这是我的日志:[Running] python -u "e:\system\Desktop\项目所需文件\工具\文件搜索工具\File Content Search Tool.py"
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
Exception in thread Thread-1 (perform_search):
Traceback (most recent call last):
File "e:\system\Desktop\\u9879�ڏ�������\�H��\�����r���H��\File Content Search Tool.py", line 437, in search_in_office_file
wb = load_workbook(filepath, read_only=True, data_only=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\cheny9210\AppData\Local\Programs\Python\Python312\Lib\site-packages\openpyxl\reader\excel.py", line 346, in load_workbook
reader = ExcelReader(filename, read_only, keep_vba,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\cheny9210\AppData\Local\Programs\Python\Python312\Lib\site-packages\openpyxl\reader\excel.py", line 123, in __init__
self.archive = _validate_archive(fn)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\cheny9210\AppData\Local\Programs\Python\Python312\Lib\site-packages\openpyxl\reader\excel.py", line 95, in _validate_archive
archive = ZipFile(filename, 'r')
^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\cheny9210\AppData\Local\Programs\Python\Python312\Lib\zipfile\__init__.py", line 1331, in __init__
self.fp = io.open(file, filemode)
^^^^^^^^^^^^^^^^^^^^^^^
PermissionError: [Errno 13] Permission denied: 'E:/SVN/DH_D82D_D83D/trunk/10COMMUNICATION/1001Minutes/12.DRBFM\\~$D82DD83D_CANDI�Ή�_DRBFM.xlsm'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "e:\system\Desktop\\u9879�ڏ�������\�H��\�����r���H��\File Content Search Tool.py", line 330, in perform_search
matches = self.search_in_office_file(file_path, pattern)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "e:\system\Desktop\\u9879�ڏ�������\�H��\�����r���H��\File Content Search Tool.py", line 534, in search_in_office_file
print(f"\u5904��Office������\u8d25 {filepath}: {str(e)}")
UnicodeEncodeError: 'cp932' codec can't encode character '\u5904' in position 0: illegal multibyte sequence
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\cheny9210\AppData\Local\Programs\Python\Python312\Lib\threading.py", line 1075, in _bootstrap_inner
self.run()
File "C:\Users\cheny9210\AppData\Local\Programs\Python\Python312\Lib\threading.py", line 1012, in run
self._target(*self._args, **self._kwargs)
File "e:\system\Desktop\\u9879�ڏ�������\�H��\�����r���H��\File Content Search Tool.py", line 359, in perform_search
print(error_info)
UnicodeEncodeError: 'cp932' codec can't encode character '\u9519' in position 2: illegal multibyte sequence
这是我的代码:import os
import re
import sys
import time
import threading
import tkinter as tk
from tkinter import ttk, filedialog, messagebox, scrolledtext
from tkinter.font import Font
import fnmatch
import subprocess
import shutil
import docx
from openpyxl import load_workbook
import PyPDF2
import zipfile
import chardet
import xlrd # 添加对旧版Excel的支持
class FileSearchApp:
def __init__(self, master):
self.master = master
master.title("高级文件搜索工具")
master.geometry("1200x800")
master.minsize(900, 650)
# 设置现代主题
self.style = ttk.Style()
self.style.theme_use("vista" if sys.platform == "win32" else "aqua")
