1-smart_scraper.py

""" 
Basic example of scraping pipeline using SmartScraper
"""
import os
import json
from dotenv import load_dotenv
from scrapegraphai.graphs import SmartScraperGraph
from scrapegraphai.utils import prettify_exec_info

load_dotenv()

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


graph_config = {
    "llm": {
        "api_key": os.getenv("OPENAI_API_KEY"),
        "model": "openai/gpt-4o",
    },
    "verbose": True,
    "headless": False,
}

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

smart_scraper_graph = SmartScraperGraph(
    prompt="Extract me all the products name",
    source="https://www.amazon.com/s?k=keyboard&crid=SPZV94HXHGCF&sprefix=keyboar%2Caps%2C233&ref=nb_sb_noss_2",
    config=graph_config
)

result = smart_scraper_graph.run()
print(json.dumps(result, indent=4))

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

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