552 lines
19 KiB
Python
552 lines
19 KiB
Python
#!/usr/bin/env python3
|
||
"""整合的 DOCX 解析器，按优先级尝试多种解析方法：
|
||
1. MarkItDown (微软官方库)
|
||
2. python-docx (成熟的 Python 库)
|
||
3. XML 原生解析 (备选方案)
|
||
|
||
代码风格要求：
|
||
- Python 3.6+ 兼容
|
||
- 遵循 PEP 8 规范
|
||
- 所有公共 API 函数添加类型提示
|
||
- 字符串优先内联使用，不提取为常量，除非被使用超过3次
|
||
- 其他被多次使用的对象根据具体情况可考虑被提取为常量（如正则表达式）
|
||
- 模块级和公共 API 函数保留文档字符串
|
||
- 内部辅助函数不添加文档字符串（函数名足够描述）
|
||
- 变量命名清晰，避免单字母变量名
|
||
"""
|
||
|
||
import argparse
|
||
import os
|
||
import re
|
||
import sys
|
||
import zipfile
|
||
import xml.etree.ElementTree as ET
|
||
from typing import List, Optional, Tuple
|
||
|
||
IMAGE_PATTERN = re.compile(r"!\[[^\]]*\]\([^)]+\)")
|
||
|
||
|
||
def normalize_markdown_whitespace(content: str) -> str:
|
||
lines = content.split("\n")
|
||
result = []
|
||
empty_count = 0
|
||
|
||
for line in lines:
|
||
stripped = line.strip()
|
||
if not stripped:
|
||
empty_count += 1
|
||
if empty_count == 1:
|
||
result.append(line)
|
||
else:
|
||
empty_count = 0
|
||
result.append(line)
|
||
|
||
return "\n".join(result)
|
||
|
||
|
||
def is_valid_docx(file_path: str) -> bool:
|
||
try:
|
||
with zipfile.ZipFile(file_path, "r") as zip_file:
|
||
required_files = ["[Content_Types].xml", "_rels/.rels", "word/document.xml"]
|
||
for required in required_files:
|
||
if required not in zip_file.namelist():
|
||
return False
|
||
return True
|
||
except (zipfile.BadZipFile, zipfile.LargeZipFile):
|
||
return False
|
||
|
||
|
||
def remove_markdown_images(markdown_text: str) -> str:
|
||
return IMAGE_PATTERN.sub("", markdown_text)
|
||
|
||
|
||
def extract_titles(markdown_text: str) -> List[str]:
|
||
"""提取 markdown 文本中的所有标题行（1-6级）"""
|
||
title_lines = []
|
||
for line in markdown_text.split("\n"):
|
||
stripped = line.lstrip()
|
||
if stripped.startswith("#"):
|
||
level = 0
|
||
for char in stripped:
|
||
if char == "#":
|
||
level += 1
|
||
else:
|
||
break
|
||
if 1 <= level <= 6:
|
||
title_lines.append(stripped)
|
||
return title_lines
|
||
|
||
|
||
def get_heading_level(line: str) -> int:
|
||
stripped = line.lstrip()
|
||
if not stripped.startswith("#"):
|
||
return 0
|
||
level = 0
|
||
for char in stripped:
|
||
if char == "#":
|
||
level += 1
|
||
else:
|
||
break
|
||
return level if 1 <= level <= 6 else 0
|
||
|
||
|
||
def extract_title_content(markdown_text: str, title_name: str) -> Optional[str]:
|
||
"""提取所有指定标题及其下级内容（每个包含上级标题）"""
|
||
lines = markdown_text.split("\n")
|
||
match_indices = []
|
||
|
||
for i, line in enumerate(lines):
|
||
level = get_heading_level(line)
|
||
if level > 0:
|
||
stripped = line.lstrip()
|
||
title_text = stripped[level:].strip()
|
||
if title_text == title_name:
|
||
match_indices.append(i)
|
||
|
||
if not match_indices:
|
||
return None
|
||
|
||
result_lines = []
|
||
for idx in match_indices:
|
||
target_level = get_heading_level(lines[idx])
|
||
|
||
parent_titles = []
|
||
current_level = target_level
|
||
for i in range(idx - 1, -1, -1):
|
||
line_level = get_heading_level(lines[i])
|
||
if line_level > 0 and line_level < current_level:
|
||
parent_titles.append(lines[i])
|
||
current_level = line_level
|
||
if current_level == 1:
|
||
break
|
||
|
||
parent_titles.reverse()
|
||
result_lines.extend(parent_titles)
|
||
|
||
result_lines.append(lines[idx])
|
||
for i in range(idx + 1, len(lines)):
|
||
line = lines[i]
|
||
line_level = get_heading_level(line)
|
||
if line_level == 0 or line_level > target_level:
|
||
result_lines.append(line)
|
||
else:
|
||
break
|
||
|
||
return "\n".join(result_lines)
|
||
|
||
|
||
def search_markdown(
|
||
content: str, pattern: str, context_lines: int = 0
