mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-04 21:00:36 +08:00
56 lines
1.6 KiB
Python
56 lines
1.6 KiB
Python
"""
|
|
Basic example of scraping pipeline using ScriptCreatorGraph
|
|
"""
|
|
|
|
import os
|
|
from dotenv import load_dotenv
|
|
from scrapegraphai.graphs import ScriptCreatorMultiGraph
|
|
from scrapegraphai.utils import prettify_exec_info
|
|
|
|
load_dotenv()
|
|
|
|
# ************************************************
|
|
# Define the configuration for the graph
|
|
# ************************************************
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"model": "ollama/mistral",
|
|
"temperature": 0,
|
|
# "model_tokens": 2000, # set context length arbitrarily,
|
|
"base_url": "http://localhost:11434", # set ollama URL arbitrarily
|
|
},
|
|
"library": "beautifoulsoup",
|
|
"verbose": True,
|
|
}
|
|
|
|
# ************************************************
|
|
# Create the ScriptCreatorGraph instance and run it
|
|
# ************************************************
|
|
|
|
urls=[
|
|
"https://schultzbergagency.com/emil-raste-karlsen/",
|
|
"https://schultzbergagency.com/johanna-hedberg/",
|
|
]
|
|
|
|
# ************************************************
|
|
# Create the ScriptCreatorGraph instance and run it
|
|
# ************************************************
|
|
|
|
script_creator_graph = ScriptCreatorMultiGraph(
|
|
prompt="Find information about actors",
|
|
# also accepts a string with the already downloaded HTML code
|
|
source=urls,
|
|
config=graph_config
|
|
)
|
|
|
|
result = script_creator_graph.run()
|
|
print(result)
|
|
|
|
# ************************************************
|
|
# Get graph execution info
|
|
# ************************************************
|
|
|
|
graph_exec_info = script_creator_graph.get_execution_info()
|
|
print(prettify_exec_info(graph_exec_info))
|