mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-12 21:01:56 +08:00
68 lines
2.0 KiB
Python
68 lines
2.0 KiB
Python
"""
|
|
Basic example of scraping pipeline using SmartScraper using Azure OpenAI Key
|
|
"""
|
|
|
|
import os
|
|
from dotenv import load_dotenv
|
|
from typing import Dict
|
|
|
|
from pydantic import BaseModel
|
|
from scrapegraphai.graphs import SmartScraperGraph
|
|
from scrapegraphai.utils import prettify_exec_info
|
|
from langchain_community.llms import HuggingFaceEndpoint
|
|
from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
|
|
|
|
# ************************************************
|
|
# Define the output schema for the graph
|
|
# ************************************************
|
|
|
|
class Project(BaseModel):
|
|
title: str
|
|
description: str
|
|
|
|
class Projects(BaseModel):
|
|
Projects: Dict[str, Project]
|
|
|
|
## required environment variable in .env
|
|
#HUGGINGFACEHUB_API_TOKEN
|
|
load_dotenv()
|
|
|
|
HUGGINGFACEHUB_API_TOKEN = os.getenv('HUGGINGFACEHUB_API_TOKEN')
|
|
# ************************************************
|
|
# Initialize the model instances
|
|
# ************************************************
|
|
|
|
repo_id = "mistralai/Mistral-7B-Instruct-v0.2"
|
|
|
|
llm_model_instance = HuggingFaceEndpoint(
|
|
repo_id=repo_id, max_length=128, temperature=0.5, token=HUGGINGFACEHUB_API_TOKEN
|
|
)
|
|
|
|
embedder_model_instance = HuggingFaceInferenceAPIEmbeddings(
|
|
api_key=HUGGINGFACEHUB_API_TOKEN, model_name="sentence-transformers/all-MiniLM-l6-v2"
|
|
)
|
|
|
|
# ************************************************
|
|
# Create the SmartScraperGraph instance and run it
|
|
# ************************************************
|
|
|
|
graph_config = {
|
|
"llm": {"model_instance": llm_model_instance},
|
|
}
|
|
|
|
smart_scraper_graph = SmartScraperGraph(
|
|
prompt="List me all the projects with their description",
|
|
source="https://perinim.github.io/projects/",
|
|
schema=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))
|