|
||
) -> Optional[str]:
|
||
"""使用正则表达式搜索 markdown 文档，返回匹配结果及其上下文"""
|
||
try:
|
||
regex = re.compile(pattern)
|
||
except re.error:
|
||
return None
|
||
|
||
lines = content.split("\n")
|
||
|
||
non_empty_indices = []
|
||
non_empty_to_original = {}
|
||
for i, line in enumerate(lines):
|
||
if line.strip():
|
||
non_empty_indices.append(i)
|
||
non_empty_to_original[i] = len(non_empty_indices) - 1
|
||
|
||
matched_non_empty_indices = []
|
||
for orig_idx in non_empty_indices:
|
||
if regex.search(lines[orig_idx]):
|
||
matched_non_empty_indices.append(non_empty_to_original[orig_idx])
|
||
|
||
if not matched_non_empty_indices:
|
||
return None
|
||
|
||
merged_ranges = []
|
||
current_start = matched_non_empty_indices[0]
|
||
current_end = matched_non_empty_indices[0]
|
||
|
||
for idx in matched_non_empty_indices[1:]:
|
||
if idx - current_end <= context_lines * 2:
|
||
current_end = idx
|
||
else:
|
||
merged_ranges.append((current_start, current_end))
|
||
current_start = idx
|
||
current_end = idx
|
||
merged_ranges.append((current_start, current_end))
|
||
|
||
results = []
|
||
for start, end in merged_ranges:
|
||
actual_start = max(0, start - context_lines)
|
||
actual_end = min(len(non_empty_indices) - 1, end + context_lines)
|
||
|
||
start_line_idx = non_empty_indices[actual_start]
|
||
end_line_idx = non_empty_indices[actual_end]
|
||
|
||
selected_indices = set(non_empty_indices[actual_start : actual_end + 1])
|
||
result_lines = [
|
||
line
|
||
for i, line in enumerate(lines)
|
||
if start_line_idx <= i <= end_line_idx
|
||
and (line.strip() or i in selected_indices)
|
||
]
|
||
results.append("\n".join(result_lines))
|
||
|
||
return "\n---\n".join(results)
|
||
|
||
|
||
def parse_with_markitdown(file_path: str) -> Optional[Tuple[str, None]]:
|
||
try:
|
||
from markitdown import MarkItDown
|
||
|
||
md = MarkItDown()
|
||
result = md.convert(file_path)
|
||
if not result.text_content.strip():
|
||
return None, "文档为空"
|
||
return result.text_content, None
|
||
except ImportError:
|
||
return None, "MarkItDown 库未安装"
|
||
except Exception as e:
|
||
return None, f"MarkItDown 解析失败: {str(e)}"
|
||
|
||
|
||
def parse_with_python_docx(file_path: str) -> Optional[Tuple[str, None]]:
|
||
try:
|
||
from docx import Document
|
||
except ImportError:
|
||
return None, "python-docx 库未安装"
|
||
|
||
try:
|
||
doc = Document(file_path)
|
||
|
||
def get_heading_level(para) -> int:
|
||
if para.style and para.style.name:
|
||
style_name = para.style.name
|
||
if "Heading 1" in style_name or "Title" in style_name:
|
||
return 1
|
||
elif "Heading 2" in style_name:
|
||
return 2
|
||
elif "Heading 3" in style_name:
|
||
return 3
|
||
elif "Heading 4" in style_name:
|
||
return 4
|
||
elif "Heading 5" in style_name:
|
||
return 5
|
||
elif "Heading 6" in style_name:
|
||
return 6
|
||
return 0
|
||
|
||
def get_list_style(para) -> Optional[str]:
|
||
if not para.style or not para.style.name:
|
||
return None
|
||
style_name = para.style.name
|
||
if "List Bullet" in style_name or "Bullet" in style_name:
|
||
return "bullet"
|
||
elif "List Number" in style_name or "Number" in style_name:
|
||
return "number"
|
||
return None
|
||
|
||
def convert_runs_to_markdown(runs) -> str:
|
||
result = []
|
||
for run in runs:
|
||
text = run.text
|
||
if not text:
|
||
continue
|
||
if run.bold:
|
||
text = f"**{text}**"
|
||
if run.italic:
|
||
text = f"*{text}*"
|
||
if run.underline:
|
||
text = f"<u>{text}</u>"
|
||
result.append(text)
|
||
return "".join(result)
|
||
|
||
def convert_table_to_markdown(table) -> str:
|
||
md_lines = []
|
||
for i, row in enumerate(table.rows):
