How to scrape Google News

# Fetch a Google News page with the Ujeebu Scrape API.
# Settings from our health checks (Ujeebu site guide). Prints the start of the page HTML.
# Uses the official SDK ujeebu-python 0.1.5: pip install ujeebu-python==0.1.5
# Run: UJEEBU_API_KEY=your_key python3 google_news_page_sdk.py

import json
import os
import sys
import time

import requests
from ujeebu_python import UjeebuClient

API_KEY = os.environ.get("UJEEBU_API_KEY")
URLS = [
    "https://news.google.com/",
]
SETTINGS = {
    "js": True,
    "proxy_type": "premium",
}


def scrape(client, url):
    try:
        response = client.scrape(url, params=SETTINGS)
    except requests.RequestException as error:
        sys.exit(f"Request failed for {url}: {error}")
    if response.status_code != 200:
        try:
            message = response.json().get("message", response.text)
        except ValueError:
            message = response.text
        sys.exit(f"HTTP {response.status_code} for {url}: {str(message)[:300]}")
    print(f"Ujb-Credits: {response.headers.get('Ujb-Credits')}", file=sys.stderr)
    return response.text


if not API_KEY:
    sys.exit("Set the UJEEBU_API_KEY environment variable.")

client = UjeebuClient(api_key=API_KEY)

for i, url in enumerate(URLS):
    if i:
        time.sleep(2)  # be polite: one page at a time
    html = scrape(client, url)
    print(len(html), "bytes")
    print(html[:500])

// Fetch a Google News page with the Ujeebu Scrape API.
// Settings from our health checks (Ujeebu site guide). Prints the start of the page HTML.
// Uses the official SDK @ujeebu-org/ujeebu-sdk 0.1.2: npm install @ujeebu-org/ujeebu-sdk@0.1.2
// Run: UJEEBU_API_KEY=your_key node google_news_page_sdk.mjs

import { UjeebuClient } from '@ujeebu-org/ujeebu-sdk';

const API_KEY = process.env.UJEEBU_API_KEY;
const URLS = [
  "https://news.google.com/",
];
const SETTINGS = {
  js: true,
  proxy_type: "premium",
};

async function scrape(client, url) {
  let res;
  try {
    res = await client.scrape(url, SETTINGS);
  } catch (err) {
    const status = err.response?.status ?? 'error';
    const message = err.response?.data?.message ?? err.message;
    console.error(`HTTP ${status} for ${url}: ${String(message).slice(0, 300)}`);
    process.exit(1);
  }
  console.error(`Ujb-Credits: ${res.headers['ujb-credits']}`);
  return String(res.data);
}

if (!API_KEY) {
  console.error('Set the UJEEBU_API_KEY environment variable.');
  process.exit(1);
}

const client = new UjeebuClient(API_KEY);
const pause = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

for (const [i, url] of URLS.entries()) {
  if (i) await pause(2000); // be polite: one page at a time
  const html = await scrape(client, url);
  console.log(html.length, 'bytes');
  console.log(html.slice(0, 500));
}

# Fetch a Google News page with the Ujeebu Scrape API.
# Settings from our health checks (Ujeebu site guide). Prints the start of the page HTML.
# Run: UJEEBU_API_KEY=your_key python3 google_news_page.py   (pip install requests)

import json
import os
import sys
import time

import requests

API_URL = "https://api.ujeebu.com/scrape"
API_KEY = os.environ.get("UJEEBU_API_KEY")
URLS = [
    "https://news.google.com/",
]
SETTINGS = {
    "js": True,
    "proxy_type": "premium",
}


def scrape(url):
    response = requests.post(
        API_URL,
        headers={"ApiKey": API_KEY},
        json={"url": url, **SETTINGS},
        timeout=180,
    )
    if response.status_code != 200:
        try:
            message = response.json().get("message", response.text)
        except ValueError:
            message = response.text
        sys.exit(f"HTTP {response.status_code} for {url}: {str(message)[:300]}")
    print(f"Ujb-Credits: {response.headers.get('Ujb-Credits')}", file=sys.stderr)
    return response.text


if not API_KEY:
    sys.exit("Set the UJEEBU_API_KEY environment variable.")

for i, url in enumerate(URLS):
    if i:
        time.sleep(2)  # be polite: one page at a time
    html = scrape(url)
    print(len(html), "bytes")
    print(html[:500])

// Fetch a Google News page with the Ujeebu Scrape API.
// Settings from our health checks (Ujeebu site guide). Prints the start of the page HTML.
// Run: UJEEBU_API_KEY=your_key node google_news_page.mjs   (Node.js 18 or later)

const API_URL = 'https://api.ujeebu.com/scrape';
const API_KEY = process.env.UJEEBU_API_KEY;
const URLS = [
  "https://news.google.com/",
];
const SETTINGS = {
  js: true,
  proxy_type: "premium",
};

async function scrape(url) {
  const res = await fetch(API_URL, {
    method: 'POST',
    headers: { ApiKey: API_KEY, 'Content-Type': 'application/json' },
    body: JSON.stringify({ url, ...SETTINGS }),
    signal: AbortSignal.timeout(180000),
  });
  const text = await res.text();
  if (res.status !== 200) {
    let message = text;
    try {
      message = JSON.parse(text).message ?? text;
    } catch {}
    console.error(`HTTP ${res.status} for ${url}: ${String(message).slice(0, 300)}`);
    process.exit(1);
  }
  console.error(`Ujb-Credits: ${res.headers.get('ujb-credits')}`);
  return text;
}

if (!API_KEY) {
  console.error('Set the UJEEBU_API_KEY environment variable.');
  process.exit(1);
}

const pause = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

for (const [i, url] of URLS.entries()) {
  if (i) await pause(2000); // be polite: one page at a time
  const html = await scrape(url);
  console.log(html.length, 'bytes');
  console.log(html.slice(0, 500));
}

