from youtube_transcript_api import YouTubeTranscriptApi as yta
import gradio as gr
from deep_translator import GoogleTranslator

opts = ['afrikaans', 'albanian', 'amharic', 'arabic', 'armenian', 'azerbaijani', 'basque', 'belarusian', 'bengali', 'bosnian', 'bulgarian', 'catalan', 'cebuano', 'chichewa', 'chinese (simplified)', 'chinese (traditional)', 'corsican', 'croatian', 'czech', 'danish', 'dutch', 'english', 'esperanto', 'estonian', 'filipino', 'finnish', 'french', 'frisian', 'galician', 'georgian', 'german', 'greek', 'gujarati', 'haitian creole', 'hausa', 'hawaiian', 'hebrew', 'hebrew', 'hindi', 'hmong', 'hungarian', 'icelandic', 'igbo', 'indonesian', 'irish', 'italian', 'japanese', 'javanese', 'kannada', 'kazakh', 'khmer', 'korean', 'kurdish (kurmanji)', 'kyrgyz', 'lao', 'latin', 'latvian', 'lithuanian', 'luxembourgish', 'macedonian', 'malagasy', 'malay', 'malayalam', 'maltese', 'maori', 'marathi', 'mongolian', 'myanmar (burmese)', 'nepali', 'norwegian', 'odia', 'pashto', 'persian', 'polish', 'portuguese', 'punjabi', 'romanian', 'russian', 'samoan', 'scots gaelic', 'serbian', 'sesotho', 'shona', 'sindhi', 'sinhala', 'slovak', 'slovenian', 'somali', 'spanish', 'sundanese', 'swahili', 'swedish', 'tajik', 'tamil', 'telugu', 'thai', 'turkish', 'ukrainian', 'urdu', 'uyghur', 'uzbek', 'vietnamese', 'welsh', 'xhosa', 'yiddish', 'yoruba', 'zulu']
def transcript_generator(link,option):

  yt_link = str(link)
  yt_id = yt_link.partition("=")[2]

  data = yta.get_transcript(yt_id)

  transcript = ''
  for value in data:
    for key,val in value.items():
      if key == 'text':
        transcript += val

  translation = GoogleTranslator(source='auto', target=option).translate(transcript)
  
  return transcript,translation

css = """
footer {display:none !important}
.output-markdown{display:none !important}
footer {visibility: hidden} 
#component-4 textarea[data-testid="textbox"] { height: 178px !important}
#component-7 textarea[data-testid="textbox"] { height: 178px !important}
.max-h-[30rem] {max-height: 18rem !important;}
.hover\:bg-orange-50:hover {
    --tw-bg-opacity: 1 !important;
    background-color: rgb(229,225,255) !important;
}
.gr-button-lg {
    z-index: 14;
    width: 113px;
    height: 30px;
    left: 0px;
    top: 0px;
    padding: 0px;
    cursor: pointer !important; 
    background: none rgb(17, 20, 45) !important;
    border: none !important;
    text-align: center !important;
    font-size: 14px !important;
    font-weight: 500 !important;
    color: rgb(255, 255, 255) !important;
    line-height: 1 !important;
    border-radius: 6px !important;
    transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
    box-shadow: none !important;
}
.gr-button-lg:hover{
    z-index: 14;
    width: 113px;
    height: 30px;
    left: 0px;
    top: 0px;
    padding: 0px;
    cursor: pointer !important; 
    background: none rgb(66, 133, 244) !important;
    border: none !important;
    text-align: center !important;
    font-size: 14px !important;
    font-weight: 500 !important;
    color: rgb(255, 255, 255) !important;
    line-height: 1 !important;
    border-radius: 6px !important;
    transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
    box-shadow: rgb(0 0 0 / 23%) 0px 1px 7px 0px !important;
}
"""

with gr.Blocks(title="YouTube Dialogue Transcriber | Data Science Dojo", css = css) as demo:


    input1 = gr.Textbox(label="Enter YouTube Link",value='',lines=1)
    input2 = gr.Dropdown(label="Select Transcript Translation Language", choices=opts)
    with gr.Tab("Transcript"):
      output1 = gr.Textbox(label="Transcript",lines=10)
    with gr.Tab("Translated Transcript"):
      output2 = gr.Textbox(label="Translation",lines=10)
    btn = gr.Button(value="Submit")
    btn.click(transcript_generator, inputs=[input1,input2], outputs=[output1,output2])
    
    gr.Examples(
        [["https://www.youtube.com/watch?v=47dtFZ8CFo8",'chinese (simplified)'], ["https://www.youtube.com/watch?v=hT_nvWreIhg",'french'],['https://www.youtube.com/watch?v=PMs76lrqiA4','urdu']],
        fn = transcript_generator,
        inputs = [input1,input2],
        outputs = [output1,output2],
        cache_examples = True,
    )
if __name__ == "__main__":
    demo.launch()