alternative.py

###############################################################################################################################################################
#                                         _____  _           ___  _         ___                                
#                                        |_   _|| |_   ___  | _ )(_) __ _  / __| __  _ _  __ _  _ __  ___  _ _ 
#                                          | |  | ' \ / -_) | _ \| |/ _` | \__ \/ _|| '_|/ _` || '_ \/ -_)| '_|
#                                          |_|  |_||_|\___| |___/|_|\__, | |___/\__||_|  \__,_|| .__/\___||_|  
#                                                                   |___/                      |_|   
#
##############################################################################################################################################################
#                          _                         ______              _         _                  _______               _         _ 
#                     _   | |                       (_____ \            | |       (_)                (_______)             (_)       (_)
#     _____  _   _  _| |_ | |__    ___    ____  _    _____) )  ___    __| |  ____  _   ____   ___     _  _  _  _____   ___  _  ____   _ 
#    (____ || | | |(_   _)|  _ \  / _ \  / ___)(_)  |  __  /  / _ \  / _  | / ___)| | / _  | / _ \   | ||_|| |(____ | /___)| ||  _ \ | |
#    / ___ || |_| |  | |_ | | | || |_| || |     _   | |  \ \ | |_| |( (_| || |    | |( (_| || |_| |  | |   | |/ ___ ||___ || || | | || |
#    \_____||____/    \__)|_| |_| \___/ |_|    (_)  |_|   |_| \___/  \____||_|    |_| \___ | \___/   |_|   |_|\_____|(___/ |_||_| |_||_|
#                                                                                    (_____|                                            
###############################################################################################################################################################
#
# Last updated in: 8/15/2024
#
###############################################################################################################################################################

# ------------------------------------------------------------------------------
# IMPORTS
# ------------------------------------------------------------------------------

import os
import subprocess
from typing import Tuple

import gradio as gr
from dotenv import load_dotenv
from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
from langchain_community.llms import HuggingFaceEndpoint
from scrapegraphai.graphs import SmartScraperGraph
from scrapegraphai.utils import prettify_exec_info

from bs4 import BeautifulSoup as Soup
from langchain_community.document_loaders import (AsyncHtmlLoader,
                                               NewsURLLoader, PubMedLoader,
                                               PlaywrightURLLoader,
                                               RecursiveUrlLoader,
                                               SeleniumURLLoader,
                                               UnstructuredURLLoader,
                                               WebBaseLoader)


# ------------------------------------------------------------------------------
# DEV ENVIRONMENT SETUP
# ------------------------------------------------------------------------------

# Load environment variables
HUGGINGFACEHUB_API_TOKEN = os.getenv('HUGGINGFACEHUB_API_TOKEN')

# Initialize the model instances
repo_id = "mistralai/Mistral-7B-Instruct-v0.2"
llm_model_instance = HuggingFaceEndpoint(
    repo_id=repo_id, max_length=8192, temperature=0.5, token=HUGGINGFACEHUB_API_TOKEN
)

embedder_model_instance = HuggingFaceInferenceAPIEmbeddings(
    api_key=HUGGINGFACEHUB_API_TOKEN, model_name="sentence-transformers/all-MiniLM-l6-v2"
)

graph_config = {
    "llm": {"model_instance": llm_model_instance},
    "embeddings": {"model_instance": embedder_model_instance}
}

# ------------------------------------------------------------------------------
# THE BIG SCRAPER
# ------------------------------------------------------------------------------

def extractDataFromUrls(urls: str, loader_type: str) -> Tuple[list, list]:
    """Extracts data from provided URLs using specified loader type.

    Args:
        urls (str): Comma-separated URLs to extract data from.
        loader_type (str): Type of loader to use for data extraction.

