From a04468041cd81ad90aa76ec15788a5ffacb6eec2 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Wed, 28 Sep 2022 18:06:48 -0700
Subject: persist: skip huge URLs

and fix some minor doc typos
---
 python/sandcrawler/persist.py | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'python/sandcrawler')

diff --git a/python/sandcrawler/persist.py b/python/sandcrawler/persist.py
index d753380..f682572 100644
--- a/python/sandcrawler/persist.py
+++ b/python/sandcrawler/persist.py
@@ -101,6 +101,10 @@ class PersistIngestFileResultWorker(SandcrawlerWorker):
         if raw["ingest_type"] not in ("pdf", "xml", "html"):
             self.counts["skip-ingest-type"] += 1
             return None
+        # limit on base_url length
+        if len(raw["base_url"]) > 1500:
+            self.counts["skip-url-too-long"] += 1
+            return None
         request = {
             "ingest_type": raw["ingest_type"],
             "base_url": raw["base_url"],
-- 
cgit v1.2.3