二次遍历：移动文件到带人数的文件夹for pdf_file in pdf_files:match = re.search(r'(中\d+班|大\d+班)', pdf_file)if match:class_name = match.group(1)count = class_stats[class_name]new_folder_name = f"{class_name}_{count}人_屈光复查202505"class_folder = os.path.join(source_folder, new_folder_name)os.makedirs(class_folder, exist_ok=True)src_path = os.path.join(source_folder, pdf_file)dest_path = os.path.join(class_folder, pdf_file)shutil.move(src_path, dest_path)print(f"移动文件: {pdf_file} -> {new_folder_name}")print("\n分类完成，统计结果:")for class_name, count in class_stats.items():print(f"{class_name}: {count}个文件")# 返回带人数的文件夹名列表return [f"{k}({v}人)" for k, v in class_stats.items()]def zip_class_folders(source_folder, class_folders):"""将班级文件夹打包为ZIP压缩包"""print("\n=== 开始打包班级文件夹 ===")for folder_name in class_folders:folder_path = os.path.join(source_folder, folder_name)zip_path = os.path.join(source_folder, f"{folder_name}_屈光复查202505.zip")with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:for root, dirs, files in os.walk(folder_path):for file in files:file_path = os.path.join(root, file)arcname = os.path.relpath(file_path, folder_path)zipf.write(file_path, arcname)print(f"已创建压缩包: {zip_path}")def main():# 设置路径base_path = r'C:\Users\jg2yXRZ\OneDrive\桌面\20250527视力复诊屈光拆分'input_pdf = os.path.join(base_path, "复诊通知XXXX.pdf")output_dir = os.path.join(base_path, "拆分文件")# 第一步：拆分PDFprint("=== 开始拆分PDF ===")os.makedirs(output_dir, exist_ok=True)doc = fitz.open(input_pdf)odd_pages = [p for p in range(1, len(doc) + 1) if p % 2 != 0]students_info = extract_student_info(input_pdf, odd_pages)formatted_list = convert_students_info(students_info)split_pdf_every_2_pages(input_pdf, output_dir, formatted_list)print("PDF拆分完成！\n")# 第二步：分类PDFprint("=== 开始分类PDF ===")class_folders = classify_pdfs_by_class(output_dir)print("PDF分类完成！")# 第三步：打包文件夹zip_class_folders(output_dir, class_folders)if __name__ == "__main__":main()

保健老师说：信息化时代下，幼儿的远端视力越来越差了。