import os import json import requests from bs4 import BeautifulSoup from urllib.parse import urlparse URL = "https://material-theme.com/docs/reference/associations/" DATA_FILE = "icons.json" def scrape_icons(): print(f"Connecting to {URL}...") response = requests.get(URL) soup = BeautifulSoup(response.text, 'html.parser') rows = soup.select("tbody tr") associations = [] print(f"Found {len(rows)} potential icons. Starting download...") for row in rows: cols = row.find_all("td") if len(cols) < 4: continue name = cols[0].get_text(strip=True) pattern = cols[1].find("code").get_text(strip=True) if cols[1].find("code") else cols[1].get_text(strip=True) img_tag = cols[3].find("img")["src"] associations.append({ "name": name, "pattern": pattern, "icon_path": img_tag }) print(f"Saved: {name}") with open(DATA_FILE, 'w', encoding='utf-8') as f: json.dump(associations, f, indent=4) print(f"\nFinished! Processed {len(associations)} icons.") print(f"Data saved to {DATA_FILE}") if __name__ == "__main__": scrape_icons()