搞定网页爬取和数据提取？Crawl4AI带你体验高效AI Agent工作流程

from crawl4ai import WebCrawler

crawler = WebCrawler()
crawler.warmup()
result = crawler.run(url="https://openai.com/api/pricing/")
print(result.markdown)

mport os
from crawl4ai import WebCrawler
from crawl4ai.extraction_strategy import LLMExtractionStrategy
from pydantic import BaseModel, Field

class OpenAIModelFee(BaseModel):
    model_name: str = Field(..., description="Name of the OpenAI model.")
    input_fee: str = Field(..., description="Fee for input token for the OpenAI model.")
    output_fee: str = Field(..., description="Fee for output token ßfor the OpenAI model.")

url = 'https://openai.com/api/pricing/'
crawler = WebCrawler()
crawler.warmup()

result = crawler.run(
        url=url,
        word_count_threshold=1,
        extraction_strategy= LLMExtractionStrategy(
            provider= "openai/gpt-4o", api_token = os.getenv('OPENAI_API_KEY'), 
            schema=OpenAIModelFee.schema(),
            extraction_type="schema",
            instruction="""从爬取的内容中，提取所有提到的模型名称以及它们的输入和输出token费用。  不要遗漏整个内容中的任何模型。一个提取的模型JSON格式应如下所示：  
{"model_name": "GPT-4", "input_fee": "US$10.00 / 1M tokens", "output_fee": "US$30.00 / 1M tokens"}。"""
        ),            
        bypass_cache=True,
    )

print(result.extracted_content)

import os
from crawl4ai import WebCrawler
from crawl4ai.extraction_strategy import LLMExtractionStrategy
from pydantic import BaseModel, Field
from praisonai_tools import BaseTool

class ModelFee(BaseModel):
    llm_model_name: str = Field(..., description="Name of the model.")
    input_fee: str = Field(..., description="Fee for input token for the model.")
    output_fee: str = Field(..., description="Fee for output token for the model.")

class ModelFeeTool(BaseTool):
    name: str = "ModelFeeTool"
    description: str = "从给定的定价页面中提取模型的输入和输出token费用。 "

    def _run(self, url: str):
        crawler = WebCrawler()
        crawler.warmup()

        result = crawler.run(
            url=url,
            word_count_threshold=1,
            extraction_strategy= LLMExtractionStrategy(
                provider="openai/gpt-4o",
                api_token=os.getenv('OPENAI_API_KEY'), 
                schema=ModelFee.schema(),
                extraction_type="schema",
                instruction="""从爬取的内容中，提取所有提到的模型名称以及它们的输入和输出token费用。  不要遗漏整个内容中的任何模型。一个提取的模型JSON格式应如下所示：  
{"model_name": "GPT-4", "input_fee": "US$10.00 / 1M tokens", "output_fee": "US$30.00 / 1M tokens"}。"""
            ),            
            bypass_cache=True,
        )
        return result.extracted_content

if __name__ == "__main__":
    # Test the ModelFeeTool
    tool = ModelFeeTool()
    url = "https://www.openai.com/pricing"
    result = tool.run(url)
    print(result)

framework: crewai
topic: extract model pricing from websites
roles:
  web_scraper:
    backstory: 一个网络爬虫专家，对从在线资源中提取结构化数据有深刻的理解。https://openai.com/api/pricing/ https://www.anthropic.com/pricing https://cohere.com/pricing
    goal: 从各种网站收集模型定价数据
    role: Web Scraper
    tasks:
      scrape_model_pricing:
        description: 从提供的网站列表中抓取模型定价信息。
        expected_output: 包含模型定价数据的原始HTML或JSON。
    tools:
    - 'ModelFeeTool'
  data_cleaner:
    backstory: 数据清洗专家，确保所有收集的数据准确无误且格式正确。
    goal: 清洗并整理抓取到的定价数据
    role: Data Cleaner
    tasks:
      clean_pricing_data:
        description: 处理原始抓取数据，删除任何重复项和不一致项，并将其转换为结构化格式。
        expected_output: 包含模型定价的已清洗且已整理的JSON或CSV文件
          data.
    tools:
    - ''
  data_analyzer:
    backstory: 数据分析专家，专注于从结构化数据中获取可操作的见解。
    goal: 分析已清洗的定价数据以提取见解
    role: Data Analyzer
    tasks:
      analyze_pricing_data:
        description: 分析已清洗的数据，提取模型定价的趋势、模式和见解。
        expected_output: 总结模型定价趋势和见解的详细报告。
    tools:
    - ''
dependencies: []