Python 对目录下pdf文件进行关键字检测，并保存检测结果

 import os
import tkinter as tk
from tkinter import filedialog, messagebox, scrolledtext
import pandas as pd
from PyPDF2 import PdfReader
import threading
import chardet,csv

class PDFKeywordDetector:
    def __init__(self, root):
        self.root = root
        self.root.title("PDF 关键字检测器")
        self.keywords = []
        self.keywords_file = "keywords.txt" 
        self.is_running = False
        self.excel_file = "检测结果.xlsx"
        self.setup_ui()

    def setup_ui(self):
        # 目录选择
        # 创建一个标签，用于提示用户选择目录
        self.directory_label = tk.Label(self.root, text="选择目录:")
        # 将标签放置在第一行第一列
        self.directory_label.grid(row=0, column=0, padx=5, pady=5, sticky='w')

        # 创建一个文本框，用于显示用户选择的目录
        self.directory_entry = tk.Entry(self.root, width=50)
        # 将文本框放置在第一行第二列
        self.directory_entry.grid(row=0, column=1, padx=5, pady=5, sticky='w')

        # 创建一个按钮，用于让用户选择目录
        self.browse_button = tk.Button(self.root, text="浏览", command=self.browse_directory)
        # 将按钮放置在第一行第三列
        self.browse_button.grid(row=0, column=2, padx=5, pady=5, sticky='w')

        # 关键字输入
        self.keyword_label = tk.Label(self.root, text="关键字 (用逗号分隔):")
        self.keyword_label.grid(row=1, column=0, padx=5, pady=5, sticky='w')

        self.keyword_entry = tk.Entry(self.root, width=50)
        self.keyword_entry.grid(row=1, column=1, padx=5, pady=5, sticky='w')

        self.keyword_add_button = tk.Button(self.root, text="添加关键字", command=self.add_keyword)
        self.keyword_add_button.grid(row=1, column=2, padx=5, pady=5, sticky='w')

        self.keyword_listbox = tk.Listbox(self.root, width=50, height=10)
        self.keyword_listbox.grid(row=2, column=0, columnspan=2, padx=5, pady=5, sticky='w')

        self.keyword_remove_button = tk.Button(self.root, text="删除选中关键字", command=self.remove_keyword)
        self.keyword_remove_button.grid(row=2, column=2, padx=5, pady=5, sticky='w')

        # 检测关键字文件的编码
        with open(self.keywords_file, 'rb') as f:
            result = chardet.detect(f.read())
        file_encoding = result['encoding']

        # 读取关键字文件中的关键字
        with open(self.keywords_file, 'r', encoding=file_encoding) as f:
            self.keywords = [line.strip() for line in f.readlines()]
            self.keyword_listbox.delete(0, tk.END)
            for keyword in self.keywords:
                self.keyword_listbox.insert(tk.END, keyword)

        # 检测按钮和进度
        self.start_button = tk.Button(self.root, text="开始检测", command=self.start_detection)
        self.start_button.grid(row=3, column=0, padx=5, pady=5, sticky='w')

        self.pause_button = tk.Button(self.root, text="暂停检测", command=self.pause_detection)
        self.pause_button.grid(row=3, column=1, padx=5, pady=5, sticky='w')

        self.progress_label = tk.Label(self.root, text="进度: 0/0")
        self.progress_label.grid(row=4, column=0, columnspan=3, padx=5, pady=5, sticky='w')

        # 日志显示
        self.log_text = scrolledtext.ScrolledText(self.root, width=70, height=15)
        self.log_text.grid(row=5, column=0, columnspan=3, padx=5, pady=5, sticky='w')

    def browse_directory(self):
        directory = filedialog.askdirectory()
        if directory:
            self.directory_entry.insert(0, directory)

    def add_keyword(self):
        keywords = self.keyword_entry.get().split(',')
        for keyword in keywords:
            keyword = keyword.strip()
            if keyword and keyword not in self.keywords:
                self.keywords.append(keyword)
                with open(self.keywords_file, 'a') as f:
                    f.write(keyword + '\n')
                self.keyword_listbox.insert(tk.END, keyword)
        self.keyword_entry.delete(0, tk.END)

    def remove_keyword(self):
        selected_indices = self.keyword_listbox.curselection()
        for index in selected_indices[::-1]:
            keyword = self.keyword_listbox.get(index)
            self.keywords.remove(keyword)
            with open(self.keywords_file, 'r') as f:
                lines = f.readlines()
            with open(self.keywords_file, 'w') as f:
                for line in lines:
                    if line.strip() != keyword:
                        f.write(line)
            self.keyword_listbox.delete(index)

    def start_detection(self):
        # 设置is_running为True
        self.is_running = True
        # 禁用开始按钮
        self.start_button.config(state=tk.DISABLED)
        # 启用暂停按钮
        self.pause_button.config(state=tk.NORMAL)
        # 获取输入的目录
        self.directory = self.directory_entry.get()
        # 如果目录为空，提示错误
        if not self.directory:
            messagebox.showerror("错误", "请选择一个目录")
            return
        # 如果关键字为空，提示错误
        if not self.keywords:
            messagebox.showerror("错误", "请添加至少一个关键字")
            return

