🦞 Smart scraper with schema

""" 
Basic example of scraping pipeline using SmartScraper
"""
from typing import List
from pydantic import BaseModel, Field
from scrapegraphai.graphs import SmartScraperGraph
from scrapegraphai.utils import prettify_exec_info

# ************************************************
# Define the output schema for the graph
# ************************************************

class Project(BaseModel):
    title: str = Field(description="The title of the project")
    description: str = Field(description="The description of the project")

class Projects(BaseModel):
    projects: List[Project]

# ************************************************
# Define the configuration for the graph
# ************************************************

graph_config = {
    "llm": {
        "client": "client_name",
        "model": "bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
        "temperature": 0.0
    },
    "embeddings": {
        "model": "bedrock/cohere.embed-multilingual-v3"
    }
}

# ************************************************
# Create the SmartScraperGraph instance and run it
# ************************************************

smart_scraper_graph = SmartScraperGraph(
    prompt="List me all the projects with their description",
    # also accepts a string with the already downloaded HTML code
    source="https://perinim.github.io/projects/",
    schema=Projects,
    config=graph_config
)

result = smart_scraper_graph.run()
print(result)

# ************************************************
# Get graph execution info
# ************************************************

graph_exec_info = smart_scraper_graph.get_execution_info()
print(prettify_exec_info(graph_exec_info))