# 创建主框架
main_frame = ttk.Frame(master, padding=10)
main_frame.pack(fill=tk.BOTH, expand=True)
# 创建左侧搜索面板
search_frame = ttk.LabelFrame(main_frame, text="搜索选项", padding=10)
search_frame.pack(side=tk.LEFT, fill=tk.Y, padx=(0, 10), pady=5)
# 使用网格布局管理器
row = 0
ttk.Label(search_frame, text="搜索目录:").grid(row=row, column=0, sticky="w", pady=5)
self.dir_entry = ttk.Entry(search_frame, width=40)
self.dir_entry.grid(row=row, column=1, padx=5, pady=5, sticky="we")
self.dir_entry.insert(0, os.getcwd())
ttk.Button(search_frame, text="浏览...", command=self.browse_directory).grid(row=row, column=2, padx=5, pady=5)
row += 1
ttk.Label(search_frame, text="关键词:").grid(row=row, column=0, sticky="w", pady=5)
self.keyword_entry = ttk.Entry(search_frame, width=40)
self.keyword_entry.grid(row=row, column=1, padx=5, pady=5, sticky="we")
row += 1
ttk.Label(search_frame, text="文件过滤:").grid(row=row, column=0, sticky="w", pady=5)
self.filter_entry = ttk.Entry(search_frame, width=40)
self.filter_entry.grid(row=row, column=1, padx=5, pady=5, sticky="we")
self.filter_entry.insert(0, "*")
row += 1
# 添加分隔线
ttk.Separator(search_frame, orient=tk.HORIZONTAL).grid(row=row, column=0, columnspan=3, sticky="ew", pady=10)
row += 1
# 搜索选项
options_frame = ttk.Frame(search_frame)
options_frame.grid(row=row, column=0, columnspan=3, sticky="we", padx=5, pady=5)
# 使用网格布局替代pack布局,更紧凑
self.case_var = tk.BooleanVar(value=False)
ttk.Checkbutton(options_frame, text="忽略大小写", variable=self.case_var).grid(row=0, column=0, sticky="w", padx=(0, 10))
self.regex_var = tk.BooleanVar(value=False)
ttk.Checkbutton(options_frame, text="正则表达式", variable=self.regex_var).grid(row=0, column=1, sticky="w", padx=(0, 10))
self.binary_var = tk.BooleanVar(value=False)
self.binary_check = ttk.Checkbutton(options_frame, text="包含二进制", variable=self.binary_var)
self.binary_check.grid(row=0, column=2, sticky="w")
# 添加文件大小限制选项
self.limit_var = tk.BooleanVar(value=True)
ttk.Checkbutton(options_frame, text="限制大小(100MB)", variable=self.limit_var).grid(row=0, column=3, sticky="w", padx=(10, 0))
row += 1
# 添加分隔线
ttk.Separator(search_frame, orient=tk.HORIZONTAL).grid(row=row, column=0, columnspan=3, sticky="ew", pady=10)
row += 1
# 搜索按钮
button_frame = ttk.Frame(search_frame)
button_frame.grid(row=row, column=0, columnspan=3, pady=10)
self.search_button = ttk.Button(button_frame, text="开始搜索", command=self.start_search)
self.search_button.pack(side=tk.LEFT, padx=5)
self.stop_button = ttk.Button(button_frame, text="停止搜索", command=self.stop_search, state=tk.DISABLED)
self.stop_button.pack(side=tk.LEFT, padx=5)
self.export_button = ttk.Button(button_frame, text="导出结果", command=self.export_results)
self.export_button.pack(side=tk.LEFT, padx=5)
row += 1
# 添加分隔线
ttk.Separator(search_frame, orient=tk.HORIZONTAL).grid(row=row, column=0, columnspan=3, sticky="ew", pady=10)
row += 1
# 状态栏
status_frame = ttk.Frame(search_frame)
status_frame.grid(row=row, column=0, columnspan=3, sticky="we", pady=5)
# 状态标签(左对齐)
self.status_label = ttk.Label(status_frame, text="就绪", font=("Arial", 9))
