starmen1265/kb-skills
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(12-02): modify Pipeline for platform-specific processing flow

Browse Source 
- Add Bilibili video detection: platform=bilibili and content_type=video
- Skip analyze step for Bilibili videos, use srt step instead
- Skip srt step for non-Bilibili-video content
- Add SRTInput import and step input creation logic
- Update _populate_skipped_step_results for srt step
- Add output_file, paragraphs, tags, corrected to result fields

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
starmen1265
2026-03-19 23:43:39 +08:00
parent b312612e6c
commit 8d41a1b324
1 changed files with 46 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
kb_workflow/pipeline/pipeline.py
+46 -5
View File
@@ -21,7 +21,7 @@ from typing import Dict, List, Optional
from kb_workflow.pipeline.config import get_settings
from kb_workflow.pipeline.link_parser import LinkParser, ParsedLink
from kb_workflow.pipeline.processors.base import BaseProcessor
from kb_workflow.pipeline.schemas import PipelineConfig, PipelineInput, PipelineOutput
from kb_workflow.pipeline.schemas import PipelineConfig, PipelineInput, PipelineOutput, SRTInput
logger = logging.getLogger(__name__)
@@ -174,6 +174,20 @@ class Pipeline:
logger.info(f"Skipping ASR for text content type: {parsed.content_type}")
continue
# B站视频：跳过 analyze 步骤，使用 srt 步骤替代
is_bilibili_video = (
parsed.platform == "bilibili" and
parsed.content_type == "video"
)
if step_name == "analyze" and is_bilibili_video:
logger.info(f"Skipping analyze for Bilibili video, using SRT processor instead")
continue
# B站文章/知乎等：跳过 srt 步骤
if step_name == "srt" and not is_bilibili_video:
logger.info(f"Skipping SRT for non-Bilibili-video content: {parsed.platform}/{parsed.content_type}")
continue
processor = self.processors[step_name]
# Mark step as started
@@ -228,10 +242,26 @@ class Pipeline:
content_type=parsed.content_type,
output_file=str(content_dir / "analysis.md"),
)
elif step_name == "srt":
# SRT needs srt file from ASR step and metadata
download_result = results.get("download", {})
asr_result = results.get("asr", {})
metadata_file = download_result.get("metadata_file", "")
# SRT file from ASR output
srt_file = asr_result.get("output_files", {}).get("srt", "")
step_input = SRTInput(
content_id=parsed.content_id,
platform=parsed.platform,
srt_file=srt_file,
metadata_file=metadata_file,
output_file=str(content_dir / "analysis.md"),
content_type=parsed.content_type,
)
elif step_name == "archive":
# Archive needs analysis file from analyze step
analyze_result = results.get("analyze", {})
analysis_file = analyze_result.get("analysis_file", "")
# Archive needs analysis file from analyze step (or srt step for Bilibili video)
analyze_result = results.get("analyze", {}) or results.get("srt", {})
analysis_file = analyze_result.get("analysis_file", "") or analyze_result.get("output_file", "")
step_input = ArchiveInput(
content_id=parsed.content_id,
@@ -261,7 +291,7 @@ class Pipeline:
# Add output fields to results
for field_name in ["metadata_file", "content_file", "title", "author",
"analysis_file", "summary", "output_files",
"archive_file", "skipped"]:
"archive_file", "skipped", "output_file", "paragraphs", "tags", "corrected"]:
if hasattr(step_output, field_name):
results[step_name][field_name] = getattr(step_output, field_name)
@@ -397,3 +427,14 @@ class Pipeline:
"analysis_file": str(analysis_path),
}
logger.info(f"Found existing analysis: {analysis_path}")
elif step_name == "srt":
# Scan for SRT output (same file as analyze - analysis.md)
analysis_path = content_dir / "analysis.md"
if analysis_path.exists():
results["srt"] = {
"success": True,
"error_message": None,
"output_file": str(analysis_path),
}
logger.info(f"Found existing SRT output: {analysis_path}")