How to scrape TechCrunch

# Scrape TechCrunch search and listing pages with the Ujeebu Scrape API.
# Calls the recipe techcrunch: the API applies its extract rules and validated settings (validated 2026-11-02). Send extract_rules or any setting to override them.
# Uses the official SDK ujeebu-python 0.1.5: pip install ujeebu-python==0.1.5
# Run: UJEEBU_API_KEY=your_key python3 techcrunch_listing_sdk.py

import json
import os
import sys
import time
from urllib.parse import parse_qsl, urlencode, urlsplit, urlunsplit

import requests
from ujeebu_python import UjeebuClient

API_KEY = os.environ.get("UJEEBU_API_KEY")
START_URL = "https://techcrunch.com/category/artificial-intelligence/"
PAGES = 3
RECIPE = "techcrunch"  # rules and settings come from the recipe; add your own to override them


def page_url(page):
    if page == 1:
        return START_URL
    return "https://techcrunch.com/category/artificial-intelligence/page/{page}/".replace("{page}", str(page))


def scrape(client, url):
    # a GET with recipe=: the API applies the recipe and answers {"result": {...}}
    try:
        response = client.scrape(url, params={"recipe": RECIPE})
    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')}, Ujb-Recipe: {response.headers.get('Ujb-Recipe')}", file=sys.stderr)
    return response.json()["result"]


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

client = UjeebuClient(api_key=API_KEY)

for page in range(1, PAGES + 1):
    result = scrape(client, page_url(page))
    print(json.dumps(result, indent=2, ensure_ascii=False))
    if not result.get("articles"):
        break
    time.sleep(2)  # be polite: one page at a time

// Scrape TechCrunch search and listing pages with the Ujeebu Scrape API.
// Calls the recipe techcrunch: the API applies its extract rules and validated settings (validated 2026-11-02). Send extract_rules or any setting to override them.
// 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 techcrunch_listing_sdk.mjs

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

const API_KEY = process.env.UJEEBU_API_KEY;
const START_URL = "https://techcrunch.com/category/artificial-intelligence/";
const PAGES = 3;
const RECIPE = "techcrunch"; // rules and settings come from the recipe; add your own to override them

function pageUrl(page) {
  if (page === 1) return START_URL;
  return "https://techcrunch.com/category/artificial-intelligence/page/{page}/".replace('{page}', String(page));
}

async function scrape(client, url) {
  let res;
  try {
    // a GET with recipe=: the API applies the recipe and answers { result: {...} }
    res = await client.scrape(url, { recipe: RECIPE });
  } 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']}, Ujb-Recipe: ${res.headers['ujb-recipe']}`);
  return res.data.result;
}

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 (let page = 1; page <= PAGES; page++) {
  const result = await scrape(client, pageUrl(page));
  console.log(JSON.stringify(result, null, 2));
  if (!result?.articles?.length) break;
  await pause(2000); // be polite: one page at a time
}

# Scrape TechCrunch search and listing pages with the Ujeebu Scrape API.
# Calls the recipe techcrunch: the API applies its extract rules and validated settings (validated 2026-11-02). Send extract_rules or any setting to override them.
# Run: UJEEBU_API_KEY=your_key python3 techcrunch_listing.py   (pip install requests)

import json
import os
import sys
import time
from urllib.parse import parse_qsl, urlencode, urlsplit, urlunsplit

import requests

API_URL = "https://api.ujeebu.com/scrape"
API_KEY = os.environ.get("UJEEBU_API_KEY")
START_URL = "https://techcrunch.com/category/artificial-intelligence/"
PAGES = 3
RECIPE = "techcrunch"  # rules and settings come from the recipe; add your own to override them


def page_url(page):
    if page == 1:
        return START_URL
    return "https://techcrunch.com/category/artificial-intelligence/page/{page}/".replace("{page}", str(page))


def scrape(url):
    response = requests.get(
        API_URL,
        headers={"ApiKey": API_KEY},
        params={"url": url, "recipe": RECIPE},
        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')}, Ujb-Recipe: {response.headers.get('Ujb-Recipe')}", file=sys.stderr)
    return response.json()["result"]


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

for page in range(1, PAGES + 1):
    result = scrape(page_url(page))
    print(json.dumps(result, indent=2, ensure_ascii=False))
    if not result.get("articles"):
        break
    time.sleep(2)  # be polite: one page at a time

// Scrape TechCrunch search and listing pages with the Ujeebu Scrape API.
// Calls the recipe techcrunch: the API applies its extract rules and validated settings (validated 2026-11-02). Send extract_rules or any setting to override them.
// Run: UJEEBU_API_KEY=your_key node techcrunch_listing.mjs   (Node.js 18 or later)

const API_URL = 'https://api.ujeebu.com/scrape';
const API_KEY = process.env.UJEEBU_API_KEY;
const START_URL = "https://techcrunch.com/category/artificial-intelligence/";
const PAGES = 3;
const RECIPE = "techcrunch"; // rules and settings come from the recipe; add your own to override them

function pageUrl(page) {
  if (page === 1) return START_URL;
  return "https://techcrunch.com/category/artificial-intelligence/page/{page}/".replace('{page}', String(page));
}

async function scrape(url) {
  const params = new URLSearchParams({ url, recipe: RECIPE });
  const res = await fetch(`${API_URL}?${params}`, {
    headers: { ApiKey: API_KEY },
    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')}, Ujb-Recipe: ${res.headers.get('ujb-recipe')}`);
  return JSON.parse(text).result;
}