self.status_label.pack(side=tk.LEFT, anchor='w')
# 进度条(中间,可伸缩)
self.progress_var = tk.DoubleVar()
self.progress_bar = ttk.Progressbar(
status_frame,
variable=self.progress_var,
length=200,
mode='determinate'
)
self.progress_bar.pack(side=tk.LEFT, fill=tk.X, expand=True, padx=10)
# 结果统计(右对齐)
self.stats_label = ttk.Label(status_frame, text="", font=("Arial", 9))
self.stats_label.pack(side=tk.RIGHT)
# 创建结果面板
results_frame = ttk.LabelFrame(main_frame, text="搜索结果", padding=10)
results_frame.pack(fill=tk.BOTH, expand=True, padx=(5, 0), pady=5)
# 分割窗格
paned_window = ttk.PanedWindow(results_frame, orient=tk.HORIZONTAL)
paned_window.pack(fill=tk.BOTH, expand=True)
# 左侧文件列表
file_list_frame = ttk.Frame(paned_window)
paned_window.add(file_list_frame, weight=1)
# 使用Treeview替代Listbox
columns = ("filename", "path")
self.file_tree = ttk.Treeview(file_list_frame, columns=columns, show="headings", selectmode="browse")
# 设置列标题
self.file_tree.heading("filename", text="文件名")
self.file_tree.heading("path", text="路径")
# 设置列宽
self.file_tree.column("filename", width=200, anchor="w")
self.file_tree.column("path", width=300, anchor="w")
self.file_tree.pack(side=tk.LEFT, fill=tk.BOTH, expand=True)
self.file_tree.bind('<<TreeviewSelect>>', self.show_file_content)
self.file_tree.bind('<Double-1>', self.open_selected_file)
file_scroll = ttk.Scrollbar(file_list_frame, command=self.file_tree.yview)
file_scroll.pack(side=tk.RIGHT, fill=tk.Y)
self.file_tree.config(yscrollcommand=file_scroll.set)
# 右键菜单
self.file_menu = tk.Menu(self.master, tearoff=0)
self.file_menu.add_command(label="打开文件", command=self.open_selected_file)
self.file_menu.add_command(label="打开文件位置", command=self.open_file_location)
self.file_tree.bind("<Button-3>", self.show_file_context_menu)
# 右侧文件内容预览
content_frame = ttk.Frame(paned_window)
paned_window.add(content_frame, weight=2)
self.content_text = scrolledtext.ScrolledText(
content_frame,
wrap=tk.WORD,
font=("Consolas", 10),
padx=5,
pady=5
)
self.content_text.pack(fill=tk.BOTH, expand=True)
# 文本区域右键菜单
text_menu = tk.Menu(self.master, tearoff=0)
text_menu.add_command(label="复制", command=self.copy_selected_text)
self.content_text.bind("<Button-3>", lambda e: text_menu.tk_popup(e.x_root, e.y_root))
# 高亮标签
self.content_text.tag_configure("match", background="yellow")
self.content_text.tag_configure("linenum", foreground="blue")
self.content_text.tag_configure("header", foreground="darkgreen", font=("Arial", 10, "bold"))
self.content_text.tag_configure("warning", foreground="red", font=("Arial", 10, "italic"))
# 初始化变量
self.results = {}
self.all_files = []
self.file_paths = []
self.stop_requested = False
self.search_thread = None
def browse_directory(self):
directory = filedialog.askdirectory(title="选择搜索目录")
if directory:
self.dir_entry.delete(0, tk.END)
self.dir_entry.insert(0, directory)
def start_search(self):
# 重置状态
self.progress_var.set(0)
self.stop_requested = False
self.results = {}
self.all_files = []
self.file_paths = []
self.file_tree.delete(*self.file_tree.get_children())
self.content_text.delete(1.0, tk.END)
self.status_label.config(text="正在搜索...")
