ingest tool: flag for HTML quick mode (CDX-only)

2 files changed, 6 insertions, 1 deletions

diff --git a/python/ingest_file.py b/python/ingest_file.py
index 73e6a13..19938df 100755
--- a/python/ingest_file.py
+++ b/python/ingest_file.py
@@ -19,6 +19,7 @@ def run_single_ingest(args):
         request['force_recrawl'] = True
     ingester = IngestFileWorker(
         try_spn2=not args.no_spn2,
+        html_quick_mode=args.html_quick_mode,
     )
     result = ingester.process(request)
     print(json.dumps(result, sort_keys=True))
@@ -59,6 +60,9 @@ def main():
     sub_single.add_argument('--ingest-type',
         default="pdf",
         help="type of ingest (pdf, html, etc)")
+    sub_single.add_argument('--html-quick-mode',
+        action='store_true',
+        help="don't fetch individual sub-resources, just use CDX")
     sub_single.add_argument('url',
         help="URL of paper to fetch")
 
diff --git a/python/sandcrawler/ingest.py b/python/sandcrawler/ingest.py
index c9b3d2f..028f2b2 100644
--- a/python/sandcrawler/ingest.py
+++ b/python/sandcrawler/ingest.py
@@ -81,7 +81,7 @@ class IngestFileWorker(SandcrawlerWorker):
         self.try_existing_pdfextract = kwargs.get('try_existing_pdfextract', True)
         self.try_wayback = kwargs.get('try_wayback', True)
         self.try_spn2 = kwargs.get('try_spn2', True)
-        self.html_quick_mode = False
+        self.html_quick_mode = kwargs.get('html_quick_mode', False)
         self.adblock_rules = load_adblock_rules()
         self.max_html_resources = 200
 
@@ -374,6 +374,7 @@ class IngestFileWorker(SandcrawlerWorker):
 
         try:
             if self.html_quick_mode:
+                print("  WARN: running quick CDX-only fetches", file=sys.stderr)
                 full_resources = quick_fetch_html_resources(raw_resources, self.wayback_client.cdx_client, when)
             else:
                 full_resources = fetch_html_resources(raw_resources, self.wayback_client, when)