一些对提取数据有用的python代码片段

用于给llm喂提示词

# html去除不必要tag

用于减少token

```
from bs4 import BeautifulSoup

def remove_class_style(html_content):
    soup = BeautifulSoup(html_content, 'html.parser')
    
    # 遍历所有标签
    for tag in soup.find_all(True):
        # 保留href和src属性
        preserved_attrs = {}
        if 'href' in tag.attrs:
            preserved_attrs['href'] = tag.attrs['href']
        if 'src' in tag.attrs:
            preserved_attrs['src'] = tag.attrs['src']
        
        # 清空标签的所有属性
        tag.attrs = preserved_attrs
    
    return str(soup)

# 示例HTML内容
html_content = """
<html>
<head>
    <title>示例页面</title>
</head>
<body class="main-body" style="background-color: #f0f0f0;">
    <div class="content" style="color: red;">
        <p class="text" style="font-size: 14px;">这是一个示例段落。</p>
        <a href="#" class="link" style="text-decoration: none;">这是一个链接。</a>
    </div>
</body>
</html>
"""

# 调用函数移除class和style属性
clean_html = remove_class_style(html_content)
print(clean_html)
```

# html转markdown

```
from markdownify import markdownify as md

html = "<h1>Hello, World!</h1>"
markdown = md(html)
print(markdown)
```

# 提取项目路径-白名单版

```
import os
import re

# 定义不匹配的规则
exclude_dirs = [r'\.vscode', r'\.git', 'runtime', 'vendor']

# 定义白名单规则
include_files = [r'\.py$', r'\.txt$', r'\.md$']  # 你可以根据需要添加更多文件类型

def should_exclude(path, rules):
    return any(re.search(rule, path) for rule in rules)

def should_include(path, rules):
    return any(re.search(rule, path) for rule in rules)

def list_files_in_directory(directory, indent_level=0):
    try:
        items = os.listdir(directory)
    except PermissionError:
        print('|' + '-' * (indent_level * 2 + 1) + '[Permission Denied]')
        return

for item in sorted(items):
        item_path = os.path.join(directory, item)
        if should_exclude(item_path, exclude_dirs):
            continue
        if os.path.isdir(item_path):
            print('|' + '-' * (indent_level * 2 + 1) + item)
            list_files_in_directory(item_path, indent_level + 1)
        elif should_include(item_path, include_files):
            print('|' + '-' * (indent_level * 2 + 1) + item)

if __name__ == "__main__":
    list_files_in_directory("./")
```

# 提取项目路径-黑名单版

例子：

```
- res
  - adminui
    - dist
      - css
        - admin.css
        - login.css
      - modules
        - admin.js
        - index.js
        - view.js
    - src
      - css
        - admin.css
        - login.css
      - modules
        - admin.js
        - index.js
        - view.js
  - config.js
```

代码

```
import os
import re

# 定义不匹配的规则
exclude_dirs = [r'\.vscode', r'\.git']
exclude_files = [r'\.png$', r'\.jpg$', r'\.jpeg$', r'\.gif$', r'\.bmp$', r'\.pyc$']

def should_exclude(path, rules):
    return any(re.search(rule, path) for rule in rules)

def list_files_in_directory(directory, indent_level=0):
    try:
        items = os.listdir(directory)
    except PermissionError:
        print(' ' * indent_level * 2 + '- [Permission Denied]')
        return

for item in sorted(items):
        item_path = os.path.join(directory, item)
        if should_exclude(item_path, exclude_dirs):
            continue
        if os.path.isdir(item_path):
            print(' ' * indent_level * 2 + f'- {item}')
            list_files_in_directory(item_path, indent_level + 1)
        elif not should_exclude(item_path, exclude_files):
            print(' ' * indent_level * 2 + f'- {item}')

if __name__ == "__main__":
    directory = input("请输入要提取目录的根路径: ")
    print(f'- {directory}')
    list_files_in_directory(directory)
```

# 提取文件

```
import os

def extract_files_content(directory, root_dir=None, whitelist_extensions=None):
    # 检查目录是否存在
    if not os.path.exists(directory):
        print(f"路径 {directory} 不存在")
        return

# 获取根目录路径
    if root_dir is None:
        root_dir = directory

# 默认白名单为空
    if whitelist_extensions is None:
        whitelist_extensions = []
    # 遍历目录下的文件和子目录
    with open("1.txt", "a", encoding="utf-8") as f:
        for filename in os.listdir(directory):
            filepath = os.path.join(directory, filename)
            if os.path.isfile(filepath):
                print(filename)
                # 检查文件后缀是否在白名单中
                if any(filename.endswith(ext) for ext in whitelist_extensions):
                    # 写入相对于根目录的文件路径
                    relative_filepath = os.path.relpath(filepath, root_dir)
                    f.write(relative_filepath + '\n')
                    f.write("```\n")
                    # 读取文件内容并写入
                    with open(filepath, 'r', encoding='utf-8') as file:
                        content = file.read()
                        f.write(content + '\n')
                    f.write("```\n\n")
            elif os.path.isdir(filepath):
                # 递归处理子目录
                extract_files_content(filepath, root_dir, whitelist_extensions)

# 提取指定路径下所有文件名和内容
current_directory = "D:\\Code\\py\\docs"  # 修改路径为正确的路径
whitelist_extensions = ['.md']  # 设置白名单后缀
# 先清空
with open("1.txt", "w", encoding="utf-8") as f:
    f.write("")
extract_files_content(current_directory, whitelist_extensions=whitelist_extensions)
```

