mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-09 21:19:20 +08:00
40 lines
1.0 KiB
Python
40 lines
1.0 KiB
Python
"""
|
|
Basic example of scraping pipeline using SmartScraper
|
|
"""
|
|
|
|
import json
|
|
from scrapegraphai.graphs import SmartScraperMultiGraph
|
|
|
|
# ************************************************
|
|
# Define the configuration for the graph
|
|
# ************************************************
|
|
graph_config = {
|
|
"llm": {
|
|
"model": "ollama/llama3.1",
|
|
"temperature": 0,
|
|
"format": "json", # Ollama needs the format to be specified explicitly
|
|
# "base_url": "http://localhost:11434", # set ollama URL arbitrarily
|
|
},
|
|
|
|
"verbose": True,
|
|
"headless": False
|
|
}
|
|
|
|
|
|
# *******************************************************
|
|
# Create the SmartScraperMultiGraph instance and run it
|
|
# *******************************************************
|
|
|
|
multiple_search_graph = SmartScraperMultiGraph(
|
|
prompt="Who is Marco Perini?",
|
|
source= [
|
|
"https://perinim.github.io/",
|
|
"https://perinim.github.io/cv/"
|
|
],
|
|
schema=None,
|
|
config=graph_config
|
|
)
|
|
|
|
result = multiple_search_graph.run()
|
|
print(json.dumps(result, indent=4))
|