#!/usr/bin/env bash
# Fetch a Google News page with the Ujeebu Scrape API.
# Settings from our health checks (Ujeebu site guide). Prints the start of the page HTML.
# Run: UJEEBU_API_KEY=your_key bash google_news_page.sh   (curl 7.76 or later)
set -euo pipefail

curl -sS --fail-with-body --max-time 180 -D headers.txt \
  -X POST 'https://api.ujeebu.com/scrape' \
  -H "ApiKey: ${UJEEBU_API_KEY:?Set the UJEEBU_API_KEY environment variable.}" \
  -H 'Content-Type: application/json' \
  -o page.html --data-binary @- <<'JSON'
{
  "url": "https://news.google.com/",
  "js": true,
  "proxy_type": "premium"
}
JSON
head -c 500 page.html
echo
grep -i '^ujb-credits' headers.txt >&2

<?php
// Fetch a Google News page with the Ujeebu Scrape API.
// Settings from our health checks (Ujeebu site guide). Prints the start of the page HTML.
// Run: UJEEBU_API_KEY=your_key php google_news_page.php   (PHP 7.4 or later with curl)

$apiKey = getenv('UJEEBU_API_KEY') ?: exit("Set the UJEEBU_API_KEY environment variable.\n");
$urls = [
    'https://news.google.com/',
];
$settings = [
    'js' => true,
    'proxy_type' => 'premium',
];

function scrape(string $url, string $apiKey, array $settings)
{
    $ch = curl_init('https://api.ujeebu.com/scrape');
    $headers = [];
    curl_setopt_array($ch, [
        CURLOPT_POST => true,
        CURLOPT_RETURNTRANSFER => true,
        CURLOPT_TIMEOUT => 180,
        CURLOPT_HTTPHEADER => ['ApiKey: ' . $apiKey, 'Content-Type: application/json'],
        CURLOPT_POSTFIELDS => json_encode(['url' => $url] + $settings),
        CURLOPT_HEADERFUNCTION => function ($ch, $line) use (&$headers) {
            if (strpos($line, ':') !== false) {
                [$k, $v] = explode(':', $line, 2);
                $headers[strtolower(trim($k))] = trim($v);
            }
            return strlen($line);
        },
    ]);
    $body = curl_exec($ch);
    if ($body === false) {
        fwrite(STDERR, 'Request failed: ' . curl_error($ch) . "\n");
        exit(1);
    }
    $status = curl_getinfo($ch, CURLINFO_RESPONSE_CODE);
    if ($status !== 200) {
        $message = json_decode($body, true)['message'] ?? $body;
        fwrite(STDERR, "HTTP $status for $url: " . substr((string) $message, 0, 300) . "\n");
        exit(1);
    }
    fwrite(STDERR, 'Ujb-Credits: ' . ($headers['ujb-credits'] ?? '?') . "\n");
    return $body;
}

foreach ($urls as $i => $url) {
    if ($i > 0) {
        sleep(2); // be polite: one page at a time
    }
    $html = scrape($url, $apiKey, $settings);
    echo strlen($html), " bytes\n", substr($html, 0, 500), "\n";
}

// Fetch a Google News page with the Ujeebu Scrape API.
// Settings from our health checks (Ujeebu site guide). Prints the start of the page HTML.
// Uses the official SDK github.com/ujeebu/ujeebu-go v0.1.8: go mod init scraper && go get github.com/ujeebu/ujeebu-go@v0.1.8
// Run: UJEEBU_API_KEY=your_key go run google_news_page.go

package main

import (
	"errors"
	"fmt"
	"os"
	"time"

	ujeebu "github.com/ujeebu/ujeebu-go"
)

var urls = []string{
	"https://news.google.com/",
}

func fail(format string, args ...any) {
	fmt.Fprintf(os.Stderr, format+"\n", args...)
	os.Exit(1)
}

func short(s string) string {
	if len(s) > 300 {
		return s[:300]
	}
	return s
}

func params(target string) ujeebu.ScrapeParams {
	p := ujeebu.ScrapeParams{URL: target}
	p.JS = true
	p.ProxyType = "premium"
	return p
}

func scrape(client *ujeebu.Client, target string) string {
	// the int is the credits the request cost (the Ujb-Credits header), not an HTTP status
	resp, credits, err := client.Scrape(params(target))
	if err != nil {
		var apiErr *ujeebu.APIError
		if errors.As(err, &apiErr) {
			fail("HTTP %d for %s: %s", apiErr.StatusCode, target, short(apiErr.Message))
		}
		fail("Request failed for %s: %v", target, err)
	}
	fmt.Fprintf(os.Stderr, "Ujb-Credits: %d\n", credits)
	return resp.HTML
}

func main() {
	apiKey := os.Getenv("UJEEBU_API_KEY")
	if apiKey == "" {
		fail("Set the UJEEBU_API_KEY environment variable.")
	}
	client, err := ujeebu.NewClient(apiKey, ujeebu.WithTimeout(180*time.Second))
	if err != nil {
		fail("%v", err)
	}

	for i, target := range urls {
		if i > 0 {
			time.Sleep(2 * time.Second) // be polite: one page at a time
		}
		html := scrape(client, target)
		fmt.Println(len(html), "bytes")
		fmt.Println(html[:min(len(html), 500)])
	}
}