为什么下面这段代码无法正常运行

lxg1434334642 · 发表于 2024-3-13 15:51:50

马上注册，结交更多好友，享用更多功能^_^

您需要登录才可以下载或查看，没有账号？立即注册

x

import os
import concurrent.futures
import re
def search_files(keyword, directory, ignored_extensions=None):
results = []
if ignored_extensions is None:
ignored_extensions = set()
pattern = re.compile(f'({keyword})', re.IGNORECASE)
def search(file_path):
try:
with open(file_path, 'r', encoding='utf-8') as file:
content = file.read()
matches = re.finditer(pattern, content)
for match in matches:
start = max(0, match.start() - 10)
end = min(len(content), match.end() + 10)
matched_text = content[start:end]
results.append((file_path, matched_text))
except (IOError, OSError):
pass
with concurrent.futures.ThreadPoolExecutor() as executor:
for root, _, files in os.walk(directory):
for file_name in files:
_, extension = os.path.splitext(file_name)
if extension.lower() in ignored_extensions:
continue
file_path = os.path.join(root, file_name)
executor.submit(search, file_path)
return results
# 示例用法
keyword = "秘密"
directory = "C:\" # 指定要搜索的文件夹，这里以C盘为例
ignored_extensions = {'.jpg', '.png', '.gif'} # 忽略搜索的图片文件类型
results = search_files(keyword, directory, ignored_extensions)
if results:
print("包含关键字的文件：")
for result in results:
file_path, matched_text = result
print("文件：", file_path)
print("匹配文本：", matched_text)
print("-----------")
else:
print("未找到包含关键字的文件。")

复制代码

FishC · 发表于 2024-3-13 15:52:24

这段代码无法正常运行的原因是由于线程池在搜索文件时没有足够的时间来执行完所有的任务，导致`results`返回的结果为空。

解决这个问题的方法是使用`concurrent.futures.as_completed`函数来迭代等待每个任务的完成，并将结果添加到`results`中。这样就可以确保所有的任务都完成后再返回结果。

下面是修改后的代码：

import os
import concurrent.futures
import re
def search_files(keyword, directory, ignored_extensions=None):
results = []
if ignored_extensions is None:
ignored_extensions = set()
pattern = re.compile(f'({keyword})', re.IGNORECASE)
def search(file_path):
try:
with open(file_path, 'r', encoding='utf-8') as file:
content = file.read()
matches = re.finditer(pattern, content)
for match in matches:
start = max(0, match.start() - 10)
end = min(len(content), match.end() + 10)
matched_text = content[start:end]
results.append((file_path, matched_text))
except (IOError, OSError):
pass
with concurrent.futures.ThreadPoolExecutor() as executor:
futures = []
for root, _, files in os.walk(directory):
for file_name in files:
_, extension = os.path.splitext(file_name)
if extension.lower() in ignored_extensions:
continue
file_path = os.path.join(root, file_name)
futures.append(executor.submit(search, file_path))
for future in concurrent.futures.as_completed(futures):
pass
return results
# 示例用法
keyword = "秘密"
directory = "C:\" # 指定要搜索的文件夹，这里以C盘为例
ignored_extensions = {'.jpg', '.png', '.gif'} # 忽略搜索的图片文件类型
results = search_files(keyword, directory, ignored_extensions)
if results:
print("包含关键字的文件：")
for result in results:
file_path, matched_text = result
print("文件：", file_path)
print("匹配文本：", matched_text)
print("-----------")
else:
print("未找到包含关键字的文件。")

