爬虫（关于大模型+爬虫技术）

两个开源爬虫项目地址

• crawl4ai：https://github.com/unclecode/crawl4ai

• ScrapeGraphAI：https://github.com/ScrapeGraphAI/Scrapegraph-ai

crawl4ai

安装：

pip install crawl4ai
pip install playweight
playweight install  

示例：

import asyncio
from crawl4ai import AsyncWebCrawler
import json
# 定义如何从页面中提取数据。
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy


async def main():
    async with AsyncWebCrawler(verbose=True) as crawler:
        result = await crawler.arun(url="https://lpt.liepin.com/recommend#preview")
        print(f"基本爬取结果: {result.markdown[:500]}")  # 打印前500个字符

asyncio.run(main())

ScrapeGraphAi

安装

pip install ScrapeGraphAi
pip install playweight
playweight install  

示例：

import json

from langchain import requests
from scrapegraphai.graphs import SmartScraperGraph
from langchain_community.chat_models.moonshot import MoonshotChat


import os

from langchain_community.chat_models import QianfanChatEndpoint
from langchain_core.language_models.chat_models import HumanMessage
#
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'Accept-Language': 'en-US,en;q=0.5',
    'Connection': 'close',
}
response=requests.get("xxxx",headers=headers)

os.environ["QIANFAN_AK"] = "xxxx"
os.environ["QIANFAN_SK"] = "xxxx"
chat = QianfanChatEndpoint(streaming=True)



graph_config = {

    "llm": {
        "model_instance": chat,
        "model_tokens": 5000
    },
}

# 创建实例
smart_scraper_graph = SmartScraperGraph(
    prompt="找到这个网站是做什么的，xxxx。",
    source="https://lpt.liepin.com/recommend#preview",
    config=graph_config
)

# 运行爬虫
result = smart_scraper_graph.run()

# 输出结果
print(json.dumps(result, indent=4))