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 (let page = 1; page <= PAGES; page++) {
  const result = await scrape(pageUrl(page));
  console.log(JSON.stringify(result, null, 2));
  if (!result?.articles?.length) break;
  await pause(2000); // be polite: one page at a time
}

#!/usr/bin/env bash
# Scrape TechCrunch search and listing pages with the Ujeebu Scrape API.
# Calls the recipe techcrunch: the API applies its extract rules and validated settings (validated 2026-11-02). Send extract_rules or any setting to override them.
# Run: UJEEBU_API_KEY=your_key bash techcrunch_listing.sh   (curl 7.76 or later)
set -euo pipefail

curl -sS --fail-with-body --max-time 180 -D headers.txt -G 'https://api.ujeebu.com/scrape' \
  -H "ApiKey: ${UJEEBU_API_KEY:?Set the UJEEBU_API_KEY environment variable.}" \
  --data-urlencode 'url=https://techcrunch.com/category/artificial-intelligence/' \
  --data-urlencode 'recipe=techcrunch'
echo
grep -i -E '^ujb-(credits|recipe)' headers.txt >&2

<?php
// Scrape TechCrunch search and listing pages with the Ujeebu Scrape API.
// Calls the recipe techcrunch: the API applies its extract rules and validated settings (validated 2026-11-02). Send extract_rules or any setting to override them.
// Run: UJEEBU_API_KEY=your_key php techcrunch_listing.php   (PHP 7.4 or later with curl)

$apiKey = getenv('UJEEBU_API_KEY') ?: exit("Set the UJEEBU_API_KEY environment variable.\n");
$startUrl = 'https://techcrunch.com/category/artificial-intelligence/';
$pages = 3;
$recipe = 'techcrunch'; // rules and settings come from the recipe; add your own to override them

function scrape(string $url, string $apiKey, string $recipe)
{
    $ch = curl_init('https://api.ujeebu.com/scrape?' . http_build_query(['url' => $url, 'recipe' => $recipe]));
    $headers = [];
    curl_setopt_array($ch, [
        CURLOPT_RETURNTRANSFER => true,
        CURLOPT_TIMEOUT => 180,
        CURLOPT_HTTPHEADER => ['ApiKey: ' . $apiKey],
        CURLOPT_HEADERFUNCTION => function ($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'] ?? '?') . ', Ujb-Recipe: ' . ($headers['ujb-recipe'] ?? '?') . "\n");
    return json_decode($body, true)['result'];
}

for ($page = 1; $page <= $pages; $page++) {
    $url = $page === 1 ? $startUrl : str_replace('{page}', (string) $page, 'https://techcrunch.com/category/artificial-intelligence/page/{page}/');
    $result = scrape($url, $apiKey, $recipe);
    echo json_encode($result, JSON_PRETTY_PRINT | JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE), "\n";
    if (empty($result['articles'])) {
        break;
    }
    sleep(2); // be polite: one page at a time
}

// Scrape TechCrunch search and listing pages with the Ujeebu Scrape API.
// Sends the extract rules and settings of the recipe techcrunch itself: the Go SDK v0.1.8 has no recipe field and always sends js, which would override the recipe.
// 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 techcrunch_listing.go

package main

import (
	"encoding/json"
	"errors"
	"fmt"
	"os"
	"strconv"
	"strings"
	"time"

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

const startURL = "https://techcrunch.com/category/artificial-intelligence/"

const pages = 3

// The extract rules of the recipe, as the JSON the API takes.
const extractRulesJSON = `{
    "articles": {
        "selector": "li.wp-block-post.post",
        "type": "obj",
        "multiple": true,
        "children": {
            "url": {
                "selector": "a.loop-card__title-link",
                "type": "link"
            },
            "title": {
                "selector": "h3",
                "type": "text"
            },
            "image": {
                "selector": ".loop-card__figure img",
                "type": "image"
            },
            "section": {
                "selector": ".loop-card__cat",
                "type": "text"
            },
            "published": {
                "selector": ".loop-card__time",
                "type": "attr",
                "attribute": "datetime"
            }
        }
    }
}`

var extractRules map[string]any

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.ExtractRules = extractRules
	return p
}

func pageURL(page int) string {
	if page == 1 {
		return startURL
	}
	return strings.ReplaceAll("https://techcrunch.com/category/artificial-intelligence/page/{page}/", "{page}", strconv.Itoa(page))
}

func scrape(client *ujeebu.Client, target string) map[string]any {
	// 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)
	result, _ := resp.Result.(map[string]any)
	return result
}

func printJSON(v any) {
	enc := json.NewEncoder(os.Stdout)
	enc.SetEscapeHTML(false)
	enc.SetIndent("", "  ")
	if err := enc.Encode(v); err != nil {
		fail("Cannot print the result: %v", err)
	}
}

func main() {
	apiKey := os.Getenv("UJEEBU_API_KEY")
	if apiKey == "" {
		fail("Set the UJEEBU_API_KEY environment variable.")
	}
	if err := json.Unmarshal([]byte(extractRulesJSON), &extractRules); err != nil {
		fail("Bad extract rules: %v", err)
	}
	client, err := ujeebu.NewClient(apiKey, ujeebu.WithTimeout(180*time.Second))
	if err != nil {
		fail("%v", err)
	}

	for page := 1; page <= pages; page++ {
		result := scrape(client, pageURL(page))
		printJSON(result)
		items, _ := result["articles"].([]any)
		if len(items) == 0 {
			break
		}
		time.Sleep(2 * time.Second) // be polite: one page at a time
	}
}