|
||
cells = []
|
||
for cell in row.cells:
|
||
cell_text = cell.text.strip().replace("\n", " ")
|
||
cells.append(cell_text)
|
||
if cells:
|
||
md_line = "| " + " | ".join(cells) + " |"
|
||
md_lines.append(md_line)
|
||
if i == 0:
|
||
sep_line = "| " + " | ".join(["---"] * len(cells)) + " |"
|
||
md_lines.append(sep_line)
|
||
return "\n".join(md_lines)
|
||
|
||
markdown_lines = []
|
||
|
||
for para in doc.paragraphs:
|
||
text = convert_runs_to_markdown(para.runs)
|
||
if not text.strip():
|
||
continue
|
||
heading_level = get_heading_level(para)
|
||
if heading_level > 0:
|
||
markdown_lines.append(f"{'#' * heading_level} {text}")
|
||
else:
|
||
list_style = get_list_style(para)
|
||
if list_style == "bullet":
|
||
markdown_lines.append(f"- {text}")
|
||
elif list_style == "number":
|
||
markdown_lines.append(f"1. {text}")
|
||
else:
|
||
markdown_lines.append(text)
|
||
markdown_lines.append("")
|
||
|
||
for table in doc.tables:
|
||
table_md = convert_table_to_markdown(table)
|
||
markdown_lines.append(table_md)
|
||
markdown_lines.append("")
|
||
|
||
content = "\n".join(markdown_lines)
|
||
if not content.strip():
|
||
return None, "文档为空"
|
||
return content, None
|
||
except Exception as e:
|
||
return None, f"python-docx 解析失败: {str(e)}"
|
||
|
||
|
||
def parse_with_xml(file_path: str) -> Optional[Tuple[str, None]]:
|
||
word_namespace = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
|
||
namespaces = {"w": word_namespace}
|
||
|
||
def safe_open_zip(zip_file: zipfile.ZipFile, name: str):
|
||
if name.startswith("..") or "/" not in name:
|
||
return None
|
||
return zip_file.open(name)
|
||
|
||
def get_heading_level(style_id: Optional[str], style_to_level: dict) -> int:
|
||
return style_to_level.get(style_id, 0)
|
||
|
||
def get_list_style(style_id: Optional[str], style_to_list: dict) -> Optional[str]:
|
||
return style_to_list.get(style_id, None)
|
||
|
||
def extract_text_with_formatting(para, namespaces: dict) -> str:
|
||
texts = []
|
||
for run in para.findall(".//w:r", namespaces=namespaces):
|
||
text_elem = run.find(".//w:t", namespaces=namespaces)
|
||
if text_elem is not None and text_elem.text:
|
||
text = text_elem.text
|
||
bold = run.find(".//w:b", namespaces=namespaces) is not None
|
||
italic = run.find(".//w:i", namespaces=namespaces) is not None
|
||
if bold:
|
||
text = f"**{text}**"
|
||
if italic:
|
||
text = f"*{text}*"
|
||
texts.append(text)
|
||
return "".join(texts).strip()
|
||
|
||
def convert_table_to_markdown(table_elem, namespaces: dict) -> str:
|
||
rows = table_elem.findall(".//w:tr", namespaces=namespaces)
|
||
if not rows:
|
||
return ""
|
||
md_lines = []
|
||
for i, row in enumerate(rows):
|
||
cells = row.findall(".//w:tc", namespaces=namespaces)
|
||
cell_texts = []
|
||
for cell in cells:
|
||
cell_text = extract_text_with_formatting(cell, namespaces)
|
||
cell_text = cell_text.replace("\n", " ").strip()
|
||
cell_texts.append(cell_text if cell_text else "")
|
||
if cell_texts:
|
||
md_line = "| " + " | ".join(cell_texts) + " |"
|
||
md_lines.append(md_line)
|
||
if i == 0:
|
||
sep_line = "| " + " | ".join(["---"] * len(cell_texts)) + " |"
|
||
md_lines.append(sep_line)
|
||
return "\n".join(md_lines)
|
||
|
||
try:
|
||
style_to_level = {}
|
||
style_to_list = {}
|
||
markdown_lines = []
|
||
|
||
with zipfile.ZipFile(file_path) as zip_file:
|
||
try:
|
||
styles_file = safe_open_zip(zip_file, "word/styles.xml")
|
||
if styles_file:
|
||
styles_root = ET.parse(styles_file)
|
||
for style in styles_root.findall(
|
||
".//w:style", namespaces=namespaces
|
||
):
|
||
style_id = style.get(f"{{{word_namespace}}}styleId")
