mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-01 21:00:48 +08:00
62 lines
1.7 KiB
Python
62 lines
1.7 KiB
Python
"""
|
|
Basic example of scraping pipeline using ScriptCreatorGraph
|
|
"""
|
|
|
|
import os
|
|
from typing import List
|
|
from dotenv import load_dotenv
|
|
from pydantic import BaseModel, Field
|
|
from scrapegraphai.graphs import ScriptCreatorGraph
|
|
from scrapegraphai.utils import prettify_exec_info
|
|
|
|
load_dotenv()
|
|
|
|
# ************************************************
|
|
# Define the schema for the graph
|
|
# ************************************************
|
|
|
|
class Project(BaseModel):
|
|
title: str = Field(description="The title of the project")
|
|
description: str = Field(description="The description of the project")
|
|
|
|
class Projects(BaseModel):
|
|
projects: List[Project]
|
|
|
|
# ************************************************
|
|
# Define the configuration for the graph
|
|
# ************************************************
|
|
|
|
fireworks_api_key = os.getenv("FIREWORKS_APIKEY")
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"api_key": fireworks_api_key,
|
|
"model": "fireworks/accounts/fireworks/models/mixtral-8x7b-instruct"
|
|
},
|
|
"verbose": True,
|
|
"library": "beautifulsoup",
|
|
}
|
|
|
|
# ************************************************
|
|
# Create the ScriptCreatorGraph instance and run it
|
|
# ************************************************
|
|
|
|
script_creator_graph = ScriptCreatorGraph(
|
|
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,
|
|
schema=Projects
|
|
)
|
|
|
|
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))
|
|
|