This repository has been archived on 2026-02-24. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
market/scrape/product/extractors/title.py
giles 6271a715a1
Some checks failed
Build and Deploy / build-and-deploy (push) Has been cancelled
feat: initialize market app with browsing, product, and scraping code
Split from coop monolith. Includes:
- Market/browse/product blueprints
- Product sync API
- Suma scraping pipeline
- Templates for market, browse, and product views
- Dockerfile and CI workflow for independent deployment
2026-02-09 23:16:34 +00:00

18 lines
570 B
Python

from __future__ import annotations
from typing import Dict
from bs4 import BeautifulSoup
from utils import normalize_text
from ..registry import extractor
@extractor
def ex_title(soup: BeautifulSoup, url: str) -> Dict:
title = None
for sel in ["h1.page-title span", "h1.page-title", "h1.product-name", "meta[property='og:title']"]:
el = soup.select_one(sel)
if el:
title = normalize_text(el.get_text()) if el.name != "meta" else el.get("content")
if title:
break
return {"title": title or "Product"}