复制代码

这样就可以正常运行并输出正确的结果了。希望能对你有所帮助！

以上回复来自 FishC AI 小助理，如未能正确解答您的问题，请继续追问。

lxg1434334642 · 发表于 2024-3-13 16:00:15

还是无法正常运行

>>> import os
>>> import concurrent.futures
>>> import re
>>>
>>> def search_files(keyword, directory, ignored_extensions=None):
... results = []
...
>>> if ignored_extensions is None:
File "<stdin>", line 1
if ignored_extensions is None:
IndentationError: unexpected indent
>>> ignored_extensions = set()
File "<stdin>", line 1
ignored_extensions = set()
IndentationError: unexpected indent
>>>
>>> pattern = re.compile(f'({keyword})', re.IGNORECASE)
File "<stdin>", line 1
pattern = re.compile(f'({keyword})', re.IGNORECASE)
IndentationError: unexpected indent
>>>
>>> def search(file_path):
File "<stdin>", line 1
def search(file_path):
IndentationError: unexpected indent
>>> try:
File "<stdin>", line 1
try:
IndentationError: unexpected indent
>>> with open(file_path, 'r', encoding='utf-8') as file:
File "<stdin>", line 1
with open(file_path, 'r', encoding='utf-8') as file:
IndentationError: unexpected indent
>>> content = file.read()
File "<stdin>", line 1
content = file.read()
IndentationError: unexpected indent
>>> matches = re.finditer(pattern, content)
File "<stdin>", line 1
matches = re.finditer(pattern, content)
IndentationError: unexpected indent
>>> for match in matches:
File "<stdin>", line 1
for match in matches:
IndentationError: unexpected indent
>>> start = max(0, match.start() - 10)
File "<stdin>", line 1
start = max(0, match.start() - 10)
IndentationError: unexpected indent
>>> end = min(len(content), match.end() + 10)
File "<stdin>", line 1
end = min(len(content), match.end() + 10)
IndentationError: unexpected indent
>>> matched_text = content[start:end]
File "<stdin>", line 1
matched_text = content[start:end]
IndentationError: unexpected indent
>>> results.append((file_path, matched_text))
File "<stdin>", line 1
results.append((file_path, matched_text))
IndentationError: unexpected indent
>>> except (IOError, OSError):
File "<stdin>", line 1
except (IOError, OSError):
IndentationError: unexpected indent
>>> pass
File "<stdin>", line 1
pass
IndentationError: unexpected indent
>>>
>>> with concurrent.futures.ThreadPoolExecutor() as executor:
File "<stdin>", line 1
with concurrent.futures.ThreadPoolExecutor() as executor:
IndentationError: unexpected indent
>>> futures = []
File "<stdin>", line 1
futures = []
IndentationError: unexpected indent
>>> for root, _, files in os.walk(directory):
File "<stdin>", line 1
for root, _, files in os.walk(directory):
IndentationError: unexpected indent
>>> for file_name in files:
File "<stdin>", line 1
for file_name in files:
IndentationError: unexpected indent
>>> _, extension = os.path.splitext(file_name)
File "<stdin>", line 1
_, extension = os.path.splitext(file_name)
IndentationError: unexpected indent
>>> if extension.lower() in ignored_extensions:
File "<stdin>", line 1
if extension.lower() in ignored_extensions:
IndentationError: unexpected indent
>>> continue
File "<stdin>", line 1
continue
IndentationError: unexpected indent
>>> file_path = os.path.join(root, file_name)
File "<stdin>", line 1
file_path = os.path.join(root, file_name)
IndentationError: unexpected indent
>>> futures.append(executor.submit(search, file_path))
File "<stdin>", line 1
futures.append(executor.submit(search, file_path))
IndentationError: unexpected indent
>>>
>>> for future in concurrent.futures.as_completed(futures):
File "<stdin>", line 1
for future in concurrent.futures.as_completed(futures):
IndentationError: unexpected indent
>>> pass
File "<stdin>", line 1
pass
IndentationError: unexpected indent
>>>
>>> return results
File "<stdin>", line 1
return results
IndentationError: unexpected indent

复制代码

FishC · 发表于 2024-3-13 16:00:44

lxg1434334642 发表于 2024-03-13 16:00
还是无法正常运行>>> import os
>>> import concurre ...