self.search_button.config(state=tk.DISABLED)
self.stop_button.config(state=tk.NORMAL)
self.stats_label.config(text="")
# 获取搜索参数
directory = self.dir_entry.get().strip()
keyword = self.keyword_entry.get().strip()
file_filter = self.filter_entry.get().strip()
# 验证输入
if not directory or not os.path.isdir(directory):
messagebox.showerror("错误", "请选择有效的搜索目录")
self.search_button.config(state=tk.NORMAL)
self.stop_button.config(state=tk.DISABLED)
return
if not keyword:
messagebox.showerror("错误", "请输入搜索关键词")
self.search_button.config(state=tk.NORMAL)
self.stop_button.config(state=tk.DISABLED)
return
# 解析文件过滤器
if file_filter == "":
filter_patterns = ['*']
else:
separators = [';', '|', ' ', ',']
for sep in separators:
if sep in file_filter:
filter_patterns = [pat.strip() for pat in file_filter.split(sep)]
break
else:
filter_patterns = [file_filter]
# 编译搜索模式
flags = re.IGNORECASE if self.case_var.get() else 0
try:
if self.regex_var.get():
pattern = re.compile(keyword, flags)
else:
escaped_keyword = re.escape(keyword)
pattern = re.compile(escaped_keyword, flags)
except re.error as e:
messagebox.showerror("正则表达式错误", f"无效的正则表达式: {str(e)}")
self.search_button.config(state=tk.NORMAL)
self.stop_button.config(state=tk.DISABLED)
return
# 在后台线程中执行搜索
self.search_thread = threading.Thread(
target=self.perform_search,
args=(directory, filter_patterns, pattern),
daemon=True
)
self.search_thread.start()
def perform_search(self, directory, filter_patterns, pattern):
"""在后台线程中执行文件搜索"""
try:
# 收集所有匹配的文件
all_files = []
for root, _, files in os.walk(directory):
if self.stop_requested:
self.master.after(0, lambda: self.status_label.config(text="搜索已取消"))
return
for file in files:
file_path = os.path.join(root, file)
# 检查文件大小限制(避免处理超大文件)
try:
file_size = os.path.getsize(file_path)
if file_size > 100 * 1024 * 1024: # 100MB
continue
except:
continue
# 检查是否符合任一过滤模式
if any(fnmatch.fnmatch(file, pat) for pat in filter_patterns):
all_files.append(file_path)
self.all_files = all_files
total_files = len(all_files)
# 初始化进度条
self.master.after(0, lambda: self.progress_bar.config(maximum=total_files))
self.master.after(0, lambda: self.stats_label.config(text=f"扫描到 {total_files} 个文件"))
# 搜索每个文件
self.results = {}
processed = 0
matches_found = 0
for file_path in self.all_files:
if self.stop_requested:
break
processed += 1
# 更新进度条(安全方式)
self.master.after(0, lambda v=processed: self.progress_var.set(v))
if processed % 10 == 0:
# 每处理10个文件更新一次进度
self.master.after(0, lambda p=processed, t=total_files:
self.stats_label.config(text=f"处理中: {p}/{t} 文件 ({round(p/t*100,1)}%)"))
# 忽略二进制文件(除非用户选择包含)
if not self.binary_var.get() and self.is_binary(file_path):
continue
# 获取文件扩展名
_, ext = os.path.splitext(file_path)
ext_lower = ext.lower()
# 处理Office文档
if ext_lower in ['.docx', '.xlsx', '.xls', '.xlsm', '.pptx', '.pdf', '.doc']:
matches = self.search_in_office_file(file_path, pattern)
# 处理压缩文件
elif ext_lower in ['.zip', '.rar', '.7z', '.tar', '.gz']:
matches = self.search_in_archive(file_path, pattern)
# 处理文本文件
else:
matches = self.search_in_text_file(file_path, pattern)
if matches:
self.results[file_path] = matches
matches_found += len(matches)
# 在UI线程中添加文件到列表
filename = os.path.basename(file_path)
self.master.after(0, lambda fp=file_path, fn=filename:
self.file_tree.insert("", "end", values=(fn, fp)))
# 更新完成状态
if self.stop_requested:
status_text = f"搜索已取消 - 找到 {len(self.results)} 个文件, {matches_found} 个匹配项"
else:
status_text = f"搜索完成 - 找到 {len(self.results)} 个文件, {matches_found} 个匹配项"
self.master.after(0, lambda: self.status_label.config(text=status_text))
self.master.after(0, lambda: self.stats_label.config(text=f"已处理 {processed}/{total_files} 文件"))
self.master.after(0, lambda: self.progress_var.set(total_files))
except Exception as e:
# 记录详细错误日志
error_info = f"搜索错误: {type(e).__name__} - {str(e)}"
print(error_info)
with open("search_errors.log", "a") as log:
log.write(f"{time.strftime('%Y-%m-%d %H:%M:%S')} - {error_info}\n")
import traceback
traceback.print_exc(file=log)
self.master.after(0, lambda: messagebox.showerror(
"搜索错误",
f"发生严重错误: {error_info}\n详细信息已记录到日志"
))
finally:
self.master.after(0, lambda: self.search_button.config(state=tk.NORMAL))
self.master.after(0, lambda: self.stop_button.config(state=tk.DISABLED))
self.search_thread = None
def search_in_text_file(self, filepath, pattern):
"""在文本文件中搜索匹配项"""
matches = []
try:
encoding = self.detect_encoding(filepath)
try:
with open(filepath, 'r', encoding=encoding, errors='replace') as f:
for line_num, line in enumerate(f, 1):
if pattern.search(line):
cleaned_line = line.strip()
if len(cleaned_line) > 150:
cleaned_line = cleaned_line[:150] + "..."
