lanyuanxiaoyao/Skill
1
0
Fork 0
Code Activity

增加unstructured处理策略

Browse Source
This commit is contained in:
兰缘小妖
2026-02-17 20:12:26 +08:00
parent 856700fbe0
commit c693e23888
7 changed files with 603 additions and 730 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
temp/scripts/pptx_parser.py
View File

@@ -7,6 +7,7 @@ import zipfile
from typing import Any, List, Optional, Tuple
from common import (
_unstructured_elements_to_markdown,
build_markdown_table,
flush_list_stack,
parse_with_docling,
@@ -19,6 +20,25 @@ def parse_pptx_with_docling(file_path: str) -> Tuple[Optional[str], Optional[str
return parse_with_docling(file_path)
def parse_pptx_with_unstructured(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 unstructured 库解析 PPTX 文件"""
try:
from unstructured.partition.pptx import partition_pptx
except ImportError:
return None, "unstructured 库未安装"
try:
elements = partition_pptx(
filename=file_path, infer_table_structure=True, include_metadata=True
)
content = _unstructured_elements_to_markdown(elements)
if not content.strip():
return None, "文档为空"
return content, None
except Exception as e:
return None, f"unstructured 解析失败: {str(e)}"
def parse_pptx_with_markitdown(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 MarkItDown 库解析 PPTX 文件"""
return parse_with_markitdown(file_path)
@@ -74,6 +94,8 @@ def parse_pptx_with_python_pptx(file_path: str) -> Tuple[Optional[str], Optional
except ImportError:
return None, "python-pptx 库未安装"
_A_NS = {"a": "http://schemas.openxmlformats.org/drawingml/2006/main"}
try:
prs = Presentation(file_path)
md_content = []
@@ -89,10 +111,7 @@ def parse_pptx_with_python_pptx(file_path: str) -> Tuple[Optional[str], Optional
if hasattr(shape, "has_table") and shape.has_table:
if list_stack:
md_content.append(
"\n" + "\n".join([x for x in list_stack if x]) + "\n"
)
list_stack.clear()
flush_list_stack(list_stack, md_content)
table_md = convert_table_to_md_pptx(shape.table)
md_content.append(table_md)
@@ -104,20 +123,8 @@ def parse_pptx_with_python_pptx(file_path: str) -> Tuple[Optional[str], Optional
if pPr is not None:
is_list = (
para.level > 0
or pPr.find(
".//a:buChar",
namespaces={
"a": "http://schemas.openxmlformats.org/drawingml/2006/main"
},
)
is not None
or pPr.find(
".//a:buAutoNum",
namespaces={
"a": "http://schemas.openxmlformats.org/drawingml/2006/main"
},
)
is not None
or pPr.find(".//a:buChar", namespaces=_A_NS) is not None
or pPr.find(".//a:buAutoNum", namespaces=_A_NS) is not None
)
if is_list:
@@ -128,16 +135,9 @@ def parse_pptx_with_python_pptx(file_path: str) -> Tuple[Optional[str], Optional
text = extract_formatted_text_pptx(para.runs)
if text:
pPr = para._element.pPr
is_ordered = (
pPr is not None
and pPr.find(
".//a:buAutoNum",
namespaces={
"a": "http://schemas.openxmlformats.org/drawingml/2006/main"
},
)
is not None
and pPr.find(".//a:buAutoNum", namespaces=_A_NS) is not None
)
marker = "1. " if is_ordered else "- "
indent = " " * level
@@ -149,20 +149,14 @@ def parse_pptx_with_python_pptx(file_path: str) -> Tuple[Optional[str], Optional
list_stack[i] = ""
else:
if list_stack:
md_content.append(
"\n"
+ "\n".join([x for x in list_stack if x])
+ "\n"
)
list_stack.clear()
flush_list_stack(list_stack, md_content)
text = extract_formatted_text_pptx(para.runs)
if text:
md_content.append(f"{text}\n")
if list_stack:
md_content.append("\n" + "\n".join([x for x in list_stack if x]) + "\n")
list_stack.clear()
flush_list_stack(list_stack, md_content)
md_content.append("---\n")