Prerequisites

  • Python 3.10 or higher
  • Praison Labs Agents package installed
  • scrapy package installed

​
Spider Tools

Use Spider Tools to crawl and scrape web content with AI agents.

1

Install Dependencies

First, install the required packages:

pip install praisonaiagents scrapy
2

Import Components

Import the necessary components:

from praisonaiagents import Agent, Task, Praison LabsAgents
from praisonaiagents.tools import scrape_page, extract_links, crawl, extract_text
3

Create Agent

Create a web scraping agent:

spider_agent = Agent(
    name="WebSpider",
    role="Web Scraping Specialist",
    goal="Extract and analyze web content efficiently.",
    backstory="Expert in web scraping and content extraction.",
    tools=[scrape_page, extract_links, crawl, extract_text],
    self_reflect=False
)
4

Define Task

Define the scraping task:

scraping_task = Task(
    description="Scrape product information from an e-commerce website.",
    expected_output="Structured product data with prices and descriptions.",
    agent=spider_agent,
    name="product_scraping"
)
5

Run Agent

Initialize and run the agent:

agents = Praison LabsAgents(
    agents=[spider_agent],
    tasks=[scraping_task],
    process="sequential"
)
agents.start()

​
Understanding Spider Tools

What are Spider Tools?

Spider Tools provide web scraping capabilities for AI agents:

  • Page scraping and downloading
  • Content extraction and filtering
  • Link discovery and crawling
  • HTML parsing and cleaning
  • Data structuring and formatting

​
Key Components

Spider Agent

Create specialized scraping agents:

Agent(tools=[scrape_page, extract_content, crawl_links, parse_html, structure_data])

Spider Task

Define scraping tasks:

Task(description="scraping_query")

Process Types

Sequential or parallel processing:

process="sequential"

Scraping Options

Customize scraping parameters:

max_depth=2, delay=1

​
Examples

​
Basic Web Scraping Agent 

from praisonaiagents import Agent, Task, Praison LabsAgents
from praisonaiagents.tools import scrape_page, extract_links, crawl, extract_text

# Create search agent
agent = Agent(
    name="AsyncWebCrawler",
    role="Web Scraping Specialist",
    goal="Extract and analyze web content efficiently.",
    backstory="Expert in web scraping and content extraction.",
    tools=[scrape_page, extract_links, crawl, extract_text],
    self_reflect=False
)

# Define task
task = Task(
    description="Scrape and analyze the content from 'https://example.com'",
    expected_output="Extracted content with links and text analysis",
    agent=agent,
    name="web_scraping"
)

# Run agent
agents = Praison LabsAgents(
    agents=[agent],
    tasks=[task],
    process="sequential"
)
agents.start()

​
Advanced Scraping with Multiple Agents 

# Create scraping agent
scraper_agent = Agent(
    name="Scraper",
    role="Content Scraper",
    goal="Extract web content systematically.",
    tools=[scrape_page, crawl_links, parse_html],
    self_reflect=False
)

# Create analysis agent
analysis_agent = Agent(
    name="Analyzer",
    role="Content Analyst",
    goal="Analyze and structure scraped content.",
    backstory="Expert in data analysis and organization.",
    tools=[extract_content, structure_data],
    self_reflect=False
)

# Define tasks
scraping_task = Task(
    description="Scrape product data from multiple pages.",
    agent=scraper_agent,
    name="product_scraping"
)

analysis_task = Task(
    description="Analyze and structure the scraped product data.",
    agent=analysis_agent,
    name="data_analysis"
)

# Run agents
agents = Praison LabsAgents(
    agents=[scraper_agent, analysis_agent],
    tasks=[scraping_task, analysis_task],
    process="sequential"
)
agents.start()

​
Best Practices

​
Common Patterns

​
Web Scraping Pipeline 

# Scraping agent
scraper = Agent(
    name="Scraper",
    role="Web Scraper",
    tools=[scrape_page, crawl_links, parse_html]
)

# Processing agent
processor = Agent(
    name="Processor",
    role="Data Processor",
    tools=[extract_content, structure_data]
)

# Define tasks
scrape_task = Task(
    description="Scrape website content",
    agent=scraper
)

process_task = Task(
    description="Process scraped content",
    agent=processor
)

# Run workflow
agents = Praison LabsAgents(
    agents=[scraper, processor],
    tasks=[scrape_task, process_task]
)