feat: initialize market app with browsing, product, and scraping code
Some checks failed
Build and Deploy / build-and-deploy (push) Has been cancelled
Some checks failed
Build and Deploy / build-and-deploy (push) Has been cancelled
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
This commit is contained in:
17
scrape/product/extractors/title.py
Normal file
17
scrape/product/extractors/title.py
Normal file
@@ -0,0 +1,17 @@
|
||||
|
||||
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"}
|
||||
Reference in New Issue
Block a user