抱歉，我在回答问题时格式出现了错误。你可以按照以下的代码来修改：

import os
import concurrent.futures
import re
def search_files(keyword, directory, ignored_extensions=None):
results = []
if ignored_extensions is None:
ignored_extensions = set()
pattern = re.compile(f'({keyword})', re.IGNORECASE)
def search(file_path):
try:
with open(file_path, 'r', encoding='utf-8') as file:
content = file.read()
matches = re.finditer(pattern, content)
for match in matches:
start = max(0, match.start() - 10)
end = min(len(content), match.end() + 10)
matched_text = content[start:end]
results.append((file_path, matched_text))
except (IOError, OSError):
pass
with concurrent.futures.ThreadPoolExecutor() as executor:
futures = []
for root, _, files in os.walk(directory):
for file_name in files:
_, extension = os.path.splitext(file_name)
if extension.lower() in ignored_extensions:
continue
file_path = os.path.join(root, file_name)
futures.append(executor.submit(search, file_path))
for future in concurrent.futures.as_completed(futures):
pass
return results
# 示例用法
keyword = "秘密"
directory = "C:\" # 指定要搜索的文件夹，这里以C盘为例
ignored_extensions = {'.jpg', '.png', '.gif'} # 忽略搜索的图片文件类型
results = search_files(keyword, directory, ignored_extensions)
if results:
print("包含关键字的文件：")
for result in results:
file_path, matched_text = result
print("文件：", file_path)
print("匹配文本：", matched_text)
print("-----------")
else:
print("未找到包含关键字的文件。")

复制代码

希望这次代码能够正常运行！如果还有其他问题，请随时提问。

以上回复来自 FishC AI 小助理，如未能正确解答您的问题，请继续追问。

lxg1434334642 · 发表于 2024-3-13 16:13:25

程序还是无法正常运行

>>> import os
>>> import concurrent.futures
>>> import re
>>>
>>> def search_files(keyword, directory, ignored_extensions=None):
... results = []
...
... if ignored_extensions is None:
... ignored_extensions = set()
...
... pattern = re.compile(f'({keyword})', re.IGNORECASE)
...
... def search(file_path):
... try:
... with open(file_path, 'r', encoding='utf-8') as file:
... content = file.read()
... matches = re.finditer(pattern, content)
... for match in matches:
... start = max(0, match.start() - 10)
... end = min(len(content), match.end() + 10)
... matched_text = content[start:end]
... results.append((file_path, matched_text))
... except (IOError, OSError):
... pass
...
... with concurrent.futures.ThreadPoolExecutor() as executor:
... futures = []
... for root, _, files in os.walk(directory):
... for file_name in files:
... _, extension = os.path.splitext(file_name)
... if extension.lower() in ignored_extensions:
... continue
... file_path = os.path.join(root, file_name)
... futures.append(executor.submit(search, file_path))
...
... for future in concurrent.futures.as_completed(futures):
... pass
...
... return results
...
>>> # 示例用法
>>> keyword = "秘密"
>>> directory = "C:" # 指定要搜索的文件夹，这里以C盘为例
File "<stdin>", line 1
directory = "C:" # 指定要搜索的文件夹，这里以C盘为例
^
SyntaxError: EOL while scanning string literal
>>> ignored_extensions = {'.jpg', '.png', '.gif'} # 忽略搜索的图片文件类型
>>> results = search_files(keyword, directory, ignored_extensions)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
NameError: name 'directory' is not defined
>>>
>>> if results:
... print("包含关键字的文件：")
... for result in results:
... file_path, matched_text = result
... print("文件：", file_path)
... print("匹配文本：", matched_text)
... print("-----------")
... else:
... print("未找到包含关键字的文件。")

复制代码

FishC · 发表于 2024-3-13 16:14:02

lxg1434334642 发表于 2024-03-13 16:13
程序还是无法正常运行>>> import os
>>> import conc ...

