📰 Wired Articles

from pydantic import BaseModel, Field
from typing import List
from scrapegraph_py import ScrapeGraphAI

# Schema for a single news item
class NewsItemSchema(BaseModel):
    category: str = Field(description="Category of the news (e.g., 'Health', 'Environment')")
    title: str = Field(description="Title of the news article")
    link: str = Field(description="URL to the news article")
    author: str = Field(description="Author of the news article")

# Schema that contains a list of news items
class ListNewsSchema(BaseModel):
    news: List[NewsItemSchema] = Field(description="List of news articles with their details")

sgai = ScrapeGraphAI()  # reads SGAI_API_KEY from env

res = sgai.extract(
    "Extract latest news articles",
    url="https://www.wired.com/",
    schema=ListNewsSchema.model_json_schema(),
)

if res.status == "success":
    print(res.data.json_data)

{
    "news": [
        {
            "category": "Artificial Intelligence",
            "title": "The Race to Build Better Large Language Models",
            "link": "https://www.wired.com/story/the-race-to-build-better-llms",
            "author": "Will Knight"
        },
        {
            "category": "Security",
            "title": "The Latest Cybersecurity Threats You Need to Know About",
            "link": "https://www.wired.com/story/latest-cybersecurity-threats",
            "author": "Lily Hay Newman"
        },
        {
            "category": "Science",
            "title": "New Discoveries in Quantum Computing",
            "link": "https://www.wired.com/story/quantum-computing-discoveries",
            "author": "Steven Levy"
        }
    ]
}