修复bug

2026-02-15 19:53:31 +08:00
parent b022ac736b
commit f30ea08805
6 changed files with 139 additions and 97 deletions
--- a/temp/scripts/pdf_parser.py
+++ b/temp/scripts/pdf_parser.py
@@ -0,0 +1,75 @@
+#!/usr/bin/env python3
+"""PDF 文件解析模块，提供三种解析方法。"""
+
+from typing import Optional, Tuple
+
+
+def parse_pdf_with_markitdown(file_path: str) -> Tuple[Optional[str], Optional[str]]:
+    """使用 MarkItDown 库解析 PDF 文件"""
+    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_pdf_with_unstructured(file_path: str) -> Tuple[Optional[str], Optional[str]]:
+    """使用 unstructured 库解析 PDF 文件"""
+    try:
+        from unstructured.partition.pdf import partition_pdf
+    except ImportError:
+        return None, "unstructured 库未安装"
+
+    try:
+        elements = partition_pdf(
+            filename=file_path,
+            strategy="fast",
+            infer_table_structure=True,
+            extract_images_in_pdf=False,
+        )
+
+        md_lines = []
+        for element in elements:
+            if hasattr(element, "text") and element.text and element.text.strip():
+                text = element.text.strip()
+                md_lines.append(text)
+                md_lines.append("")
+
+        content = "\n".join(md_lines).strip()
+        if not content:
+            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_pdf_with_pypdf(file_path: str) -> Tuple[Optional[str], Optional[str]]:
+    """使用 pypdf 库解析 PDF 文件"""
+    try:
+        from pypdf import PdfReader
+    except ImportError:
+        return None, "pypdf 库未安装"
+
+    try:
+        reader = PdfReader(file_path)
+        md_content = []
+
+        for page in reader.pages:
+            text = page.extract_text(extraction_mode="plain")
+            if text and text.strip():
+                md_content.append(text.strip())
+                md_content.append("")
+
+        content = "\n".join(md_content).strip()
+        if not content:
+            return None, "文档为空"
+        return content, None
+    except Exception as e:
+        return None, f"pypdf 解析失败: {str(e)}"