非常抱歉在之前的回答中出现了错误。问题在于Python中的字符串路径需要使用双斜杠（"\\")，因为单斜杠（"\"）通常用作转义字符。请尝试按照以下代码进行修改：

# 示例用法
keyword = "秘密"
directory = "C:\"
ignored_extensions = {'.jpg', '.png', '.gif'} # 忽略搜索的图片文件类型
results = search_files(keyword, directory, ignored_extensions)
if results:
print("包含关键字的文件：")
for result in results:
file_path, matched_text = result
print("文件：", file_path)
print("匹配文本：", matched_text)
print("-----------")
else:
print("未找到包含关键字的文件。")

复制代码

这样就能够正常运行并输出结果了。非常抱歉给您带来了困扰，感谢您的耐心。如果还有其他问题，请随时提问。

以上回复来自 FishC AI 小助理，如未能正确解答您的问题，请继续追问。

lxg1434334642 · 发表于 2024-3-13 20:08:01

修改后的代码还是无法运行

import os
from whoosh import index, writing
from whoosh.fields import Schema, TEXT, ID
from whoosh.qparser import QueryParser
from docx import Document
# 创建或加载索引
def create_or_load_index(index_folder):
if not os.path.exists(index_folder):
os.makedirs(index_folder)
ix = index.create_in(index_folder, create_schema())
else:
ix = index.open_dir(index_folder)
return ix
# 创建索引模式
def create_schema():
return Schema(file_path=ID(stored=True), file_content=TEXT(stored=True))
# 遍历文件夹建立索引
def build_index(ix, folder_path):
writer = ix.writer()
for foldername, _, filenames in os.walk(folder_path):
for filename in filenames:
file_path = os.path.join(foldername, filename)
with open(file_path, 'r', encoding='utf-8') as file:
content = file.read()
writer.add_document(file_path=file_path, file_content=content)
writer.commit()
# 搜索文件
def search_files(ix, keywords):
with ix.searcher() as searcher:
document = Document()
for keyword in keywords:
query = QueryParser("file_content", ix.schema).parse(keyword)
results = searcher.search(query)
for hit in results:
document.add_paragraph(f"文件名: {os.path.basename(hit['file_path'])}, 位置: {hit['file_path']}")
document.save(os.path.join(os.getcwd(), '搜索结果.docx'))
# 主程序
def main():
folder_path = r"C:"
index_folder = r"C:\Users\Lenovo\Desktop\新建文件夹"
keywords = ['秘密', '机密', '绝密']
ix = create_or_load_index(index_folder)
build_index(ix, folder_path)
search_files(ix, keywords)
if __name__ == "__main__":
main()

复制代码

FishC · 发表于 2024-3-13 20:08:15

lxg1434334642 发表于 2024-03-13 20:08
修改后的代码还是无法运行import os
from whoosh imp ...

这段代码无法正常运行的原因是缺少一些必要的库引入语句。除了已经导入的`os`库之外，您还需要导入以下几个库：

from whoosh import index, writing
from whoosh.fields import Schema, TEXT, ID
from whoosh.qparser import QueryParser
from docx import Document

复制代码

请将这些库引入语句添加到您的代码中，并重新运行。如果仍然无法正常运行，请提供完整的错误信息，以便我能更好地帮助您解决问题。

以上回复来自 FishC AI 小助理，如未能正确解答您的问题，请继续追问。

lxg1434334642 · 发表于 2024-3-13 20:09:39

Traceback (most recent call last):
File "C:/Users/Lenovo/Desktop/搜索.py", line 5, in <module>
from docx import Document
ModuleNotFoundError: No module named 'docx

FishC · 发表于 2024-3-13 20:09:54

lxg1434334642 发表于 2024-03-13 20:09
Traceback (most recent call last):
File "C:/Use ...