matches.append((line_num, cleaned_line))
except UnicodeDecodeError:
# 特殊编码处理回退
with open(filepath, 'rb') as f:
content = f.read()
try:
text = content.decode('utf-8', errors='replace')
except:
text = content.decode('latin-1', errors='replace')
for line_num, line in enumerate(text.splitlines(), 1):
if pattern.search(line):
cleaned_line = line.strip()
if len(cleaned_line) > 150:
cleaned_line = cleaned_line[:150] + "..."
matches.append((line_num, cleaned_line))
except Exception as e:
print(f"读取文本文件失败 {filepath}: {str(e)}")
return matches
def search_in_office_file(self, filepath, pattern):
"""在Office文件中搜索文本内容"""
matches = []
_, ext = os.path.splitext(filepath)
ext_lower = ext.lower()
try:
# DOCX文件处理
if ext_lower == '.docx':
doc = docx.Document(filepath)
# 搜索段落
for i, para in enumerate(doc.paragraphs, 1):
if para.text and pattern.search(para.text):
matches.append((i, f"段落 {i}: {para.text[:100]}" + ("..." if len(para.text) > 100 else "")))
# 搜索表格
for table in doc.tables:
for row_idx, row in enumerate(table.rows, 1):
for cell_idx, cell in enumerate(row.cells, 1):
if cell.text and pattern.search(cell.text):
content = cell.text.strip()
if len(content) > 100:
content = content[:100] + "..."
matches.append((row_idx, f"表格 行{row_idx}列{cell_idx}: {content}"))
# XLSX/XLS文件处理
elif ext_lower in ('.xlsx', '.xls', '.xlsm'):
# 处理新格式Excel文件
if ext_lower in ('.xlsx', '.xlsm'):
wb = load_workbook(filepath, read_only=True, data_only=True)
for sheet_name in wb.sheetnames:
sheet = wb[sheet_name]
for row_idx, row in enumerate(sheet.iter_rows(values_only=True), 1):
for col_idx, cell in enumerate(row, 1):
if cell is not None and pattern.search(str(cell)):
cell_ref = f"{chr(64+col_idx)}{row_idx}"
cell_value = str(cell).strip()
if len(cell_value) > 100:
cell_value = cell_value[:100] + "..."
matches.append((row_idx, f"工作表 '{sheet_name}' 单元格 {cell_ref}: {cell_value}"))
# 处理旧格式Excel文件
elif ext_lower == '.xls':
wb = xlrd.open_workbook(filepath)
for sheet_idx in range(wb.nsheets):
sheet = wb.sheet_by_index(sheet_idx)
for row_idx in range(sheet.nrows):
for col_idx in range(sheet.ncols):
cell = sheet.cell_value(row_idx, col_idx)
if cell and pattern.search(str(cell)):
cell_ref = f"{chr(65+col_idx)}{row_idx+1}"
cell_value = str(cell).strip()
if len(cell_value) > 100:
cell_value = cell_value[:100] + "..."
matches.append((row_idx+1, f"工作表 '{sheet.name}' 单元格 {cell_ref}: {cell_value}"))
# PPTX文件处理
elif ext_lower == '.pptx':
from pptx import Presentation
ppt = Presentation(filepath)
# 搜索幻灯片文本
for slide_idx, slide in enumerate(ppt.slides, 1):
for shape in slide.shapes:
if hasattr(shape, "text"):
if shape.text and pattern.search(shape.text):
content = shape.text.strip()
if len(content) > 100:
content = content[:100] + "..."