    Returns:
        tuple: A tuple containing the extracted data in JSON format and as a list of Document objects.
               Returns error messages if an exception occurs.
    """
    try:
        urls = urls.split(',')
        data = []

        if loader_type == 'AsyncHtmlLoader':
            loader = AsyncHtmlLoader(urls)
        elif loader_type == 'UnstructuredURL':
            loader = UnstructuredURLLoader(urls=urls)
        elif loader_type == 'RecursiveURL':
            loader = RecursiveUrlLoader(
                url=urls[0], max_depth=2, extractor=lambda x: Soup(x, "html.parser").text
            )
        elif loader_type == 'SeleniumURL':
            loader = SeleniumURLLoader(urls=urls)
        elif loader_type == 'SeleniumURLH':
            loader = SeleniumURLLoader(urls=urls, headless=False)
        elif loader_type == 'PlaywrightURL':
            loader = PlaywrightURLLoader(urls=urls)
        elif loader_type == 'PubMed':
            loader = PubMedLoader(urls[0])
        elif loader_type == 'NewsURL':
            loader = NewsURLLoader(urls)
        elif loader_type == 'WebBaseLoader':
            loader = WebBaseLoader(urls)
        else:
            return "Not Implemented. Development in Progress", "Work In Progress"

        data = loader.load()
        jsonData = []
        for item in data:
            jsonData.append(item.to_json())

        return jsonData, data

    except Exception as err:
        return "An Error Occurred. Contact Developer" + str(err), "Error Occured. Boom" 


def scrapeAndSummarize(prompt: str, source: str) -> Tuple[dict, str]:
    """Scrapes website content based on the prompt and summarizes it.

    Args:
        prompt (str): The prompt to guide the scraping process.
        source (str): The URL of the website to scrape.

    Returns:
        tuple: A tuple containing the scraped data as a dictionary and the execution information.
    """
    smart_scraper_graph = SmartScraperGraph(
        prompt=prompt,
        source=source,
        config=graph_config
    )
    result = smart_scraper_graph.run()
    exec_info = smart_scraper_graph.get_execution_info()
    return result, prettify_exec_info(exec_info)

# ------------------------------------------------------------------------------
# TABBED GRADIO UI
# ------------------------------------------------------------------------------

# Define choices for the dropdown menu
choices = [
    'AsyncHtmlLoader', 'UnstructuredURL', 'RecursiveURL', 'PubMed',
    'WebBaseLoader', 'Scrapy', 'PySpider', 'Beautiful Soup',
    'SeleniumURL', 'SeleniumURLH', 'PlaywrightURL', 'NewsURL',
]

# Create the Gradio interface with tabs
with gr.Blocks() as demo:
    gr.Markdown("# Web Scraping and Summarization")

    with gr.Tabs():
        # Tab 1: Data Extraction
        with gr.TabItem("Data Extraction"):
            gr.Markdown("## Extract data from URLs using various loaders")
            with gr.Row():
                url_input = gr.Textbox(label="Enter your comma separated URLs here")
                loader_dropdown = gr.Dropdown(choices=choices, label="Pick your Loader from here")
            extract_button = gr.Button("Extract Data")
            with gr.Row():
                extracted_data_json = gr.JSON(label="Extracted Data (JSON)")
                extracted_data_text = gr.Textbox(label="Extracted Data (Text)")
            extract_button.click(
                extractDataFromUrls,
                inputs=[url_input, loader_dropdown],
                outputs=[extracted_data_json, extracted_data_text]
            )

        # Tab 2: Website Scraping and Summarization
        with gr.TabItem("Website Scraping & Summarization"):
            gr.Markdown("# Scrape websites, no-code version")
            gr.Markdown("""Easily scrape and summarize web content using advanced AI models on the Hugging Face Hub without writing any code. Input your desired prompt and source URL to get started.
                        This is a no-code version of the excellent lib [ScrapeGraphAI](https://github.com/VinciGit00/Scrapegraph-ai).
                        It's a basic demo and a work in progress. Please contribute to it to make it more useful!""")
            with gr.Row():
                with gr.Column():
                    model_dropdown = gr.Textbox(label="Model", value="Mistral-7B-Instruct-v0.2")
                    prompt_input = gr.Textbox(label="Prompt", value="List me all the press releases with their headlines and urls.")
                    source_input = gr.Textbox(label="Source URL", value="https://www.whitehouse.gov/")
                    scrape_button = gr.Button("Scrape and Summarize")
                with gr.Column():
                    result_output = gr.JSON(label="Result")
                    exec_info_output = gr.Textbox(label="Execution Info")

            scrape_button.click(
                scrapeAndSummarize,
                inputs=[prompt_input, source_input],
                outputs=[result_output, exec_info_output]
            )

# Launch the Gradio interface
demo.launch()