cbsnews.com

CBSNews.com - News Headlines

The Reporter

We monitor the news headline from this website which we then use to train our sentiment analysis engine to detect for bad news about publicly traded companies

Harvested on

CSV JSON HTML Changes

news_headline	article_url	origin_pattern	origin_url	createdAt	updatedAt	pingedAt

Data source unique ID

n4793_cd2dea52066b64727ecd800c3db339ebeses

Privacy

Public

Last ran status

COMPLETED

Last ran

2025-10-31 00:00:00 UTC

Crawl Frequency

Six Hourly

Urls to Monitor

Use default URL in recipe

Sample code snippets to quickly import data set into your application

For more information on how to automatically trigger an import please reference our WebHook API guide

Integrating with Java

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.Arrays;

public class HelloWorld {
  public static void main(String[] args) {

    try {
      URL urlCSV = new URL(
        "https://cache.getdata.io/n4793_cd2dea52066b64727ecd800c3db339ebeses/latest_all.csv"
      );

      URLConnection urlConn = urlCSV.openConnection();
      InputStreamReader inputCSV = new InputStreamReader(
        ((URLConnection) urlConn).getInputStream()
      );
      BufferedReader br = new BufferedReader(inputCSV);

      String line;
      String[] fields;
      while ((line = br.readLine()) != null) {
        // Each row
        fields = line.split(",");
        System.out.println(Arrays.toString(fields));

      }
      // clean up buffered reader
      br.close();


    } catch (Exception e) {
      System.out.println(e.getMessage());
    }
  }   
}

Integrating with NodeJs

const csv     = require('csv-parser');
const https   = require('https');
const fs      = require('fs');

const file = fs.createWriteStream("temp_download.csv");
const request = https.get(
  "https://cache.getdata.io/n4793_cd2dea52066b64727ecd800c3db339ebeses/latest_all.csv", 
  function(response) {
    response.pipe(file);
  }
);

file.on('finish', function() {
  file.close();
  fs.createReadStream('temp_download.csv').pipe(csv()).on('data', (row) => {
    // Each row
    console.log(row);

  }).on('end', () => {
    console.log('CSV file successfully processed');

  });
});

Integrating with PHP

$data = file_get_contents("https://cache.getdata.io/n4793_cd2dea52066b64727ecd800c3db339ebeses/latest_all.csv");
$rows = explode("\n",$data);
$s = array();
foreach($rows as $row) {

  # Each row
  var_dump( $row);
  
}

Integrating with Python

import csv
import urllib2

url = 'https://cache.getdata.io/n4793_cd2dea52066b64727ecd800c3db339ebeses/latest_all.csv'
response = urllib2.urlopen(url)
cr = csv.reader(response)

for row in cr:
  # Each row
  print row

Integrating with Ruby

require 'open-uri'
require 'tempfile'
require 'csv'

temp_file = Tempfile.new( "getdata", :encoding => 'ascii-8bit')
temp_file << open("https://cache.getdata.io/n4793_cd2dea52066b64727ecd800c3db339ebeses/latest_all.csv").read
temp_file.rewind

CSV.foreach( open(uri), :headers => :first_row ).each do |row|      
  # Each row
  puts row
end