uv add scrapfly-sdk

from crewai import Agent, Task, Crew
from crewai_tools import ScrapflyScrapeWebsiteTool

# Initialize the tool
scrape_tool = ScrapflyScrapeWebsiteTool(api_key="your_scrapfly_api_key")

# Define an agent that uses the tool
web_scraper_agent = Agent(
    role="Web Scraper",
    goal="Extract information from websites",
    backstory="An expert in web scraping who can extract content from any website.",
    tools=[scrape_tool],
    verbose=True,
)

# Example task to extract content from a website
scrape_task = Task(
    description="Extract the main content from the product page at https://web-scraping.dev/products and summarize the available products.",
    expected_output="A summary of the products available on the website.",
    agent=web_scraper_agent,
)

# Create and run the crew
crew = Crew(agents=[web_scraper_agent], tasks=[scrape_task])
result = crew.kickoff()

# Example with custom scraping parameters
web_scraper_agent = Agent(
    role="Web Scraper",
    goal="Extract information from websites with custom parameters",
    backstory="An expert in web scraping who can extract content from any website.",
    tools=[scrape_tool],
    verbose=True,
)

# The agent will use the tool with parameters like:
# url="https://web-scraping.dev/products"
# scrape_format="markdown"
# ignore_scrape_failures=True
# scrape_config={
#     "asp": True,  # Bypass scraping blocking solutions, like Cloudflare
#     "render_js": True,  # Enable JavaScript rendering with a cloud headless browser
#     "proxy_pool": "public_residential_pool",  # Select a proxy pool
#     "country": "us",  # Select a proxy location
#     "auto_scroll": True,  # Auto scroll the page
# }

scrape_task = Task(
    description="Extract the main content from the product page at https://web-scraping.dev/products using advanced scraping options including JavaScript rendering and proxy settings.",
    expected_output="A detailed summary of the products with all available information.",
    agent=web_scraper_agent,
)

# Example of using the tool with an agent
web_scraper_agent = Agent(
    role="Web Scraper",
    goal="Extract information from websites",
    backstory="An expert in web scraping who can extract content from any website.",
    tools=[scrape_tool],
    verbose=True,
)

# Create a task for the agent
scrape_task = Task(
    description="Extract the main content from example.com in markdown format.",
    expected_output="The main content of example.com in markdown format.",
    agent=web_scraper_agent,
)

# Run the task
crew = Crew(agents=[web_scraper_agent], tasks=[scrape_task])
result = crew.kickoff()

# Create a task with more specific instructions
advanced_scrape_task = Task(
    description="""
    Extract content from example.com with the following requirements:
    - Convert the content to plain text format
    - Enable JavaScript rendering
    - Use a US-based proxy
    - Handle any scraping failures gracefully
    """,
    expected_output="The extracted content from example.com",
    agent=web_scraper_agent,
)

# Create a task that instructs the agent to handle errors
error_handling_task = Task(
    description="""
    Extract content from a potentially problematic website and make sure to handle any 
    scraping failures gracefully by setting ignore_scrape_failures to True.
    """,
    expected_output="Either the extracted content or a graceful error message",
    agent=web_scraper_agent,
)

class ScrapflyScrapeWebsiteTool(BaseTool):
    name: str = "Scrapfly web scraping API tool"
    description: str = (
        "Scrape a webpage url using Scrapfly and return its content as markdown or text"
    )
    
    # Implementation details...
    
    def _run(
        self,
        url: str,
        scrape_format: str = "markdown",
        scrape_config: Optional[Dict[str, Any]] = None,
        ignore_scrape_failures: Optional[bool] = None,
    ):
        from scrapfly import ScrapeApiResponse, ScrapeConfig

        scrape_config = scrape_config if scrape_config is not None else {}
        try:
            response: ScrapeApiResponse = self.scrapfly.scrape(
                ScrapeConfig(url, format=scrape_format, **scrape_config)
            )
            return response.scrape_result["content"]
        except Exception as e:
            if ignore_scrape_failures:
                logger.error(f"Error fetching data from {url}, exception: {e}")
                return None
            else:
                raise e