continue renaming extractor to plugin, add plan for hook concurrency, add chrome kill helper script

archivebox/plugins/parse_html_urls/on_Snapshot__60_parse_html_urls.py

@@ -28,7 +28,7 @@ from urllib.parse import urljoin, urlparse
 
 import rich_click as click
 
-EXTRACTOR_NAME = 'parse_html_urls'
+PLUGIN_NAME = 'parse_html_urls'
 
 # Check if parse_dom_outlinks extractor already ran
 DOM_OUTLINKS_URLS_FILE = Path('parse_dom_outlinks/urls.jsonl')
@@ -179,7 +179,7 @@ def main(url: str, snapshot_id: str = None, crawl_id: str = None, depth: int = 0
         record = {
             'type': 'Snapshot',
             'url': found_url,
-            'via_extractor': EXTRACTOR_NAME,
+            'plugin': PLUGIN_NAME,
             'depth': depth + 1,
         }
         if snapshot_id:

archivebox/plugins/parse_html_urls/tests/test_parse_html_urls.py

@@ -233,7 +233,7 @@ class TestParseHtmlUrls:
         entry = json.loads(output_file.read_text().strip())
         assert entry['url'] == 'https://example.com'
         assert 'type' in entry
-        assert 'via_extractor' in entry
+        assert 'plugin' in entry
 
 
 if __name__ == '__main__':