wehub-resource-sync
43 lines
956 B
Python
43 lines
956 B
Python
"""
|
|
Basic example of scraping pipeline using SmartScraper
|
|
"""
|
|
|
|
import json
|
|
import os
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
from scrapegraphai.graphs import SmartScraperGraph
|
|
|
|
load_dotenv()
|
|
|
|
# ************************************************
|
|
# Define the configuration for the graph
|
|
# ************************************************
|
|
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"api_key": os.getenv("OPENAI_API_KEY"),
|
|
"model": "openai/gpt-4o",
|
|
},
|
|
"scrape_do": {
|
|
"api_key": os.getenv("SCRAPE_DO_API_KEY"),
|
|
},
|
|
"verbose": True,
|
|
"headless": False,
|
|
}
|
|
|
|
# ************************************************
|
|
# Create the SmartScraperGraph instance and run it
|
|
# ************************************************
|
|
|
|
smart_scraper_graph = SmartScraperGraph(
|
|
prompt="List me all the projects",
|
|
source="https://perinim.github.io/projects/",
|
|
config=graph_config,
|
|
)
|
|
|
|
result = smart_scraper_graph.run()
|
|
print(json.dumps(result, indent=4))
|