Skip to main content

rag_caching

""" 
Basic example of scraping pipeline using SmartScraper
"""

import os
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
# ************************************************

openai_key = os.getenv("OPENAI_APIKEY")

graph_config = {
"llm": {
"api_key": openai_key,
"model": "openai/gpt-3.5-turbo",
},
"caching": True
}

# ************************************************
# 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/",
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))