Den Inhalt mehrerer Websites auf einmal abrufen

import requests
import hashlib

API_KEY = "YOUR_API_KEY"

def create_hash_id(url):
    return hashlib.sha256(url.encode()).hexdigest()[:16]

def compose_items_array():
    urls = [
        "https://www.google.com/search?q=nikola+tesla&gl=us&hl=en",
        "https://www.google.com/search?q=alexander+the+great&gl=us&hl=en",
        "https://www.google.com/search?q=google+solar+eclipse&gl=us&hl=en",
        "https://www.google.com/search?q=crispr&gl=us&hl=en",
        "https://www.google.com/search?q=genghis%20khan&gl=us&hl=en"
    ]
    return [{"custom_id": create_hash_id(url), "url": url} for url in urls]

def start_batch(items):
    payload = {
        "items": items
    }
    headers = {"Authorization": f"Bearer {API_KEY}"}
    response = requests.post(
        "https://api.olostep.com/v1/batches",
        headers=headers,
        json=payload
    )
    return response.json()["id"]

if __name__ == "__main__":
    items = compose_items_array()
    batch_id = start_batch(items)
    print("Batch gestartet. ID:", batch_id)

import requests

def check_batch_status(batch_id):
    headers = {"Authorization": f"Bearer {API_KEY}"}
    response = requests.get(
        f"https://api.olostep.com/v1/batches/{batch_id}",
        headers=headers
    )
    return response.json()["status"]

import time

def recursive_check(batch_id):
    status = check_batch_status(batch_id)
    print("Status:", status)
    if status == "completed":
        print("Batch ist abgeschlossen!")
    else:
        time.sleep(60)
        recursive_check(batch_id)

import requests

def get_completed_items(batch_id):
    headers = {"Authorization": f"Bearer {API_KEY}"}
    response = requests.get(
        f"https://api.olostep.com/v1/batches/{batch_id}/items",
        headers=headers
    )
    return response.json()["items"]

items = get_completed_items(batch_id)
for item in items:
    print(f"URL: {item['url']}\nCustom ID: {item['custom_id']}\nRetrieve ID: {item['retrieve_id']}\n---")

def retrieve_content(retrieve_id):
    url = "https://api.olostep.com/v1/retrieve"
    headers = {"Authorization": f"Bearer {API_KEY}"}
    params = {"retrieve_id": retrieve_id}

    response = requests.get(url, headers=headers, params=params)
    return response.json()

# Beispielverwendung:
items = get_completed_items(batch_id)
for item in items:
    content = retrieve_content(item['retrieve_id'])
    print(content)