TK-10709: strip Crexi marketing-header prefix from detail addresses

963bc1dbb05437403c0fa8169409dddcb686602c · 2026-08-25 15:14:54 -0700 · Steve Abrams

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Files touched

M scripts/scrape-crexi-loopnet.js

Diff

commit 963bc1dbb05437403c0fa8169409dddcb686602c
Author: Steve Abrams <steve@designerwallcoverings.com>
Date:   Tue Aug 25 15:14:54 2026 -0700

    TK-10709: strip Crexi marketing-header prefix from detail addresses
    
    Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 scripts/scrape-crexi-loopnet.js | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/scripts/scrape-crexi-loopnet.js b/scripts/scrape-crexi-loopnet.js
index 150ef0b..2cd1867 100644
--- a/scripts/scrape-crexi-loopnet.js
+++ b/scripts/scrape-crexi-loopnet.js
@@ -145,7 +145,12 @@ function detailAgent(url) {
   const head = d.head || '';
   const flat = head.replace(/\n+/g, ' ');
   // authoritative address + headline price (both near the top → in head)
-  const address = cleanAddr((flat.match(/([0-9][^,\n]{2,60}?,\s*[A-Za-z .]+,\s*CA\s*\d{5})\s+For Sale/) || [])[1]);
+  let address = cleanAddr((flat.match(/([0-9][^,\n]{2,80}?,\s*[A-Za-z .]+,\s*CA\s*\d{5})\s+For Sale/) || [])[1]);
+  if (address) {
+    // Crexi sometimes prepends a "<type> | X% CAP | N Units " marketing header before the repeated
+    // street address — strip it so the stored address is just the street, city, CA, zip.
+    address = address.replace(/^.*?\b\d+\s+Units?\s+(?=\d)/i, '').replace(/^.*\|\s*/, '').replace(/\s{2,}/g, ' ').trim();
+  }
   let price = null;
   let m = flat.match(/\$([\d,]{5,})\s*\|\s*\d+\s+days?\s+on\s+market/i);       // "$6,500,000 | 169 days on market"
   if (!m) m = flat.match(/Listed by[^$]{0,80}?\$([\d,]{5,})(?!\s*\/)/i);       // "Listed by <firm> $6,500,000"

← f0860c1 TK-10709: robust Crexi agent-attributed scraper · back to Commercialrealestate · auto-data-snapshot: 2026-08-25T15:12:26 (2 data files) — dat b362871 →