mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-06-28 21:01:55 +08:00
49 lines
1.5 KiB
Python
49 lines
1.5 KiB
Python
"""
|
|
Basic example of scraping pipeline using SmartScraper and OneAPI
|
|
"""
|
|
from typing import List
|
|
from pydantic import BaseModel, Field
|
|
from scrapegraphai.graphs import SmartScraperGraph
|
|
from scrapegraphai.utils import prettify_exec_info
|
|
|
|
# ************************************************
|
|
# Define the configuration 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
|
|
# *********************************************
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"api_key": "***************************",
|
|
"model": "oneapi/qwen-turbo",
|
|
"base_url": "http://127.0.0.1:3000/v1", # 设置 OneAPI URL
|
|
}
|
|
}
|
|
|
|
# ************************************************
|
|
# Create the SmartScraperGraph instance and run it
|
|
# ************************************************
|
|
|
|
smart_scraper_graph = SmartScraperGraph(
|
|
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
|
|
)
|
|
|
|
# ************************************************
|
|
# Get graph execution info
|
|
# ************************************************
|
|
result = smart_scraper_graph.run()
|
|
print(result)
|
|
print(prettify_exec_info(result))
|