wehub-resource-sync
46 lines
1.2 KiB
Python
46 lines
1.2 KiB
Python
"""
|
|
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
|
|
# ************************************************
|
|
|
|
groq_key = os.getenv("GROQ_APIKEY")
|
|
|
|
graph_config = {
|
|
"llm": {"model": "groq/gemma-7b-it", "api_key": groq_key, "temperature": 0},
|
|
"headless": False,
|
|
"backend": "undetected_chromedriver",
|
|
}
|
|
|
|
# ************************************************
|
|
# 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))
|