utils.py

import json
import re


import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity


########################### Chapter rendering functions ###########################

def get_chapters(paragraphs, table_of_content):

    chapters = []

    for i in range(len(table_of_content)):


        if i < len(table_of_content) - 1:

            chapter = {'num_chapter': i,
                       'title': table_of_content[i]['title'],
                       'start_paragraph_number': table_of_content[i]['start_paragraph_number'],
                       'end_paragraph_number': table_of_content[i + 1]['start_paragraph_number'],
                       'start_time': paragraphs[table_of_content[i]['start_paragraph_number']]['start_time'],
                       'end_time': paragraphs[table_of_content[i + 1]['start_paragraph_number']]['start_time'],
                      }

        else:
            chapter = {'num_chapter': i,
                       'title': table_of_content[i]['title'],
                       'start_paragraph_number': table_of_content[i]['start_paragraph_number'],
                       'end_paragraph_number': len(paragraphs),
                       'start_time': paragraphs[table_of_content[i]['start_paragraph_number']]['start_time'],
                       'end_time': paragraphs[-1]['start_time'],
                      }

        paragraphs_chapter = [paragraphs[j]['paragraph_text'] for j in
                                range(chapter['start_paragraph_number'], chapter['end_paragraph_number'])]

        paragraph_timestamps_chapter = [paragraphs[j]['start_time'] for j in
                                          range(chapter['start_paragraph_number'], chapter['end_paragraph_number'])]

        chapter['paragraphs'] = paragraphs_chapter
        chapter['paragraph_timestamps'] = paragraph_timestamps_chapter

        chapters.append(chapter)

    return chapters

def convert_seconds_to_hms(seconds):
    # Calculate hours, minutes, and remaining seconds
    hours = seconds // 3600
    minutes = (seconds % 3600) // 60
    remaining_seconds = seconds % 60

    # Format the result as HH:MM:SS
    return f"{hours:02}:{minutes:02}:{remaining_seconds:02}"

def toc_to_html(chapters):

    toc_html = "<h1>Video chapters</h1><p>\n"

    for chapter in chapters:
        num_chapter = chapter['num_chapter']
        title = chapter['title']

        from_to = convert_seconds_to_hms(int(chapter['start_time'])) + " - "

        toc_html += f"""{from_to}<a href = "#{num_chapter}" >{num_chapter+1} - {title}</a><br>\n"""

    return toc_html


def section_to_html(section_json_data):
    formatted_section = ""

    paragraphs = section_json_data['paragraphs']
    paragraphs_timestamp_hms = [convert_seconds_to_hms(int(section_json_data['paragraph_timestamps'][i])) for i in range(len(paragraphs))]

    for i, (paragraph, paragraph_timestamp_hms) in enumerate(zip(paragraphs, paragraphs_timestamp_hms)):

        formatted_section += f"""
        <div class="row mb-4">
            <div class="col-md-1">
                {paragraph_timestamp_hms}
            </div>
            <div class="col-md-11">
                <p>{paragraph}</p>
            </div>
        </div>"""

    num_section = section_json_data['num_chapter']

    from_to = "From "+convert_seconds_to_hms(int(section_json_data['start_time'])) + " to " + convert_seconds_to_hms(
        int(section_json_data['end_time']))

    title = f"{section_json_data['title']}"

    title_link = f"""<div class="transcript-title-icon" " id="{num_section}">{num_section+1} - {title}</div>"""

    summary_section = f"""
            <a id="{num_section}"><h2 id="{num_section}">{title_link}</h2></a>
            {from_to}
            <p>
            <div class="summary-section">
                <div class="summary-text" >
                    {formatted_section}
                </div>
            </div>
            """

    return summary_section


def get_result_as_html(chapters, video_id):
    video_embed = f"""
<iframe width="100%" height="400" src="https://www.youtube.com/embed/{video_id}" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
"""

    toc = toc_to_html(chapters)

    edited_transcript = f"""
<h1>Structured transcript</h1>
<p>
"""

    for i in range(len(chapters)):
        chapter_json_data = chapters[i]

        edited_transcript += section_to_html(chapter_json_data)

    result_as_html = f"""
<link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="stylesheet">
<div class="container mt-4">
    <div class="content">
        {video_embed}
    </div>
    <p>
    <div class="content">
        {toc}
    </div>
    <p>
    <div class="content">
        {edited_transcript}
    </div>
</div>"""

    return result_as_html

def get_transcript_as_text(transcript):
    temp_list = [convert_seconds_to_hms(int(s['start']))+' '+s['text'] for s in transcript]
    transcript_as_text = '\n'.join(temp_list)

    return transcript_as_text

def load_transcript(video_id):
    file_name = f"examples/{video_id}_transcript.json"
    with open(file_name, 'r') as file:
        transcript = json.load(file)

    transcript_as_text = get_transcript_as_text(transcript)
    return transcript_as_text

def load_json_chapters(video_id):
    file_name = f"examples/{video_id}.json"
    with open(file_name, 'r') as file:
        chapters = json.load(file)

    return chapters