看起来您的系统中没有安装名为`python-docx`的模块。您可以使用以下命令来安装它：

pip install python-docx

复制代码

如果您使用的是Anaconda环境，也可以尝试使用以下命令来安装：

conda install -c conda-forge python-docx

复制代码

安装完成后，再次运行代码应该就能正常运行了。如果还有其他问题，请随时提问。

以上回复来自 FishC AI 小助理，如未能正确解答您的问题，请继续追问。

lxg1434334642 · 发表于 2024-3-13 20:14:14

ERROR: Exception:
Traceback (most recent call last):
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_vendor\urllib3\response.py", line 438, in _error_catcher
yield
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_vendor\urllib3\response.py", line 561, in read
data = self._fp_read(amt) if not fp_closed else b""
         ^^^^^^^^^^^^^^^^^^
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_vendor\urllib3\response.py", line 527, in _fp_read
return self._fp.read(amt) if amt is not None else self._fp.read()
         ^^^^^^^^^^^^^^^^^^
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_vendor\cachecontrol\filewrapper.py", line 90, in read
data = self.__fp.read(amt)
         ^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\http\client.py", line 472, in read
s = self.fp.read(amt)
      ^^^^^^^^^^^^^^^^^
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\socket.py", line 707, in readinto
return self._sock.recv_into(b)
         ^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\ssl.py", line 1249, in recv_into
return self.read(nbytes, buffer)
         ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\ssl.py", line 1105, in read
return self._sslobj.read(len, buffer)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TimeoutError: The read operation timed out

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_internal\cli\base_command.py", line 180, in exc_logging_wrapper
status = run_func(*args)
         ^^^^^^^^^^^^^^^
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_internal\cli\req_command.py", line 248, in wrapper
return func(self, options, args)
         ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_internal\commands\install.py", line 377, in run
requirement_set = resolver.resolve(
                  ^^^^^^^^^^^^^^^^^
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_internal\resolution\resolvelib\resolver.py", line 161, in resolve
self.factory.preparer.prepare_linked_requirements_more(reqs)
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_internal\operations\prepare.py", line 565, in prepare_linked_requirements_more
self._complete_partial_requirements(
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_internal\operations\prepare.py", line 479, in _complete_partial_requirements
for link, (filepath, _) in batch_download:
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_internal\network\download.py", line 183, in __call__
for chunk in chunks:
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_internal\cli\progress_bars.py", line 53, in _rich_progress_bar
for chunk in iterable:
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_internal\network\utils.py", line 63, in response_chunks
for chunk in response.raw.stream(
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_vendor\urllib3\response.py", line 622, in stream
data = self.read(amt=amt, decode_content=decode_content)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_vendor\urllib3\response.py", line 560, in read
with self._error_catcher():
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\contextlib.py", line 155, in __exit__
self.gen.throw(value)
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\pip\_vendor\urllib3\response.py", line 443, in _error_catcher
raise ReadTimeoutError(self._pool, None, "Read timed out.")
pip._vendor.urllib3.exceptions.ReadTimeoutError: HTTPSConnectionPool(host='files.pythonhosted.org', port=443): Read timed out.

FishC · 发表于 2024-3-13 20:14:56

lxg1434334642 发表于 2024-03-13 20:14
ERROR: Exception:
Traceback (most recent call las ...

这个错误是由于在安装`python-docx`模块时，连接到Python Package Index（PyPI）的过程中发生了超时错误。由于网络环境不稳定或网络连接问题，导致无法从PyPI下载所需的模块文件。

您可以尝试使用以下方法来解决这个问题：

1. 首先，确保您的网络连接正常并且没有任何限制，可以使用浏览器访问https://pypi.org/，以确保能够正常访问。

2. 如果您使用的是代理服务器，请确保已正确配置代理设置。可以通过设置环境变量来配置代理，例如：

set http_proxy=http://your_proxy_server:port
set https_proxy=https://your_proxy_server:port

复制代码

将 "your_proxy_server" 替换为实际的代理服务器地址，将 "port" 替换为代理服务器端口号。

3. 另外，您可以尝试使用其他的Python包管理工具，例如Anaconda或Miniconda，来安装`python-docx`模块。您可以尝试使用以下命令在Anaconda环境中安装：

conda install -c conda-forge python-docx

复制代码

如果以上方法仍然无法解决问题，可以尝试使用离线安装包手动安装`python-docx`模块，您可以从https://www.lfd.uci.edu/~gohlke/pythonlibs/ 网站下载适用于您版本的Python和操作系统的离线安装包。

