mirror of
https://github.com/ArchiveBox/ArchiveBox.git
synced 2026-04-06 07:47:53 +10:00
Remove extractor field from Crawl model and fix tests
- Remove extractor field from Crawl model (moved to config dict) - Update migration 0002_drop_seed_model to not add extractor - Update archivebox_add.py to use config['PARSER'] instead - Update admin.py recrawl to not pass extractor - Update jsonl.py serialization to not include extractor - Update test schema SCHEMA_0_8 to not include extractor - Set default timeout to 60s for test commands
This commit is contained in:
@@ -206,7 +206,6 @@ def crawl_to_jsonl(crawl) -> Dict[str, Any]:
|
||||
'type': TYPE_CRAWL,
|
||||
'id': str(crawl.id),
|
||||
'urls': crawl.urls,
|
||||
'extractor': crawl.extractor,
|
||||
'status': crawl.status,
|
||||
'max_depth': crawl.max_depth,
|
||||
'created_at': crawl.created_at.isoformat() if crawl.created_at else None,
|
||||
|
||||
Reference in New Issue
Block a user