增加参数控制是否使用ocr模式解析pdf

temp/scripts/parser.py

@@ -2,8 +2,17 @@
 """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 logging
 import os
 import sys
+import warnings
+
+# 抑制第三方库的进度条和日志，仅保留解析结果输出
+os.environ["HF_HUB_DISABLE_PROGRESS_BARS"] = "1"
+os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1"
+os.environ["TQDM_DISABLE"] = "1"
+warnings.filterwarnings("ignore")
+logging.disable(logging.WARNING)
 
 import common
 import docx_parser
@@ -27,6 +36,12 @@ def main() -> None:
         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）",
     )
 
+    parser.add_argument(
+        "--high-res",
+        action="store_true",
+        help="PDF 解析时启用 OCR 版面分析（需要额外依赖，处理较慢）",
+    )
+
     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"
@@ -88,12 +103,22 @@ def main() -> None:
             ("XML 原生解析", xlsx_parser.parse_xlsx_with_xml),
         ]
     else:
-        parsers = [
-            ("docling", pdf_parser.parse_pdf_with_docling),
-            ("unstructured", pdf_parser.parse_pdf_with_unstructured),
-            ("MarkItDown", pdf_parser.parse_pdf_with_markitdown),
-            ("pypdf", pdf_parser.parse_pdf_with_pypdf),
-        ]
+        if args.high_res:
+            parsers = [
+                ("docling OCR", pdf_parser.parse_pdf_with_docling_ocr),
+                ("unstructured OCR", pdf_parser.parse_pdf_with_unstructured_ocr),
+                ("docling", pdf_parser.parse_pdf_with_docling),
+                ("unstructured", pdf_parser.parse_pdf_with_unstructured),
+                ("MarkItDown", pdf_parser.parse_pdf_with_markitdown),
+                ("pypdf", pdf_parser.parse_pdf_with_pypdf),
+            ]
+        else:
+            parsers = [
+                ("docling", pdf_parser.parse_pdf_with_docling),
+                ("unstructured", pdf_parser.parse_pdf_with_unstructured),
+                ("MarkItDown", pdf_parser.parse_pdf_with_markitdown),
+                ("pypdf", pdf_parser.parse_pdf_with_pypdf),
+            ]
 
     failures = []
     content = None