mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-06 21:11:37 +08:00
54 lines
1.4 KiB
Python
54 lines
1.4 KiB
Python
"""
|
|
Basic example of scraping pipeline using Code Generator with schema
|
|
"""
|
|
|
|
import os, json
|
|
from typing import List
|
|
from dotenv import load_dotenv
|
|
from langchain_core.pydantic_v1 import BaseModel, Field
|
|
from scrapegraphai.graphs import CodeGeneratorGraph
|
|
|
|
load_dotenv()
|
|
|
|
# ************************************************
|
|
# Define the output 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
|
|
# ************************************************
|
|
|
|
openai_key = os.getenv("OPENAI_APIKEY")
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"api_key":openai_key,
|
|
"model": "openai/gpt-4o",\
|
|
},
|
|
"library": "beautifulsoup",
|
|
"verbose": True,
|
|
"headless": False,
|
|
"reduction": 2,
|
|
}
|
|
|
|
# ************************************************
|
|
# Create the SmartScraperGraph instance and run it
|
|
# ************************************************
|
|
|
|
code_generator_graph = CodeGeneratorGraph(
|
|
prompt="List me all the projects with their description",
|
|
source="https://perinim.github.io/projects/",
|
|
schema=Projects,
|
|
config=graph_config
|
|
)
|
|
|
|
result = code_generator_graph.run()
|
|
print(result)
|