Created
May 27, 2025 01:19
-
-
Save tbbooher/f773f74cfac3693f8e9979c2124ac63c to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python3 | |
| import json | |
| import time | |
| import requests | |
| from datetime import datetime | |
| # ——— CONFIG ——— | |
| cities = [ | |
| "dallas","austin","houston","sanantonio","denver","seattle", | |
| "sfbay","portland","boise","phoenix","chicago","boulder", | |
| "reno","saltlakecity","minneapolis","charlotte","atlanta", | |
| "losangeles","newyork","philadelphia" | |
| ] | |
| UA = ( | |
| "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) " | |
| "AppleWebKit/537.36 (KHTML, like Gecko) " | |
| "Chrome/113.0.0.0 Safari/537.36" | |
| ) | |
| OUTPUT_FILE = "raw_data.jsonl" | |
| def fetch_city(city): | |
| resp = requests.get( | |
| f"https://{city}.craigslist.org/search/bia", | |
| params={"has_image":1,"min_price":150,"query":"mountain bike","sort":"listing_date"}, | |
| headers={"User-Agent": UA}, | |
| timeout=10 | |
| ) | |
| resp.raise_for_status() | |
| return resp.text | |
| with open(OUTPUT_FILE, "a", encoding="utf-8") as out: | |
| for city in cities: | |
| print(f"[{city}] downloading…") | |
| html = fetch_city(city) | |
| # pull out the JSON-LD block | |
| start = html.find('id="ld_searchpage_results"') | |
| if start == -1: | |
| print(f" ⚠️ no JSON-LD for {city}") | |
| continue | |
| # assume the <script> content is valid JSON | |
| json_start = html.find("{", start) | |
| json_end = html.find("</script>", json_start) | |
| block = html[json_start:json_end].strip() | |
| try: | |
| data = json.loads(block) | |
| except json.JSONDecodeError as e: | |
| print(f" ❌ JSON parse error in {city}: {e}") | |
| continue | |
| # output number of records found | |
| records = data.get("itemListElement", []) | |
| print(f" ℹ️ found {len(records)} records in {city}") | |
| timestamp = datetime.utcnow().isoformat() | |
| for elt in records: | |
| rec = { | |
| "city": city, | |
| "scraped_at": timestamp, | |
| "item": elt.get("item", {}) | |
| } | |
| out.write(json.dumps(rec) + "\n") | |
| print(f" → wrote {len(records)} listings") | |
| time.sleep(2) | |
| print("Done downloading raw data.") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment