64 lines
2.4 KiB
Python
64 lines
2.4 KiB
Python
import os
|
||
import sys
|
||
|
||
|
||
def collect_code_files(output_file="code_collection.txt"):
|
||
# 定义代码文件扩展名
|
||
code_extensions = [
|
||
'.py', '.java', '.cpp', '.c', '.h', '.hpp', '.cs',
|
||
'.js', '.html', '.css', '.php', '.go', '.rb',
|
||
'.swift', '.kt', '.ts', '.sh', '.pl', '.r'
|
||
]
|
||
|
||
# 定义要排除的目录
|
||
excluded_dirs = [
|
||
'venv', 'env', '.venv', '.env', 'virtualenv',
|
||
'__pycache__', 'node_modules', '.git', '.idea',
|
||
'dist', 'build', 'target', 'bin'
|
||
]
|
||
|
||
# 计数器
|
||
file_count = 0
|
||
|
||
# 打开输出文件
|
||
with open(output_file, 'w', encoding='utf-8') as out_file:
|
||
# 遍历当前目录及所有子目录
|
||
for root, dirs, files in os.walk('.'):
|
||
# 从dirs中移除排除的目录，这会阻止os.walk进入这些目录
|
||
dirs[:] = [d for d in dirs if d not in excluded_dirs]
|
||
|
||
for file in files:
|
||
# 获取文件扩展名
|
||
_, ext = os.path.splitext(file)
|
||
|
||
# 检查是否为代码文件
|
||
if ext.lower() in code_extensions:
|
||
file_path = os.path.join(root, file)
|
||
file_count += 1
|
||
|
||
# 写入文件路径作为分隔
|
||
out_file.write(f"\n{'=' * 80}\n")
|
||
out_file.write(f"File: {file_path}\n")
|
||
out_file.write(f"{'=' * 80}\n\n")
|
||
|
||
# 尝试读取文件内容并写入
|
||
try:
|
||
with open(file_path, 'r', encoding='utf-8') as code_file:
|
||
out_file.write(code_file.read())
|
||
except UnicodeDecodeError:
|
||
# 尝试用不同的编码
|
||
try:
|
||
with open(file_path, 'r', encoding='latin-1') as code_file:
|
||
out_file.write(code_file.read())
|
||
except Exception as e:
|
||
out_file.write(f"无法读取文件内容: {str(e)}\n")
|
||
except Exception as e:
|
||
out_file.write(f"读取文件时出错: {str(e)}\n")
|
||
|
||
print(f"已成功收集 {file_count} 个代码文件到 {output_file}")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
# 如果提供了命令行参数，则使用它作为输出文件名
|
||
output_file = sys.argv[1] if len(sys.argv) > 1 else "code_collection.txt"
|
||
collect_code_files(output_file) |