134 lines
4.2 KiB
Python
134 lines
4.2 KiB
Python
#!/usr/bin/env python3
|
||
"""文档解析器命令行交互模块，提供命令行接口。支持 DOCX、PPTX、XLSX 和 PDF 文件。"""
|
||
|
||
import argparse
|
||
import os
|
||
import sys
|
||
|
||
import common
|
||
import docx_parser
|
||
import pdf_parser
|
||
import pptx_parser
|
||
import xlsx_parser
|
||
|
||
|
||
def main() -> None:
|
||
parser = argparse.ArgumentParser(
|
||
description="将 DOCX、PPTX、XLSX 或 PDF 文件解析为 Markdown"
|
||
)
|
||
|
||
parser.add_argument("file_path", help="DOCX、PPTX、XLSX 或 PDF 文件的绝对路径")
|
||
|
||
parser.add_argument(
|
||
"-n",
|
||
"--context",
|
||
type=int,
|
||
default=2,
|
||
help="与 -s 配合使用，指定每个检索结果包含的前后行数（不包含空行）",
|
||
)
|
||
|
||
group = parser.add_mutually_exclusive_group()
|
||
group.add_argument(
|
||
"-c", "--count", action="store_true", help="返回解析后的 markdown 文档的总字数"
|
||
)
|
||
group.add_argument(
|
||
"-l", "--lines", action="store_true", help="返回解析后的 markdown 文档的总行数"
|
||
)
|
||
group.add_argument(
|
||
"-t",
|
||
"--titles",
|
||
action="store_true",
|
||
help="返回解析后的 markdown 文档的标题行（1-6级）",
|
||
)
|
||
group.add_argument(
|
||
"-tc",
|
||
"--title-content",
|
||
help="指定标题名称，输出该标题及其下级内容（不包含#号）",
|
||
)
|
||
group.add_argument(
|
||
"-s",
|
||
"--search",
|
||
help="使用正则表达式搜索文档，返回所有匹配结果（用---分隔）",
|
||
)
|
||
|
||
args = parser.parse_args()
|
||
|
||
if not os.path.exists(args.file_path):
|
||
print(f"错误: 文件不存在: {args.file_path}")
|
||
sys.exit(1)
|
||
|
||
file_type = common.detect_file_type(args.file_path)
|
||
if not file_type:
|
||
print(f"错误: 不是有效的 DOCX、PPTX、XLSX 或 PDF 格式: {args.file_path}")
|
||
sys.exit(1)
|
||
|
||
if file_type == "docx":
|
||
parsers = [
|
||
("MarkItDown", docx_parser.parse_docx_with_markitdown),
|
||
("python-docx", docx_parser.parse_docx_with_python_docx),
|
||
("XML 原生解析", docx_parser.parse_docx_with_xml),
|
||
]
|
||
elif file_type == "pptx":
|
||
parsers = [
|
||
("MarkItDown", pptx_parser.parse_pptx_with_markitdown),
|
||
("python-pptx", pptx_parser.parse_pptx_with_python_pptx),
|
||
("XML 原生解析", pptx_parser.parse_pptx_with_xml),
|
||
]
|
||
elif file_type == "xlsx":
|
||
parsers = [
|
||
("MarkItDown", xlsx_parser.parse_xlsx_with_markitdown),
|
||
("pandas", xlsx_parser.parse_xlsx_with_pandas),
|
||
("XML 原生解析", xlsx_parser.parse_xlsx_with_xml),
|
||
]
|
||
else:
|
||
parsers = [
|
||
("MarkItDown", pdf_parser.parse_pdf_with_markitdown),
|
||
("unstructured", pdf_parser.parse_pdf_with_unstructured),
|
||
("pypdf", pdf_parser.parse_pdf_with_pypdf),
|
||
]
|
||
|
||
failures = []
|
||
content = None
|
||
|
||
for parser_name, parser_func in parsers:
|
||
content, error = parser_func(args.file_path)
|
||
if content is not None:
|
||
content = common.remove_markdown_images(content)
|
||
content = common.normalize_markdown_whitespace(content)
|
||
break
|
||
else:
|
||
failures.append(f"- {parser_name}: {error}")
|
||
|
||
if content is None:
|
||
print("所有解析方法均失败:")
|
||
for failure in failures:
|
||
print(failure)
|
||
sys.exit(1)
|
||
|
||
if args.count:
|
||
print(len(content.replace("\n", "")))
|
||
elif args.lines:
|
||
print(len(content.split("\n")))
|
||
elif args.titles:
|
||
titles = common.extract_titles(content)
|
||
for title in titles:
|
||
print(title)
|
||
elif args.title_content:
|
||
title_content = common.extract_title_content(content, args.title_content)
|
||
if title_content is None:
|
||
print(f"错误: 未找到标题 '{args.title_content}'")
|
||
sys.exit(1)
|
||
print(title_content, end="")
|
||
elif args.search:
|
||
search_result = common.search_markdown(content, args.search, args.context)
|
||
if search_result is None:
|
||
print(f"错误: 正则表达式无效或未找到匹配: '{args.search}'")
|
||
sys.exit(1)
|
||
print(search_result, end="")
|
||
else:
|
||
print(content, end="")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|