extract_text

curl -X POST https://www.crawlforge.dev/api/v1/tools/extract_text \
  -H "X-API-Key: cf_test_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com/article",
    "selector": "article",
    "clean": true,
    "max_length": 5000
  }'

// npm install crawlforge-sdk
import { CrawlForge } from 'crawlforge-sdk';

const client = new CrawlForge({ apiKey: process.env.CRAWLFORGE_API_KEY });

const htmlContent =
  '<html><body>' +
  '<article>' +
  '<h1>Article Title</h1>' +
  '<p>This is the main content of the article.</p>' +
  '<a href="/related">Related Article</a>' +
  '</article>' +
  '</body></html>';

const result = await client.extractText({
  html: htmlContent,
  selector: 'article',
  clean: true,
  preserve_links: true,
});

// result.data is untyped in crawlforge-sdk 0.1 — its shape is the Response Example below.
const { text, metadata } = result.data as {
  text: string; metadata: { word_count: number; character_count: number };
};
console.log('Extracted text:', text);
console.log('Word count:', metadata.word_count);
console.log('Character count:', metadata.character_count);

# pip install crawlforge
from crawlforge import CrawlForge

client = CrawlForge()  # reads CRAWLFORGE_API_KEY

result = client.extract_text(
    url='https://example.com/article',
    selector='article, .main-content',
    clean=True,
    preserve_formatting=True,
    max_length=10000,
)

# result.data is a plain dict — its shape is the Response Example below.
text = result.data['text']
metadata = result.data['metadata']

print(f"Title: {metadata['title']}")
print(f"Word count: {metadata['word_count']}")
print(f"Character count: {metadata['character_count']}")
print(f"\nExtracted text:\n{text[:500]}...")