pip install scrapegraphai capsolver

playwright install

import json
from scrapegraphai.graphs import SmartScraperGraph

# Define the configuration for the scraping pipeline
graph_config = {
    "llm": {
        "api_key": "YOUR_OPENAI_APIKEY",
        "model": "openai/gpt-4o-mini",
    },
    "verbose": True,
    "headless": False,
}

# Create the SmartScraperGraph instance
smart_scraper_graph = SmartScraperGraph(
    prompt="List me all the quotes with their description",
    source="https://quotes.toscrape.com/",
    config=graph_config
)

# Run the pipeline
result = smart_scraper_graph.run()
print(json.dumps(result, indent=4))

import json
from scrapegraphai.graphs import SmartScraperGraph

# Define the configuration for the scraping pipeline
graph_config = {
    "llm": {
        "model": "ollama/llama3.1",
        "temperature": 0,
        "format": "json",  # Ollama needs the format to be specified explicitly
        # "base_url": "http://localhost:11434", # set ollama URL arbitrarily
    },
    "verbose": True,
    "headless": False
}

# Create the SmartScraperGraph instance
smart_scraper_graph = SmartScraperGraph(
    prompt="List me all the quotes with their description",
    source="https://quotes.toscrape.com/",
    config=graph_config
)

# Run the pipeline
result = smart_scraper_graph.run()
print(json.dumps(result, indent=4))

import capsolver
import os
import json
from scrapegraphai.graphs import SmartScraperGraph

# Consider using environment variables for sensitive information
PROXY = os.getenv("PROXY", "http://username:password@host:port")
capsolver.api_key = os.getenv("CAPSOLVER_API_KEY", "Your Capsolver API Key")
PAGE_URL = os.getenv("PAGE_URL", "PAGE_URL")
PAGE_KEY = os.getenv("PAGE_SITE_KEY", "PAGE_SITE_KEY")

def solve_recaptcha_v2(url, key):
    solution = capsolver.solve({
        "type": "ReCaptchaV2Task",
        "websiteURL": url,
        "websiteKey": key,
        "proxy": PROXY
    })
    return solution['solution']['gRecaptchaResponse']

def main():
    print("Solving reCaptcha v2")
    solution = solve_recaptcha_v2(PAGE_URL, PAGE_KEY)
    print("Solution: ", solution)

# Define the configuration for the scraping pipeline
graph_config = {
    "llm": {
        "api_key": "YOUR_OPENAI_APIKEY",
        "model": "openai/gpt-4o-mini",
    },
    "verbose": True,
    "headless": False,
}

# Create the SmartScraperGraph instance
smart_scraper_graph = SmartScraperGraph(
    prompt="Find the description of each quote.",
    source="https://quotes.toscrape.com/",
    config=graph_config
)

# Run the pipeline
result = smart_scraper_graph.run()
print(json.dumps(result, indent=4))