乱码名的pdf自动重命名

barnett2016

网站下载出来的pdf，很多是数字 字母的乱码名，文件一多，手动改名很麻烦，
这个脚本就是从pdf里提取文字，再将pdf改成中文名。方便以后搜索查看。

[Python] 纯文本查看 复制代码

import os
import re
import random
from pdfplumber import open as pdf_open
from tkinter import Tk, filedialog, Text, Button, Scrollbar, END
import threading
import time  # 提示缺模块，pip安装即可，python3.7以上皆可正常用

def extract_title_efficiently(pdf_path):
    try:
        with pdf_open(pdf_path) as pdf:
            text = pdf.pages[0].extract_text()
            title_match = re.search(r'标题：(.+)', text)
            if title_match:
                return title_match.group(1).strip()
    except Exception as e:
        return None

def extract_chinese_text_from_first_four_lines(pdf_path):
    try:
        with pdf_open(pdf_path) as pdf:
            text = pdf.pages[0].extract_text().strip()
            lines = text.split('\n')
            first_four_lines = ' '.join(lines[:4]).strip()
            chinese_text = re.sub(r'[^\u4e00-\u9fff\d]+', '', first_four_lines)
            return chinese_text
    except Exception as e:
        return None

def generate_valid_filename(text, max_length=50):
    return re.sub(r'[<>:"/\\|?*\x00-\x1F\x7F]+', '-', text[:max_length])

def generate_unique_filename(folder_path, filename, new_filename):
    base, extension = os.path.splitext(filename)
    counter = 1
    while True:
        new_filename = f"{base}-{new_filename}"
        new_path = os.path.join(folder_path, new_filename + extension)
        if not os.path.exists(new_path):
            return new_filename + extension
        counter += 1

def load_skipped_files(skipped_file_path):
    skipped_files = set()
    if os.path.exists(skipped_file_path):
        with open(skipped_file_path, 'r', encoding='utf-8') as file:
            skipped_files = {line.strip() for line in file.readlines()}
    return skipped_files

def record_skipped_file(skipped_file_path, filename):
    with open(skipped_file_path, 'a', encoding='utf-8') as file:
        file.write(filename + '\n')

def rename_pdf_with_title_or_extracted_text(folder_path, text_box, log_file_path, skipped_file_path):
    if not os.path.isdir(folder_path):
        update_text_box(text_box, "错误：提供的路径不是一个目录。")
        return

    skipped_files = load_skipped_files(skipped_file_path)

    update_text_box(text_box, f"正在处理文件夹：{folder_path}")
    walk_folder(folder_path, skipped_files, text_box, log_file_path, skipped_file_path)

    update_text_box(text_box, "所有文件改名已完成。")

def walk_folder(folder_path, skipped_files, text_box, log_file_path, skipped_file_path):
    for root, dirs, files in os.walk(folder_path):
        for filename in sorted(files):
            if filename.lower().endswith('.pdf') and filename not in skipped_files:
                pdf_path = os.path.join(root, filename)
                start_time = time.time()  # 记录开始时间
                try:
                    title = extract_title_efficiently(pdf_path)
                    if not title:
                        title = extract_chinese_text_from_first_four_lines(pdf_path)
                    if title:
                        new_filename = generate_valid_filename(title)
                        new_filename = generate_unique_filename(root, filename, new_filename)
                        os.rename(pdf_path, os.path.join(root, new_filename))
                        with open(log_file_path, 'a', encoding='utf-8') as log_file:
                            log_file.write(f"文件 '{filename}' 已重命名为 '{new_filename}'\n")
                        update_text_box(text_box, f"文件 '{filename}' 已重命名为 '{new_filename}'")
                    else:
                        record_skipped_file(skipped_file_path, filename)
                        update_text_box(text_box, f"跳过文件：'{filename}'（未找到标题或中文文本）")
                except Exception as e:
                    record_skipped_file(skipped_file_path, filename)
                    update_text_box(text_box, f"跳过文件：'{filename}'（处理时发生错误）")
                elapsed_time = time.time() - start_time  # 计算处理时间
                if elapsed_time > 10:  # 如果处理时间超过10s
                    record_skipped_file(skipped_file_path, filename)
                    update_text_box(text_box, f"跳过文件：'{filename}'（处理时间超过10s）")

def update_text_box(text_box, message):
    text_box.config(state='normal')
    text_box.insert(END, message + '\n')
    text_box.yview(END)  # 滚动到文本框的底部
    text_box.config(state='disabled')

def do_renaming_thread(folder_path, text_box, log_file_path, skipped_file_path):
    rename_pdf_with_title_or_extracted_text(folder_path, text_box, log_file_path, skipped_file_path)

# 创建主窗口
root = Tk()
root.title("PDF Renamer by barnett2016")

# 创建文本框用于显示消息
text_box = Text(root, height=10)
text_box.pack()

# 创建滚动条
scrollbar = Scrollbar(root, orient='vertical', command=text_box.yview)
scrollbar.pack(side='right', fill='y')

# 将滚动条与文本框连接
text_box.config(yscrollcommand=scrollbar.set)

# 存储选择的文件夹路径
selected_folder = None

def browse_folder():
    global selected_folder
    selected_folder = filedialog.askdirectory()
    if selected_folder:
        update_text_box(text_box, f"请选择的文件夹：{selected_folder}")

def do_renaming():
    if selected_folder:
        log_file_path = os.path.join(selected_folder, "改名记录.txt")
        skipped_file_path = os.path.join(selected_folder, "skipped.txt")
        renaming_thread = threading.Thread(target=do_renaming_thread, args=(selected_folder, text_box, log_file_path, skipped_file_path))
        renaming_thread.start()
    else:
        update_text_box(text_box, "错误：请先选择文件夹。")

# 创建按钮用于选择文件夹
browse_button = Button(root, text="打开PDF所在文件夹", command=browse_folder)
browse_button.pack()

# 创建按钮用于执行重命名操作
rename_button = Button(root, text="开始重命名PDF文件", command=do_renaming)
rename_button.pack()

# 启动GUI主循环
root.mainloop()

cku

发票也可重命名吗

tyy474

最麻烦就是高速发票，加油发票，数量多了，下载回来都是乱七八糟的名字，头都大了几圈

YiRan777

高速发票一动就自动乱码了

HjiaLe

tyy474 发表于 2024-11-18 17:07
最麻烦就是高速发票，加油发票，数量多了，下载回来都是乱七八糟的名字，头都大了几圈

那些用的话可能会乱码

loveaqc

HjiaLe 发表于 2024-11-18 17:45
那些用的话可能会乱码

好的谢谢

qcf

好厉害。。。。。

cxx0515

cku 发表于 2024-11-18 16:39
发票也可重命名吗

能获取文件名的应该都可以，发票可以根据字段来组合重命名

x3622691

非常好，改名方便了！

3291952274

谢谢大佬