matches.append((slide_idx, f"幻灯片 {slide_idx}: {content}"))
# PDF文件处理
elif ext_lower == '.pdf':
with open(filepath, 'rb') as f:
pdf = PyPDF2.PdfReader(f)
for page_num in range(len(pdf.pages)):
page_text = pdf.pages[page_num].extract_text()
if page_text and pattern.search(page_text):
# 提取匹配内容
matches_found = []
for match in pattern.finditer(page_text):
context = page_text[max(0, match.start()-20):match.end()+20]
context = context.replace('\n', ' ').strip()
matches_found.append(context)
# 添加到结果
if matches_found:
preview = "; ".join(matches_found[:3]) # 显示前3个匹配
if len(matches_found) > 3:
preview += f" ... (+{len(matches_found)-3} 更多)"
matches.append((page_num+1, f"页面 {page_num+1}: {preview}"))
# 旧版DOC文件处理
elif ext_lower == '.doc':
try:
# 尝试使用antiword转换DOC为文本
result = subprocess.run(['antiword', filepath], capture_output=True, text=True, timeout=10)
if result.returncode == 0:
doc_text = result.stdout
for line_num, line in enumerate(doc_text.split('\n'), 1):
if line and pattern.search(line):
cleaned_line = line.strip()
if len(cleaned_line) > 150:
cleaned_line = cleaned_line[:150] + "..."
matches.append((line_num, cleaned_line))
except Exception:
# 备用方法:使用python-doc处理
import win32com.client
word = win32com.client.Dispatch("Word.Application")
word.Visible = False
doc = word.Documents.Open(filepath)
doc_text = doc.Content.Text
doc.Close()
word.Quit()
for line_num, line in enumerate(doc_text.split('\n'), 1):
if line and pattern.search(line):
cleaned_line = line.strip()
if len(cleaned_line) > 150:
cleaned_line = cleaned_line[:150] + "..."
matches.append((line_num, cleaned_line))
except Exception as e:
print(f"处理Office文件失败 {filepath}: {str(e)}")
return matches
def search_in_archive(self, filepath, pattern):
"""在压缩文件中搜索匹配项"""
matches = []
_, ext = os.path.splitext(filepath)
ext_lower = ext.lower()
try:
# ZIP文件处理
if ext_lower in ('.zip', '.jar', '.war'):
with zipfile.ZipFile(filepath, 'r') as archive:
for name in archive.namelist():
# 只处理文本文件和Office文档
if not name.endswith(('/')) and not self.is_binary(name):
try:
with archive.open(name) as file:
content = file.read(4096) # 只读取前4KB
# 尝试检测编码
result = chardet.detect(content)
encoding = result['encoding'] if result['confidence'] > 0.7 else 'utf-8'
# 解码内容并搜索
try:
text_content = content.decode(encoding, errors='replace')
if pattern.search(text_content):
matches.append((name, f"压缩文件中的文件: {name}"))
except:
# 二进制内容搜索
if pattern.search(content):
matches.append((name, f"压缩文件中的文件(二进制内容): {name}"))
except Exception:
continue
# 其他压缩格式(需要外部工具)
elif ext_lower in ('.rar', '.7z', '.tar', '.gz'):
# 使用7zip命令行工具解压并搜索
temp_dir = tempfile.mkdtemp()
try:
subprocess.run(['7z', 'x', filepath, f'-o{temp_dir}'],
stdout=subprocess.PIPE, stderr=subprocess.PIPE,
check=True, timeout=60)
# 递归搜索解压的目录
for root, _, files in os.walk(temp_dir):
for file in files:
full_path = os.path.join(root, file)
_, file_ext = os.path.splitext(file)
file_ext = file_ext.lower()
# 只在文本/Office文件中搜索
if file_ext in ['', '.txt', '.py', '.java', '.c', '.cpp', '.h', '.html',
'.xml', '.json', '.csv', '.docx', '.xlsx', '.pptx', '.pdf']:
if file_ext in ['.docx', '.xlsx', '.pptx', '.pdf']:
file_matches = self.search_in_office_file(full_path, pattern)
else:
