from bs4 import BeautifulSoup
from urllib import request
from bot.web_scrapping.searchable_index import SearchableIndex
from bot.utils.show_log import logger
from bot.utils.constanst import set_api_key
import pandas as pd
import requests
import os

set_api_key(api_key='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')


def save_content_to_file(url=None, text=None, output_folder=None, file_format=None):
    file_path = os.path.join(output_folder, f"combined_content.{file_format}")

    write_functions = {
        'txt': lambda: write_text(file_path, text),
        'pdf': lambda: write_pdf(url, file_path),
        'csv': lambda: write_csv(file_path, text),
        'xml': lambda: write_xml(file_path, text)
    }

    write_function = write_functions.get(file_format)
    if write_function:
        write_function()
        logger.info(f"Content appended to {file_path}")
    else:
        logger.warning("Invalid file format. Supported formats: txt, pdf, csv, xml")

    return file_path


def write_text(file_path, text):
    with open(file_path, "a", encoding="utf-8") as file:
        for t in text:
            file.write(f'{t.text}\n')


def write_pdf(url, file_path):
    request.urlretrieve(url, file_path)


def write_csv(file_path, text):
    df = pd.DataFrame({'Content': [t.text for t in text]})
    df.to_csv(file_path, mode='a', index=False, header=False)


def write_xml(file_path, text):
    xml_content = ''.join([f'<item>{t.text}</item>' for t in text])
    with open(file_path, "a", encoding="utf-8") as file:
        file.write(xml_content)


def content_crawler_and_index(url, llm, prompt, file_format='txt', output_folder='learning_documents'):
    if url == 'NO_URL':
        file_path = output_folder
    else:
        responses = requests.get(url)
        if responses.status_code != 200:
            logger.warning("Failed to retrieve content from the URL.")
            return None
        if not os.path.exists(output_folder):
            os.makedirs(output_folder)
        soup = BeautifulSoup(responses.text, "html.parser")
        text = soup.find_all(['h2', 'p', 'i', 'ul'])
        file_path = save_content_to_file(text=text, url=url, output_folder=output_folder, file_format=file_format)

    index = SearchableIndex.embed_index(url=url, path=file_path, llm=llm, prompt=prompt)
    if url != 'NO_URL' and os.path.isfile(file_path):
        os.remove(file_path)

    return index


if __name__ == '__main__':
    pass
    # Example usage:
    # First URL
    # idx = content_crawler_and_index("https://www.presight.io/terms-of-use.html", file_format='txt')
    #
    # Second URL (appends content to existing files)
    # idx = content_crawler_and_index(url='https://arxiv.org/pdf/2309.11235v1.pdf', file_format='pdf')
    # # example get response chatbot
    # prompt = 'explain the paper'
    # llm = ChatOpenAI(model_name='gpt-3.5-turbo', temperature=0)
    # response = SearchableIndex.query(prompt, llm, idx)
    # print(response)
    # logger.info(response)