Make transcripts from YouTube captions

transcripts_from_yt.py

"""
MIT License

Copyright (c) 2019 Zev Averbach

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

This product includes youtube_transcript_api developed by Jonas Depoix, Copyright (c) 2018 Jonas Depoix

"""

import json
from typing import List, Optional, Dict, Union

from youtube_transcript_api import YouTubeTranscriptApi

from google_sheets import Sheet


PARAGRAPH_MAX_CHARS = 400
TRANSCRIPT_IN_GOOGLE_SHEETS_RATE_LIMIT_NUM_CHARS = 1_000
TRANSCRIPT_IN_GOOGLE_SHEETS_MAX_CHARS_PER_CELL = 50_000


def get_json_transcript(video_id: str) -> dict:
    return YouTubeTranscriptApi.get_transcript(video_id)


def make_paragraphs(transcript_json: dict) -> List[str]:
    paragraphs = []
    paragraph = ""
    for snip in transcript_json:
        if paragraph == "":
            space = ""
        else:
            space = " "
        paragraph += f'{space}{snip["text"]}'
        if len(paragraph) > PARAGRAPH_MAX_CHARS:
            paragraphs.append(paragraph)
            paragraph = ""
    return paragraphs


def get_transcript_paragraphs(video_id: str) -> List[str]:
    return make_paragraphs(get_json_transcript(video_id))


def write_json(video_id: str, json_text: List[Dict[Union[str, float]]]):
    json.dump(json_text, open(f"{video_id}.json", "w"), indent=4)


def write_paragraphs_to_file(video_id: str, paragraphs: List[str]):
    with open(f"{video_id}.txt", "w") as fout:
        fout.write("\n\n".join(paragraphs))