file_matches = self.search_in_text_file(full_path, pattern)
if file_matches:
matches.append((file, f"压缩文件中的文件: {file}"))
finally:
shutil.rmtree(temp_dir, ignore_errors=True)
except Exception as e:
print(f"处理压缩文件失败 {filepath}: {str(e)}")
return matches
def detect_encoding(self, filepath):
"""改进的文件编码检测方法"""
try:
# 尝试读取文件前4KB进行编码检测
with open(filepath, 'rb') as f:
raw_data = f.read(4096)
# 使用chardet进行编码检测
result = chardet.detect(raw_data)
# 优先使用检测到的编码,否则尝试常见编码
if result['confidence'] > 0.7:
return result['encoding']
# 中文环境常用编码回退策略
common_encodings = ['utf-8', 'gbk', 'gb2312', 'gb18030', 'latin1']
for encoding in common_encodings:
try:
# 尝试解码验证
raw_data.decode(encoding, errors='strict')
return encoding
except UnicodeDecodeError:
continue
# 默认使用UTF-8
return 'utf-8'
except Exception:
return 'utf-8'
def is_binary(self, filepath):
"""检查文件是否为二进制文件"""
try:
with open(filepath, 'rb') as f:
chunk = f.read(1024)
if b'\0' in chunk: # 空字节是二进制文件的标志
return True
# 检查高字节值
if any(byte >= 0x80 for byte in chunk):
return True
return False
except:
return False
def stop_search(self):
"""停止当前搜索"""
self.stop_requested = True
self.status_label.config(text="正在停止搜索...")
self.stop_button.config(state=tk.DISABLED)
# 冻结进度条显示当前进度
self.progress_bar.config(mode='indeterminate' if self.progress_var.get() == 0 else 'determinate')
def export_results(self):
"""导出搜索结果"""
if not self.results:
messagebox.showinfo("导出结果", "没有可导出的搜索结果")
return
file_path = filedialog.asksaveasfilename(
title="保存搜索结果为",
defaultextension=".csv",
filetypes=[("CSV 文件", "*.csv"), ("文本文件", "*.txt")]
)
if not file_path:
return
try:
with open(file_path, 'w', encoding='utf-8') as f:
# 写出CSV头部
f.write("文件路径,匹配行号,匹配内容\n")
# 写出每项结果
for file, matches in self.results.items():
for line_num, match_content in matches:
# 清理内容中的逗号
cleaned_content = match_content.replace('"', '""').replace(',', ';')
f.write(f'"{file}",{line_num},"{cleaned_content}"\n')
messagebox.showinfo("导出成功", f"搜索结果已保存到:\n{file_path}")
except Exception as e:
messagebox.showerror("导出错误", f"导出失败: {str(e)}")
def show_file_content(self, event=None):
"""在预览区域显示文件内容"""
# 获取选中的文件
selection = self.file_tree.selection()
if not selection:
return
selected_item = selection[0]
filepath = self.file_tree.item(selected_item, 'values')[1]
# 清空预览区域
self.content_text.delete(1.0, tk.END)
# 获取文件扩展名
_, ext = os.path.splitext(filepath)
ext_lower = ext.lower()
# 显示文件路径标题
self.content_text.insert(tk.END, f"文件路径: {filepath}\n", "header")
# 处理不同文件类型
try:
# 处理Office文档
if ext_lower in ['.docx', '.xlsx', '.xls', '.xlsm', '.pptx', '.pdf', '.doc']:
matches = self.results.get(filepath, [])
if not matches:
self.content_text.insert(tk.END, "\n未找到匹配内容\n", "warning")
return
self.content_text.insert(tk.END, f"\n找到 {len(matches)} 个匹配项:\n\n", "header")
# 显示每个匹配项
for i, (line_num, content) in enumerate(matches, 1):
self.content_text.insert(tk.END, f"[匹配项 {i}] 位置: {line_num}\n")
self.content_text.insert(tk.END, f"{content}\n\n")
# 处理压缩文件
elif ext_lower in ['.zip', '.rar', '.7z', '.tar', '.gz']:
matches = self.results.get(filepath, [])
if not matches:
self.content_text.insert(tk.END, "\n未找到匹配内容\n", "warning")
return
self.content_text.insert(tk.END, f"\n找到 {len(matches)} 个匹配项:\n\n", "header")
for i, (file_in_zip, content) in enumerate(matches, 1):
