Craigslist Listings Scraper

E-commerce & Marketplaces

Operated by Sourcelane✓ verified

A web-scraping connector that extracts Craigslist classified listings across cities and categories (cars & trucks, housing, jobs, gigs, services, for sale, free items, etc.) using keyword and filter-based search or by scraping specific listing URLs; it returns per-listing records with identifiers and metadata (headline and permalink), numeric price and currency, site/city and category metadata, timestamps, textual location and map coordinates, full listing description as clean text, structured attribute sets for vehicles/housing/jobs (e.g., odometer, VIN, year/make/model; bedrooms, bathrooms, square footage, availability dates; compensation, employment type), photo URLs and image counts, and reply/availability status. The connector supports filters including keyword search, price ranges, posted-today and has-photo, sorting by relevance/newest/price, option for lightweight search-only results or full-detail scraping that opens each listing to parse attributes, and a mode to process lists of explicit listing URLs.

Verified Sep 28, 12:10 AM

$0.0015

per listing

Up to 100 per call. Only pay for results returned; failed calls are refunded.

What people use it for

Used car and vehicle market research (track prices by make/model, mileage and condition)
Rental and real-estate monitoring (find apartments under budget with bedroom, square-footage and availability data)
Lead generation for dealers, movers, property managers and service businesses (identify private sellers and landlords posting now)
Price intelligence for resellers (scan for underpriced furniture, electronics, bikes and tools)
Job market and gig research (collect job titles, compensation and employment types across cities)
results building and archiving (collect classified listings, photos and locations for analysis or machine-learning)

Trust & reliability

7d uptime trend

Window	Uptime	Success rate	p50	p95
24h	—	—	—	—
7d	—	—	—	—
30d	—	—	—	—

Calling contract

Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.

Call it via Sourcelane

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"craigslist-listings-scraper","params":{"city":"sfbay","maxItems":5},"maxResults":10}'

Request params

Field	Type	Required	Description
`mode`	string	optional	Search: browse a Craigslist city + category with optional keyword and filters. URLs: paste listing links and get their full details.
`city`	string	optional	Craigslist site name - the subdomain in the URL, e.g. 'sfbay', 'newyork', 'losangeles', 'chicago', 'toronto', 'london'. A full Craigslist URL is accepted too. Required in Search mode.
`category`	string	optional	The Craigslist section to search. For any other category use the 'Custom category code' field below, which overrides this choice.
`categoryCode`	string	optional	Any Craigslist category code as it appears in a search URL, e.g. 'cto' (cars by owner), 'boo' (boats), 'pta' (auto parts), 'sof' (software jobs), 'vga' (video gaming). Overrides the Category dropdown when set.
`query`	string	optional	Search terms, exactly as you would type them into the Craigslist search box. Leave empty to list everything in the category.
`minPrice`	integer	optional	Only return listings priced at or above this amount (in the city's local currency).
`maxPrice`	integer	optional	Only return listings priced at or below this amount (in the city's local currency).
`postedToday`	boolean	optional	Only return listings posted within the last 24 hours.
`hasImage`	boolean	optional	Only return listings that include at least one photo.
`sort`	string	optional	Order in which results are returned; matters when Max items cuts the list short.
`maxItems`	integer	optional	Maximum number of listings to return in Search mode. 0 = every matching listing (up to the site's 10,000-result limit). Capped at 100 per call.
`fetchDetails`	boolean	optional	Open every listing page to capture the full description, attributes, all photo URLs, address and posting dates. Turn off for a faster, cheaper title/price/location-only crawl.
`urls`	array	optional	Craigslist listing links to scrape in URLs mode, one per line. Both classic (https://sfbay.craigslist.org/sby/cto/d/slug/1234567890.html) and new (https://www.craigslist.org/view/d/slug/key) link formats work.

Each result contains

Field	Type	Description
`listingId`	string	Listing Id
`url`	string	Url
`title`	string	Title
`price`	null	Price
`currency`	null	Currency
`city`	string	City
`category`	string	Category
`categoryCode`	string	Category Code
`postedAt`	string	Posted At
`updatedAt`	null	Updated At
`location`	string	Location
`latitude`	number	Latitude
`longitude`	number	—
`body`	string	—
`attributes`	object	—
`imageUrls`	array	—
`imageCount`	integer	—
`hasImage`	boolean	—
`replyAvailable`	boolean	—
`query`	null	—

Use Craigslist Listings Scraper from Claude, ChatGPT or Cursor

Pick your tool and connect in under a minute. Then just ask — for example: “Track the price of these 20 grocery items at Woolworths and Coles every week.”

Connect Claude

Web, desktop and mobile. Paste one URL.

1Copy your personal connector URL
2In Claude open Settings → Connectors → Add custom connector
3Paste the URL and click Add — done

Manual setup (config files, REST, Python) +

Claude Code

Adds the Sourcelane MCP server with your key as a header.

terminal

claude mcp add --transport http sourcelane https://cool-puffin-608.convex.site/mcp \
  --header "Authorization: Bearer sl_live_your_agent_key"

Claude Desktop (config file)

Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.

claude_desktop_config.json

{
  "mcpServers": {
    "sourcelane": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://cool-puffin-608.convex.site/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

Cursor & Windsurf

Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).

mcp.json

{
  "mcpServers": {
    "sourcelane": {
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

VS Code

Save as .vscode/mcp.json. VS Code prompts for your key once.

.vscode/mcp.json

{
  "servers": {
    "sourcelane": {
      "type": "http",
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer ${input:sourcelane-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "sourcelane-key",
      "description": "Sourcelane agent key",
      "password": true
    }
  ]
}

ChatGPT Custom GPT (Actions)

Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.

OpenAPI schema URL

https://sourcelane-amber.vercel.app/openapi.json

REST

One POST. Pass maxResults to cap cost.

curl

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"craigslist-listings-scraper","params":{"city":"sfbay","maxItems":5},"maxResults":10}'

Python, LangChain, CrewAI, OpenAI Agents SDK…

Wrap the REST call as a tool, or point an MCP client at the endpoint.

python

import requests

res = requests.post(
    "https://cool-puffin-608.convex.site/v1/call",
    headers={"Authorization": "Bearer sl_live_your_agent_key"},
    json={
        "listing": "craigslist-listings-scraper",
        "params": {"city":"sfbay","maxItems":5},
        "maxResults": 10,
    },
    timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])

Reviews

—

0 reviews

Leave a review

Loading reviews…