自动同步: 2026-03-18 02:10

skills/kb_workflow/pipeline/processors/parse.py

@@ -0,0 +1,83 @@
+"""ParseProcessor - URL parsing processor
+
+Parses URLs from various platforms (Bilibili, Zhihu) and extracts
+platform, content type, and content ID information.
+"""
+
+from __future__ import annotations
+
+from typing import Optional, TYPE_CHECKING
+
+from kb_workflow.pipeline.config import get_settings
+from kb_workflow.pipeline.link_parser import LinkParser
+from kb_workflow.pipeline.schemas import ParseInput, ParseOutput
+from kb_workflow.pipeline.processors.base import BaseProcessor
+
+if TYPE_CHECKING:
+    from kb_workflow.pipeline.state import WorkflowStateManager
+
+
+class ParseProcessor(BaseProcessor):
+    """URL parsing processor.
+
+    Parses URLs from Bilibili and Zhihu platforms, extracting
+    platform, content type, and content ID.
+
+    Attributes:
+        STEP_NAME: "parse" - identifies this processor step
+    """
+
+    STEP_NAME = "parse"
+
+    async def process(self, input_data: ParseInput) -> ParseOutput:
+        """Parse the URL and extract platform information.
+
+        Args:
+            input_data: ParseInput with URL to parse
+
+        Returns:
+            ParseOutput with parsed information or error message
+        """
+        parser = LinkParser()
+        parsed = parser.parse(input_data.url)
+
+        if parsed is None:
+            # Unknown URL format
+            result = ParseOutput(
+                success=False,
+                error_message="Unsupported URL format",
+                platform="",
+                content_type="",
+                content_id="",
+                resolved_url="",
+                original_url=input_data.url
+            )
+
+            # Record failure state
+            if self.state_manager:
+                state = self.state_manager.load()
+                if state:
+                    state.mark_step_failed(self.STEP_NAME, result.error_message)
+                    self.state_manager.save(state)
+
+            return result
+
+        # Successful parse
+        result = ParseOutput(
+            success=True,
+            platform=parsed.platform,
+            content_type=parsed.content_type,
+            content_id=parsed.content_id,
+            resolved_url=parsed.resolved_url,
+            original_url=parsed.original_url
+        )
+
+        # Record success state
+        if self.state_manager:
+            state = self.state_manager.load()
+            if state:
+                summary = f"platform={parsed.platform}, type={parsed.content_type}, id={parsed.content_id}"
+                state.mark_step_completed(self.STEP_NAME, summary)
+                self.state_manager.save(state)
+
+        return result