|
||
style_name_elem = style.find("w:name", namespaces=namespaces)
|
||
if style_id and style_name_elem is not None:
|
||
style_name = style_name_elem.get(f"{{{word_namespace}}}val")
|
||
if style_name:
|
||
if style_name == "Title":
|
||
style_to_level[style_id] = 1
|
||
elif style_name == "heading 1":
|
||
style_to_level[style_id] = 1
|
||
elif style_name == "heading 2":
|
||
style_to_level[style_id] = 2
|
||
elif style_name == "heading 3":
|
||
style_to_level[style_id] = 3
|
||
elif style_name == "heading 4":
|
||
style_to_level[style_id] = 4
|
||
elif style_name == "heading 5":
|
||
style_to_level[style_id] = 5
|
||
elif style_name == "heading 6":
|
||
style_to_level[style_id] = 6
|
||
elif (
|
||
"List Bullet" in style_name
|
||
or "Bullet" in style_name
|
||
):
|
||
style_to_list[style_id] = "bullet"
|
||
elif (
|
||
"List Number" in style_name
|
||
or "Number" in style_name
|
||
):
|
||
style_to_list[style_id] = "number"
|
||
except Exception:
|
||
pass
|
||
|
||
document_file = safe_open_zip(zip_file, "word/document.xml")
|
||
if not document_file:
|
||
return None, "document.xml 不存在或无法访问"
|
||
|
||
root = ET.parse(document_file)
|
||
body = root.find(".//w:body", namespaces=namespaces)
|
||
if body is None:
|
||
return None, "document.xml 中未找到 w:body 元素"
|
||
|
||
for child in body.findall("./*", namespaces=namespaces):
|
||
if child.tag.endswith("}p"):
|
||
style_elem = child.find(".//w:pStyle", namespaces=namespaces)
|
||
style_id = (
|
||
style_elem.get(f"{{{word_namespace}}}val")
|
||
if style_elem is not None
|
||
else None
|
||
)
|
||
|
||
heading_level = get_heading_level(style_id, style_to_level)
|
||
list_style = get_list_style(style_id, style_to_list)
|
||
para_text = extract_text_with_formatting(child, namespaces)
|
||
|
||
if para_text:
|
||
if heading_level > 0:
|
||
markdown_lines.append(f"{'#' * heading_level} {para_text}")
|
||
elif list_style == "bullet":
|
||
markdown_lines.append(f"- {para_text}")
|
||
elif list_style == "number":
|
||
markdown_lines.append(f"1. {para_text}")
|
||
else:
|
||
markdown_lines.append(para_text)
|
||
markdown_lines.append("")
|
||
|
||
elif child.tag.endswith("}tbl"):
|
||
table_md = convert_table_to_markdown(child, namespaces)
|
||
if table_md:
|
||
markdown_lines.append(table_md)
|
||
markdown_lines.append("")
|
||
|
||
content = "\n".join(markdown_lines)
|
||
if not content.strip():
|
||
return None, "文档为空"
|
||
return content, None
|
||
except Exception as e:
|
||
return None, f"XML 解析失败: {str(e)}"
|
||
|
||
|
||
def main() -> None:
|
||
parser = argparse.ArgumentParser(description="将 DOCX 文件解析为 Markdown")
|
||
|
||
parser.add_argument("file_path", help="DOCX 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)
|
||
|
||
if not args.file_path.lower().endswith(".docx"):
|
||
print(f"警告: 文件扩展名不是 .docx: {args.file_path}")
|
||
|
||
if not is_valid_docx(args.file_path):
|
||
print(f"错误: 文件不是有效的 DOCX 格式或已损坏: {args.file_path}")
|
||
sys.exit(1)
|
||
|
||
parsers = [
|
||
("MarkItDown", parse_with_markitdown),
|
||
("python-docx", parse_with_python_docx),
|
||
("XML 原生解析", parse_with_xml),
|
||
]
|
||
|
||
failures = []
|
||
content = None
|
||
|
||
for parser_name, parser_func in parsers:
|
||
content, error = parser_func(args.file_path)
|
||
if content is not None:
|
||
content = remove_markdown_images(content)
|
||
content = 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 = extract_titles(content)
|
||
for title in titles:
|
||
print(title)
|
||
elif args.title_content:
|
||
title_content = 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 = 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()
|