Python SDK

pip install ujeebu-python

from ujeebu_python import UjeebuClient

# Initialize with your API key
client = UjeebuClient('your-api-key')

# Scrape a website
response = client.scrape(
    'https://example.com',
    params={'js': True, 'response_type': 'html'}
)

print(response.text)

import os
from ujeebu_python import UjeebuClient

client = UjeebuClient(os.environ['UJEEBU_API_KEY'])

response = client.scrape('https://example.com')
print(response.text)

response = client.extract('https://example.com/article')

data = response.json()
print(data['article']['title'])
print(data['article']['author'])
print(data['article']['text'])
print(data['article']['pub_date'])

response = client.serp(params={
    'search': 'artificial intelligence',
    'search_type': 'search',
    'lang': 'en',
    'results_count': 20
})

data = response.json()
print(data['organic_results'])
print(data['knowledge_graph'])

response = client.preview('https://example.com/article')

data = response.json()
print(data['title'])
print(data['description'])
print(data['image'])
print(data['author'])
print(data['site_name'])

response = client.ai_scrape(
    'https://example.com/product',
    'Extract the product name, price, and rating'
)

data = response.json()
print(data['data'])

response = client.auto_extract('https://example.com/article')

data = response.json()
print(f"Page type: {data['page_type']}")
print(data['data'])

response = client.markdown('https://example.com/article')

data = response.json()
print(data['markdown'])

response = client.get_pdf(
    'https://example.com',
    params={'js': True, 'wait_for': 2000}
)

data = response.json()
# data['pdf'] contains base64-encoded PDF

response = client.get_screenshot(
    'https://example.com',
    params={'js': True, 'screenshot_fullpage': True}
)

data = response.json()
# data['screenshot'] contains base64-encoded image

response = client.get_html(
    'https://example.com',
    params={'js': True, 'strip_tags': 'script,style'}
)

data = response.json()
print(data['html'])

from requests.exceptions import HTTPError, ConnectionError, Timeout

try:
    response = client.scrape('https://example.com')
    response.raise_for_status()
    print(response.text)
except HTTPError as e:
    print(f'HTTP Error: {e.response.status_code}')
    print(f'Message: {e.response.json().get("message")}')
except ConnectionError:
    print('Network connection error')
except Timeout:
    print('Request timed out')
except Exception as e:
    print(f'Error: {e}')

import pandas as pd
from ujeebu_python import UjeebuClient

client = UjeebuClient(os.environ['UJEEBU_API_KEY'])

# Scrape product data
response = client.scrape(
    'https://example.com/products',
    params={
        'extract_rules': {
            'products': {
                'selector': '.product',
                'type': 'list',
                'data': {
                    'name': '.title',
                    'price': '.price',
                    'rating': '.rating'
                }
            }
        }
    }
)

data = response.json()
df = pd.DataFrame(data['result']['products'])
print(df.head())

import asyncio
from concurrent.futures import ThreadPoolExecutor
from ujeebu_python import UjeebuClient

client = UjeebuClient(os.environ['UJEEBU_API_KEY'])
urls = ['https://example1.com', 'https://example2.com', 'https://example3.com']

async def scrape_all(urls):
    loop = asyncio.get_event_loop()
    with ThreadPoolExecutor() as executor:
        tasks = [
            loop.run_in_executor(executor, client.scrape, url)
            for url in urls
        ]
        return await asyncio.gather(*tasks)

results = asyncio.run(scrape_all(urls))
for result in results:
    print(len(result.text))