self.content_text.insert(tk.END, f"[匹配项 {i}] 文件: {file_in_zip}\n")
self.content_text.insert(tk.END, f"{content}\n\n")
# 处理文本文件
else:
# 获取关键词高亮模式
keyword = self.keyword_entry.get().strip()
flags = re.IGNORECASE if self.case_var.get() else 0
if self.regex_var.get():
try:
pattern = re.compile(keyword, flags)
except:
pattern = None
else:
pattern = re.compile(re.escape(keyword), flags)
# 显示文件内容并高亮匹配
self.content_text.insert(tk.END, "\n文件内容:\n\n", "header")
# 限制预览内容大小(最多显示1000行)
max_preview_lines = 1000
try:
encoding = self.detect_encoding(filepath)
with open(filepath, 'r', encoding=encoding, errors='replace') as f:
line_count = 0
for line in f:
line_count += 1
if line_count > max_preview_lines:
self.content_text.insert(tk.END, f"\n... (文件过大,仅显示前{max_preview_lines}行)\n", "warning")
break
# 插入行号
self.content_text.insert(tk.END, f"{line_count:4d} | ", "linenum")
# 插入行内容并高亮匹配
if pattern:
start_idx = 0
for match in pattern.finditer(line):
# 插入匹配前的文本
self.content_text.insert(tk.END, line[start_idx:match.start()])
# 插入高亮的匹配文本
self.content_text.insert(tk.END, match.group(), "match")
start_idx = match.end()
# 插入匹配后的文本
self.content_text.insert(tk.END, line[start_idx:])
else:
self.content_text.insert(tk.END, line)
except UnicodeDecodeError:
self.content_text.insert(tk.END, "\n无法解码此文件内容(可能是二进制文件)\n", "warning")
except Exception as e:
self.content_text.insert(tk.END, f"\n读取文件时出错: {str(e)}\n", "warning")
except Exception as e:
self.content_text.insert(tk.END, f"\n加载文件内容出错: {str(e)}\n", "warning")
def open_selected_file(self, event=None):
"""用系统默认程序打开选中的文件"""
selection = self.file_tree.selection()
if not selection:
return
selected_item = selection[0]
filepath = self.file_tree.item(selected_item, 'values')[1]
try:
if sys.platform == "win32":
os.startfile(filepath)
elif sys.platform == "darwin": # macOS
subprocess.run(["open", filepath])
else: # Linux
subprocess.run(["xdg-open", filepath])
except Exception as e:
messagebox.showerror("打开文件失败", f"无法打开文件: {str(e)}")
def open_file_location(self):
"""在文件资源管理器中打开文件所在位置"""
selection = self.file_tree.selection()
if not selection:
return
selected_item = selection[0]
filepath = self.file_tree.item(selected_item, 'values')[1]
folder = os.path.dirname(filepath)
try:
if sys.platform == "win32":
subprocess.run(["explorer", "/select,", filepath])
elif sys.platform == "darwin": # macOS
subprocess.run(["open", "-R", filepath])
else: # Linux
subprocess.run(["xdg-open", folder])
except Exception as e:
messagebox.showerror("打开位置失败", f"无法打开位置: {str(e)}")
def show_file_context_menu(self, event):
"""显示文件列表的右键菜单"""
item = self.file_tree.identify_row(event.y)
if item:
self.file_tree.selection_set(item)
self.file_menu.tk_popup(event.x_root, event.y_root)
def copy_selected_text(self):
"""复制预览区域中选中的文本"""
selected_text = self.content_text.get(tk.SEL_FIRST, tk.SEL_LAST)
if selected_text:
self.master.clipboard_clear()
self.master.clipboard_append(selected_text)
# 程序入口
if __name__ == "__main__":
root = tk.Tk()
app = FileSearchApp(root)
# 添加图标(如果有)
try:
if sys.platform == "win32":
root.iconbitmap("search_icon.ico")
else:
img = tk.PhotoImage(file="search_icon.png")
root.iconphoto(True, img)
except:
pass
root.mainloop()
检查问题,搜索出错