How to scrape B
altimore Sun
with AgentQL

Looking for a better way to scrape Baltimore Sun? Say goodbye to fragile XPath or DOM selectors that easily break with website updates. AI-powered AgentQL ensures consistent web scraping across various platforms, from Baltimore Sun to any other website, regardless of UI changes.

Not just for scraping Baltimore Sun

Smart selectors work anywhere

https://baltimoresun.com

URL

Input any webpage.

{
  headlines[]
  date
  author
  content
}

Query

Describe data in natural language.

{
  "headlines": [
    "Baltimore Orioles beat New York Yankees",
    "Ravens sign new linebacker"
  ],
  "date": "2024-04-27",
  "author": "John Smith",
  "content": "The Baltimore Orioles defeated the New York Yankees 6-3 on Saturday night at Camden Yards. The Ravens signed free agent linebacker Roquan Smith to a multiyear contract."
}

Returns

Receive accurate output in seconds.

How to use AgentQL on Baltimore Sun

A dotted lineA blue lineA blue line
1

Install the SDK

Install code for JS and Python

npm install agentql

pip3 install agentql

2

Test and refine

Use the query debugger

3

Run your script

Install code for both JS and Python

agentql init

python example.py

Get started

Holds no opinions on what’s and how’s. Build whatever makes sense to you.