refactor: 优化解析器日志与API检查逻辑，简化异常处理

Author: begoniezhao

docreader/parser/chain_parser.py

@@ -6,6 +6,7 @@
 from docreader.utils import endecode
 
 logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
 
 
 class FirstParser(BaseParser):
@@ -16,16 +17,15 @@ def __init__(self, *args, **kwargs):
 
         self._parsers: List[BaseParser] = []
         for parser_cls in self._parser_cls:
-            try:
-                parser = parser_cls(*args, **kwargs)
-                self._parsers.append(parser)
-            except Exception as e:
-                logger.error(f"Failed to create parser {parser_cls.__name__}: {e}")
+            parser = parser_cls(*args, **kwargs)
+            self._parsers.append(parser)
 
     def parse_into_text(self, content: bytes) -> Document:
         for p in self._parsers:
+            logger.info(f"FirstParser: using parser {p.__class__.__name__}")
             document = p.parse_into_text(content)
             if document.is_valid():
+                logger.info(f"FirstParser: parser {p.__class__.__name__} succeeded")
                 return document
         return Document()
 
@@ -43,16 +43,14 @@ def __init__(self, *args, **kwargs):
 
         self._parsers: List[BaseParser] = []
         for parser_cls in self._parser_cls:
-            try:
-                parser = parser_cls(*args, **kwargs)
-                self._parsers.append(parser)
-            except Exception as e:
-                logger.error(f"Failed to create parser {parser_cls.__name__}: {e}")
+            parser = parser_cls(*args, **kwargs)
+            self._parsers.append(parser)
 
     def parse_into_text(self, content: bytes) -> Document:
         images: Dict[str, str] = {}
         document = Document()
         for p in self._parsers:
+            logger.info(f"PipelineParser: using parser {p.__class__.__name__}")
             document = p.parse_into_text(content)
             content = endecode.encode_bytes(document.content)
             images.update(document.images)

docreader/parser/mineru_parser.py

@@ -28,7 +28,6 @@ def __init__(
         self.image_helper = MarkdownImageUtil()
         self.base64_pattern = re.compile(r"data:image/(\w+);base64,(.*)")
         self.enable = self.ping()
-        assert self.ping(), "MinerU API is not reachable"
 
     def ping(self, timeout: int = 5) -> bool:
         try:
@@ -41,6 +40,10 @@ def ping(self, timeout: int = 5) -> bool:
             return False
 
     def parse_into_text(self, content: bytes) -> Document:
+        if not self.enable:
+            logger.debug("MinerU API is not enabled")
+            return Document()
+
         logger.info(f"Parsing scanned PDF via MinerU API (size: {len(content)} bytes)")
         md_content: str = ""
         images_b64: Dict[str, str] = {}