from langchain_community.document_loaders import WebBaseLoader
from langchain.prompts import ChatPromptTemplate
from langchain.output_parsers import ResponseSchema
from langchain.output_parsers import StructuredOutputParser
from langchain_core.output_parsers import StrOutputParser
from scrap_post import scrappost
import requests



def is_shortened_url(url):                                  # It is checking whether it is a shorten url or regular website url 
    try:
        response = requests.head(url, allow_redirects=True)
        final_url = response.url
        if final_url != url:
            return True
        return False
    except requests.exceptions.RequestException as e:
        print("Error:", e)
        return False

def expand_short_url(short_url):                      # It is converting shorten url to regular url 
    try:
        response = requests.head(short_url, allow_redirects=True)
        if response.status_code == 200:
            return response.url
        else:
            print("Error: Short URL couldn't be expanded.")
            return None
    except requests.exceptions.RequestException as e:
        print("Error:", e)
        return None

def get_original_url(url):
    if is_shortened_url(url):
        return expand_short_url(url)
    else:
        return url




# Below function extract the post only content from complete web page content and parraphrase the extracted post 
    
def paraphrased_post(url,model):

    post=scrappost(url)

    template="""You are a helpful paraphraser tool. You are provided with a content and your task is to paraphrase it.
                {data}"""

    prompt = ChatPromptTemplate.from_template(template)

    chain = prompt | model | StrOutputParser()
    phrased_post=chain.invoke({"data":post})

    data2=extract_data(phrased_post , model)
    keywords=data2['Keywords'][:3]
    take_aways=data2['Take Aways'][:3]
    highlights=data2['Highlights'][:3]
    return phrased_post,keywords , take_aways, highlights
    




# Below function extract the details such as keywords  , Take aways , highlights and questions 
def extract_data(post_data ,model):
    keywords = ResponseSchema(name="Keywords",
                        description="These are the keywords extracted from LinkedIn post",type="list")

    Take_aways = ResponseSchema(name="Take Aways",
                                description="These are the take aways extracted from LinkedIn post", type= "list")
    Highlights=ResponseSchema(name="Highlights",
                                description="These are the highlights extracted from LinkedIn post", type= "list")
    
    
    response_schema = [
        keywords,
        Take_aways,
        Highlights

    ]
    output_parser = StructuredOutputParser.from_response_schemas(response_schema)
    format_instructions = output_parser.get_format_instructions()

    template = """
        You are a helpful keywords , take aways and highlights extractor from the post of LinkedIn Bot. Your task is to extract relevant keywords , take aways and highlights in descending order of their scores in a list, means high relevant should  be on the top .
        From the following text message, extract the following information:

        text message: {content}
        {format_instructions}
        """
    
    prompt_template = ChatPromptTemplate.from_template(template)
    messages = prompt_template.format_messages(content=post_data, format_instructions=format_instructions)
    response = model(messages)
    output_dict=  output_parser.parse(response.content)
    return  output_dict