希望这些方法能够帮助您解决问题。如果还有其他疑问，请随时提问。

以上回复来自 FishC AI 小助理，如未能正确解答您的问题，请继续追问。

lxg1434334642 · 发表于 2024-3-13 20:24:29

raceback (most recent call last):
  File "C:/Users/Lenovo/Desktop/搜索.py", line 52, in <module>
main()
  File "C:/Users/Lenovo/Desktop/搜索.py", line 47, in main
ix = create_or_load_index(index_folder)
  File "C:/Users/Lenovo/Desktop/搜索.py", line 13, in create_or_load_index
ix = index.open_dir(index_folder)
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\whoosh\index.py", line 123, in open_dir
return FileIndex(storage, schema=schema, indexname=indexname)
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\whoosh\index.py", line 421, in __init__
TOC.read(self.storage, self.indexname, schema=self._schema)
  File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python312\Lib\site-packages\whoosh\index.py", line 618, in read
raise EmptyIndexError("Index %r does not exist in %r"
whoosh.index.EmptyIndexError: Index 'MAIN' does not exist in FileStorage('C:\\Users\\Lenovo\\Desktop\\新建文件夹')

FishC · 发表于 2024-3-13 20:24:52

lxg1434334642 发表于 2024-03-13 20:24
raceback (most recent call last):
File "C:/User ...

这个错误是由于索引文件夹中不存在名为"MAIN"的索引造成的。出现这个错误可能有以下几个原因：

1. 第一次运行程序时，尚未创建索引文件夹或索引文件夹被删除。
2. 您提供的索引文件夹路径不正确。

要解决这个问题，您可以尝试以下步骤：

1. 确保指定的索引文件夹存在，并且您有读写权限。
2. 如果程序是第一次运行，或者索引文件夹已被删除，请确保在运行程序之前执行`build_index`函数来创建索引。
3. 检查索引文件夹中是否存在名为"MAIN"的索引文件。如果没有，请确保在调用`create_or_load_index`函数之前执行`build_index`函数。

希望这些提示能够帮助您解决问题。

以上回复来自 FishC AI 小助理，如未能正确解答您的问题，请继续追问。

lxg1434334642 · 发表于 2024-3-13 20:29:38

为什么修改后的代码还是无法运行
import os
from whoosh import index, writing
from whoosh.fields import Schema, TEXT, ID
from whoosh.qparser import QueryParser
from docx import Document

# 创建或加载索引
def create_or_load_index(index_folder):
if not os.path.exists(index_folder):
      os.makedirs(index_folder)
      ix = index.create_in(index_folder, create_schema())
else:
      ix = index.open_dir(index_folder)
return ix

# 创建索引模式
def create_schema():
return Schema(file_path=ID(stored=True), file_content=TEXT(stored=True))

# 遍历文件夹建立索引
def build_index(ix, folder_path):
writer = ix.writer()
for foldername, _, filenames in os.walk(folder_path):
      for filename in filenames:
         file_path = os.path.join(foldername, filename)
         with open(file_path, 'r', encoding='utf-8') as file:
            content = file.read()
            writer.add_document(file_path=file_path, file_content=content)
writer.commit()

# 搜索文件
def search_files(ix, keywords):
with ix.searcher() as searcher:
      document = Document()
      for keyword in keywords:
         query = QueryParser("file_content", ix.schema).parse(keyword)
         results = searcher.search(query)
         for hit in results:
            document.add_paragraph(f"文件名: {os.path.basename(hit['file_path'])}, 位置: {hit['file_path']}")
      document.save(os.path.join(os.getcwd(), '搜索结果.docx'))

# 主程序
def main():
folder_path = r"C:\"
index_folder = r"C:\Users\Lenovo\Desktop\新建文件夹"
keywords = ['秘密', '机密', '绝  密']
ix = create_or_load_index(index_folder)
build_index(ix, folder_path)
search_files(ix, keywords)

if __name__ == "__main__":
main()[/code]

FishC · 发表于 2024-3-13 20:30:05

lxg1434334642 发表于 2024-03-13 20:29
为什么修改后的代码还是无法运行
import os
from wh ...