提取目录文件转为下划线，方便导入知识库

```
import os
import re

# 定义不匹配的规则
exclude_dirs = [r'\.vscode', r'\.git']
exclude_files = [r'\.png$', r'\.jpg$', r'\.jpeg$', r'\.gif$', r'\.bmp$', r'\.pyc$']

def should_exclude(path, rules):
    return any(re.search(rule, path) for rule in rules)

# 获取根目录路径
    if root_dir is None:
        root_dir = directory

# 默认白名单为空
    if whitelist_extensions is None:
        whitelist_extensions = []

# 遍历目录下的文件和子目录
    for filename in os.listdir(directory):
        filepath = os.path.join(directory, filename)
        if os.path.isfile(filepath):
            # 检查文件后缀是否在白名单中
            if any(filename.endswith(ext) for ext in whitelist_extensions):
                # 构建文件名格式：一级文件夹_可能的下一级文件夹_...._最终文件名字
                relative_filepath = os.path.relpath(filepath, root_dir)
                base_filename = os.path.basename(relative_filepath)
                structured_filename = '_'.join(relative_filepath.split(os.sep)[:-1] + [base_filename])
                # 写入文件内容
                with open("tmp/" + structured_filename, "w", encoding="utf-8") as f:
                    # 读取文件内容并写入
                    with open(filepath, 'r', encoding='utf-8') as file:
                        content = file.read()
                        f.write(content)
        elif os.path.isdir(filepath) and not should_exclude(filepath, exclude_dirs):
            # 递归处理子目录
            extract_files_content(filepath, root_dir, whitelist_extensions)

# 提取指定路径下所有文件名和内容
current_directory = "docs"  # 修改路径为正确的路径
whitelist_extensions = ['.md']  # 设置白名单后缀
extract_files_content(current_directory, whitelist_extensions=whitelist_extensions)

```

用于给llm喂提示词

# html去除不必要tag

用于减少token

```
from bs4 import BeautifulSoup

# 调用函数移除class和style属性
clean_html = remove_class_style(html_content)
print(clean_html)
```

# html转markdown

```
from markdownify import markdownify as md

html = "<h1>Hello, World!</h1>"
markdown = md(html)
print(markdown)
```

# 提取项目路径-白名单版

```
import os
import re

# 定义不匹配的规则
exclude_dirs = [r'\.vscode', r'\.git', 'runtime', 'vendor']

# 定义白名单规则
include_files = [r'\.py$', r'\.txt$', r'\.md$']  # 你可以根据需要添加更多文件类型

def should_exclude(path, rules):
    return any(re.search(rule, path) for rule in rules)

def should_include(path, rules):
    return any(re.search(rule, path) for rule in rules)

if __name__ == "__main__":
    list_files_in_directory("./")
```

# 提取项目路径-黑名单版

例子：

代码

```
import os
import re

# 定义不匹配的规则
exclude_dirs = [r'\.vscode', r'\.git']
exclude_files = [r'\.png$', r'\.jpg$', r'\.jpeg$', r'\.gif$', r'\.bmp$', r'\.pyc$']

def should_exclude(path, rules):
    return any(re.search(rule, path) for rule in rules)

if __name__ == "__main__":
    directory = input("请输入要提取目录的根路径: ")
    print(f'- {directory}')
    list_files_in_directory(directory)
```

# 提取文件

```
import os

# 获取根目录路径
    if root_dir is None:
        root_dir = directory

提取目录文件转为下划线，方便导入知识库

```
import os
import re

# 定义不匹配的规则
exclude_dirs = [r'\.vscode', r'\.git']
exclude_files = [r'\.png$', r'\.jpg$', r'\.jpeg$', r'\.gif$', r'\.bmp$', r'\.pyc$']

def should_exclude(path, rules):
    return any(re.search(rule, path) for rule in rules)

# 获取根目录路径
    if root_dir is None:
        root_dir = directory

# 默认白名单为空
    if whitelist_extensions is None:
        whitelist_extensions = []

```

Last modification：October 14, 2024

如果觉得我的文章对你有用，请随意赞赏

一些对提取数据有用的python代码片段

Leave a Comment Cancel reply
使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款

博客重新搭建

樱花动漫APP打包

Handsome主题配套友情链接修改默认网站图标为对应站ico

宝塔7.7专业，企业开心版

宝塔开心版教程

wsl安装miniconda，cuda

中山大学数据库实验SQL server2019环境配置

vscode sftp插件链接本地宝塔

二分查找模板

Crx搜搜：一键搜索下载谷歌Chrome浏览器插件

一些对提取数据有用的python代码片段

Leave a Comment Cancel reply 使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款

一些对提取数据有用的python代码片段

Leave a Comment Cancel reply
使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款