Python實(shí)現(xiàn)文件查詢關(guān)鍵字功能的示例詳解

更新時(shí)間：2026年02月12日 09:52:17 作者：豆本-豆豆奶

這篇文章主要為大家詳細(xì)介紹了Python實(shí)現(xiàn)文件查詢關(guān)鍵字功能,文中的示例詳解詳細(xì),具有一定的借鑒價(jià)值,感興趣的小伙伴可以跟隨小編一起學(xué)習(xí)一下

思路

主要思路就是通過(guò)打開(kāi)文件夾，獲取文件，一個(gè)個(gè)遍歷查找關(guān)鍵字，流程圖如下：

流程圖

怎么樣，思路非常簡(jiǎn)單，所以其實(shí)實(shí)現(xiàn)也不難。

本文將支持少部分文件類型，更多類型需要讀者自己實(shí)現(xiàn)：

txt
docx
csv
xlsx
pptx

讀取txt

安裝庫(kù)

pip install chardet

代碼

import chardet


def detect_encoding(file_path):
    raw_data = None
    with open(file_path, 'rb') as f:
        for line in f:
            raw_data = line
            break

        if raw_data is None:
            raw_data = f.read()
    result = chardet.detect(raw_data)
    return result['encoding']


def read_txt(file_path, keywords=''):
    is_in = False
    encoding = detect_encoding(file_path)
    with open(file_path, 'r', encoding=encoding) as f:
        for line in f:
            if line.find(keywords) != -1:
                is_in = True
                break

    return is_in

我們使用了 chardet 庫(kù)來(lái)判斷 txt 的編碼，以應(yīng)對(duì)不同編碼的讀取方式。

讀取docx

安裝庫(kù)

pip install python-docx

代碼

from docx import Document


def read_docx(file_path, keywords=''):
    doc = Document(file_path)
    is_in = False

    for para in doc.paragraphs:
        if para.text.find(keywords) != -1:
            is_in = True
            break

    return is_in

讀取csv

代碼

import csv


def read_csv(file_path, keywords=''):
    is_in = False

    encoding = detect_encoding(file_path)
    with open(file_path, mode='r', encoding=encoding) as f:
        reader = csv.reader(f)

        for row in reader:
            row_text = ''.join([str(v) for v in row])
            if row_text.find(keywords) != -1:
                is_in = True
                break

    return is_in

讀取xlsx

安裝庫(kù)

pip install openpyxl

代碼

from openpyxl import load_workbook


def read_xlsx(file_path, keywords=''):
    wb = load_workbook(file_path)
    sheet_names = wb.sheetnames

    is_in = False
    for sheet_name in sheet_names:
        sheet = wb[sheet_name]
        for row in sheet.iter_rows(values_only=True):
            row_text = ''.join([str(v) for v in row])
            if row_text.find(keywords) != -1:
                is_in = True
                break

    wb.close()

    return is_in

讀取pptx

安裝庫(kù)

pip install python-pptx

代碼

from pptx import Presentation


def read_ppt(ppt_file, keywords=''):
    prs = Presentation(ppt_file)
    is_in = False
    for slide in prs.slides:
        for shape in slide.shapes:
            if shape.has_text_frame:
                text_frame = shape.text_frame
                for paragraph in text_frame.paragraphs:
                    for run in paragraph.runs:
                        if run.text.find(keywords) != -1:
                            is_in = True
                            break

    return is_in

文件夾遞歸

為了防止文件夾嵌套導(dǎo)致的問(wèn)題，我們還有一個(gè)文件夾遞歸的操作。

代碼

from pathlib import Path


def list_files_recursive(directory):
    file_paths = []

    for path in Path(directory).rglob('*'):
        if path.is_file():
            file_paths.append(str(path))

    return file_paths

完整代碼

# -*- coding: utf-8 -*-
from pptx import Presentation
import chardet
from docx import Document
import csv
from openpyxl import load_workbook
from pathlib import Path


def detect_encoding(file_path):
    raw_data = None
    with open(file_path, 'rb') as f:
        for line in f:
            raw_data = line
            break

        if raw_data is None:
            raw_data = f.read()
    result = chardet.detect(raw_data)
    return result['encoding']


def read_txt(file_path, keywords=''):
    is_in = False
    encoding = detect_encoding(file_path)
    with open(file_path, 'r', encoding=encoding) as f:
        for line in f:
            if line.find(keywords) != -1:
                is_in = True
                break

    return is_in


def read_docx(file_path, keywords=''):
    doc = Document(file_path)
    is_in = False

    for para in doc.paragraphs:
        if para.text.find(keywords) != -1:
            is_in = True
            break

    return is_in


def read_csv(file_path, keywords=''):
    is_in = False

    encoding = detect_encoding(file_path)
    with open(file_path, mode='r', encoding=encoding) as f:
        reader = csv.reader(f)

        for row in reader:
            row_text = ''.join([str(v) for v in row])
            if row_text.find(keywords) != -1:
                is_in = True
                break

    return is_in


def read_xlsx(file_path, keywords=''):
    wb = load_workbook(file_path)
    sheet_names = wb.sheetnames

    is_in = False
    for sheet_name in sheet_names:
        sheet = wb[sheet_name]
        for row in sheet.iter_rows(values_only=True):
            row_text = ''.join([str(v) for v in row])
            if row_text.find(keywords) != -1:
                is_in = True
                break

    wb.close()

    return is_in


def read_ppt(ppt_file, keywords=''):
    prs = Presentation(ppt_file)
    is_in = False
    for slide in prs.slides:
        for shape in slide.shapes:
            if shape.has_text_frame:
                text_frame = shape.text_frame
                for paragraph in text_frame.paragraphs:
                    for run in paragraph.runs:
                        if run.text.find(keywords) != -1:
                            is_in = True
                            break

    return is_in


def list_files_recursive(directory):
    file_paths = []

    for path in Path(directory).rglob('*'):
        if path.is_file():
            file_paths.append(str(path))

    return file_paths


if __name__ == '__main__':
    keywords = '測(cè)試關(guān)鍵字'
    file_paths = list_files_recursive(r'測(cè)試文件夾')
    for file_path in file_paths:
        if file_path.endswith('.txt'):
            is_in = read_txt(file_path, keywords)
        elif file_path.endswith('.docx'):
            is_in = read_docx(file_path, keywords)
        elif file_path.endswith('.csv'):
            is_in = read_csv(file_path, keywords)
        elif file_path.endswith('.xlsx'):
            is_in = read_xlsx(file_path, keywords)
        elif file_path.endswith('.pptx'):
            is_in = read_ppt(file_path, keywords)

        if is_in:
            print(file_path)