这段代码无法正常运行的原因是在`keywords`变量的赋值处缺少了一个列表，导致语法错误。您需要将`keywords =`修改为`keywords = []`来定义一个空列表。这样修改后的代码如下所示：import osfrom whoosh import index, writingfrom whoosh.fields import Schema, TEXT, IDfrom whoosh.qparser import QueryParserfrom docx import Document# 创建或加载索引def create_or_load_index(index_folder): if not os.path.exists(index_folder): os.makedirs(index_folder) ix = index.create_in(index_folder, create_schema()) else: ix = index.open_dir(index_folder) return ix# 创建索引模式def create_schema(): return Schema(file_path=ID(stored=True), file_content=TEXT(stored=True))# 遍历文件夹建立索引def build_index(ix, folder_path): writer = ix.writer() for foldername, _, filenames in os.walk(folder_path): for filename in filenames: file_path = os.path.join(foldername, filename) with open(file_path, 'r', encoding='utf-8') as file: content = file.read() writer.add_document(file_path=file_path, file_content=content) writer.commit()# 搜索文件def search_files(ix, keywords): with ix.searcher() as searcher: document = Document() for keyword in keywords: query = QueryParser("file_content", ix.schema).parse(keyword) results = searcher.search(query) for hit in results: document.add_paragraph(f"文件名: {os.path.basename(hit)}, 位置: {hit}") document.save(os.path.join(os.getcwd(), '搜索结果.docx'))# 主程序def main(): folder_path = r"C:\" index_folder = r"C:\Users\Lenovo\Desktop\新建文件夹" keywords = [] ix = create_or_load_index(index_folder) build_index(ix, folder_path) search_files(ix, keywords)if __name__ == "__main__": main()

以上回复来自 FishC AI 小助理，如未能正确解答您的问题，请继续追问。

lxg1434334642 · 发表于 2024-3-13 20:34:40

请问这个代码里面我需要填写什么？

folder_path = r"C:\Your\Folder\Path"

复制代码

FishC · 发表于 2024-3-13 20:35:18

lxg1434334642 发表于 2024-03-13 20:34
请问这个代码里面我需要填写什么？folder_path = r"C: ...

在这个代码中，您需要将`folder_path`变量的值设置为您希望搜索的文件夹路径。例如，如果您要搜索名为`MyFolder`的文件夹，该文件夹位于C盘的根目录下，您可以将`folder_path`设置为：

`folder_path = r"C:\MyFolder"`

请注意，在Windows系统中，文件夹路径使用反斜杠（\）作为路径分隔符。为了确保反斜杠被正确解释为路径分隔符，请在路径字符串前添加字母"r"，以表示它是一个原始字符串。

确保替换`C:\Your\Folder\Path`和`MyFolder`，以适应您具体的文件夹和文件路径。

以上回复来自 FishC AI 小助理，如未能正确解答您的问题，请继续追问。

lxg1434334642 · 发表于 2024-3-13 20:36:56

如果我想搜索电脑内所有文件应该怎么填写

FishC · 发表于 2024-3-13 20:37:16

lxg1434334642 发表于 2024-03-13 20:36
如果我想搜索电脑内所有文件应该怎么填写

要搜索电脑中的所有文件，您可以将`folder_path`变量的值设置为根目录的路径，例如：`folder_path = 'C:\\'`。这将使程序遍历整个C盘（或其他驱动器）来搜索文件。请注意，这可能会需要很长时间，并且搜索的范围非常广泛，可能会导致性能问题。因此，请谨慎使用此功能。

以上回复来自 FishC AI 小助理，如未能正确解答您的问题，请继续追问。

账号		自动登录	找回密码
密码			立即注册

为什么下面这段代码无法正常运行

马上注册，结交更多好友，享用更多功能^_^

本帖被以下淘专辑推荐:

浏览过的版块