Edit vendor
Catalog automation
Catalog scraper
SCRIPTScript-driven · seed_data/scrape_trinity_special_event_rentals.py
Last run: May 26, 2026 · 12:22 PM · 234 new · 0 updated
💬 Refine via chat
💬 Re-scrape log
234 images still hot-linked to the vendor's CDN.
Localize to mirror bytes to disk + repoint
image_path — survives CDN rotation + lets
proposal / lookbook bundles ship the bytes to the portal.
History · 3 rounds
Feedback: Continue
Generated script-driven scraper at seed_data/scrape_trinity_special_event_rentals.py. The site is Weebly-based with two tiers: category pages (e.g. /chairs, /tables) listing all items inline as image+text pairs, plus some individual detail pages. The revised script scrapes all known category pages first — parsing image+name+price from adjacent heading/paragraph nodes — then falls back to individual sitemap product pages for anything not already seen, and deduplicates everything by name.
Feedback: <div class="nav desktop-nav"><ul class="wsite-menu-default"> <li id="active" class="wsite-menu-item-wrap wsite-nav-1 active" style="position: relative;"> <a href="/home.html" class="wsite-menu-item" style="position: relative;"> Home </a> </li> <li id="pg952097067102165377" class="wsite-menu-item-wrap wsite-nav-2" style="position: relative;"> <a href="/about-us.html" class="wsite-menu-item" style="position: relative;"> About Us </a> </li> <li id="pg212228198560131955" class="wsite-menu-item-wrap wsite-nav-3" style="position: relative;"> <a class="wsite-menu-item" style="position: relative;"> Our Selections </a> </li> <li id="pg687424907855613521" class="wsite-menu-item-wrap wsite-nav-4" style="position: relative;"> <a href="/gallery.html" class="wsite-menu-item" style="position: relative;"> Gallery </a> </li> <li id="pg549335246655190952" class="wsite-menu-item-wrap wsite-nav-5" style="position: relative;"> <a href="/inquire.html" class="wsite-menu-item" style="position: relative;"> Inquire </a> </li> </ul> </div> Here is the navbar where each rental catalogue category exists. Rental items are formatted like this <div class="wsite-image wsite-image-border-none " style="padding-top:10px;padding-bottom:10px;margin-left:0;margin-right:0;text-align:center"> <a> <img src="/uploads/1/4/3/2/143229321/published/cane-chair-natural-15-fixed.png?1776102046" alt="Picture" style="width:246;max-width:100%"> </a> <div style="display:block;font-size:90%"></div> </div>
Error: Claude stopped with unexpected reason: max_tokens
Generated script-driven scraper at seed_data/scrape_trinity_special_event_rentals.py. The site is Weebly-based with no grid catalog page — products are spread across individual detail pages listed in the sitemap. Each page needs to be fetched to extract the product name and image; prices appear to be quote-only. A config can't handle multi-URL scraping, so a custom script is needed.
AI tagging
6 pending6 items from this vendor need tagging (color / material / style — feeds the operator's color-scheme + filter search). Claude Haiku reads each image; cost scales linearly with item count.