        # 加载已检测的文件
        self.detected_files = self.load_detected_files()
        # 计算未检测的文件数量
        self.total_files = len([f for f in os.listdir(self.directory) if f.endswith('.pdf') and f not in self.detected_files])
        # 初始化已处理文件数量
        self.processed_files = 0

        # 启动线程，检测关键字
        threading.Thread(target=self.detect_keywords).start()

    def pause_detection(self):
        # 设置is_running为False
        self.is_running = False
        # 启用开始按钮
        self.start_button.config(state=tk.NORMAL)
        # 禁用暂停按钮
        self.pause_button.config(state=tk.DISABLED)

    def load_detected_files(self):
        # 获取当前目录
        current_directory = self.directory_entry.get()

        # 拼接已检测文件的路径
        detected_file = os.path.join(current_directory, "已检测.csv")

        # 如果文件存在
        if os.path.exists(detected_file):
            # 读取文件
            with open(detected_file, 'rb') as f:
                result = chardet.detect(f.read())
            # 用相应的编码来读取文件
            df = pd.read_csv(detected_file, encoding=result['encoding'])
            # 返回文件名的唯一值列表
            return df['已检测文件名'].unique().tolist()
        # 如果文件不存在，返回空列表
        return []

    def save_detection_result(self, results):
        # 如果excel文件存在
        if os.path.exists(self.excel_file):
            # 读取excel文件
            df = pd.read_excel(self.excel_file)
            # 将results添加到df中
            df = df._append(pd.DataFrame(results), ignore_index=True)
        else:
            # 如果excel文件不存在，则创建一个新的DataFrame
            df = pd.DataFrame(results)
        # 将df写入excel文件
        excel_file = os.path.join(self.directory, "检测结果.xlsx")
        df.to_excel(excel_file, index=False)

    def browse_keyword_file(self):
        # 打开文件对话框，让用户选择一个文本文件
        file_path = filedialog.askopenfilename(filetypes=[("文本文件", "*.txt")])
        if file_path:
            # 获取文件的绝对路径
            file_path = os.path.abspath(file_path)  # 获取绝对路径
            # 清空文本框
            self.keyword_file_entry.delete(0, tk.END)
            # 将选择的文件路径插入文本框
            self.keyword_file_entry.insert(0, file_path)

    def detect_keywords(self):
        results = []
        count = 0

        for file in os.listdir(self.directory):
            if not self.is_running:
                break
            if file.endswith('.pdf') and file not in self.detected_files:
                self.processed_files += 1
                self.log_text.insert(tk.END, f"检测文件: {file}\n")
                self.log_text.yview(tk.END)
                file_path = os.path.join(self.directory, file)
                try:
                    f = open(file_path, "rb")
                    pdf = PdfReader(f)
                    for page_num in range(len(pdf.pages)):
                        page_text = pdf.pages[page_num].extract_text()
                        for keyword in self.keywords:
                            if keyword in page_text:
                                results.append({"文件名": file, "检测页码": page_num + 1, "关键字": keyword})
                except Exception as e:
                    self.log_text.insert(tk.END, f"错误处理文件 {file}: {e}\n")
                    self.log_text.yview(tk.END)
                finally:
                    f.close()
                count += 1
                if count % 100 == 0:
                    self.save_detection_result(results)
                    results = []
                self.progress_label.config(text=f"进度: {self.processed_files}/{self.total_files}")
                self.root.update()
                self.detected_files.append(file)  # 将已检测的文件添加到detected_files列表中
        if results:
            self.save_detection_result(results)
            # 将detected_files列表写入"已检测.csv"文件
        detected_file = os.path.join(self.directory, "已检测.csv")
        with open(detected_file, "w", newline="", encoding="GBK") as csvfile:
            writer = csv.writer(csvfile)
            writer.writerow(["已检测文件名"])
            for file in self.detected_files:
                writer.writerow([file])    
        self.is_running = False
        self.start_button.config(state=tk.NORMAL)
        self.pause_button.config(state=tk.DISABLED)
        self.log_text.insert(tk.END, "检测完成\n")
        self.log_text.yview(tk.END)

if __name__ == "__main__":
    root = tk.Tk()
    app = PDFKeywordDetector(root)
    root.mainloop()

本代码非常原始，有需求可以自行修改