Downloading segmented video from vimeo

vimeo-download.py

#!/usr/bin/env python3

import subprocess
import sys
from pathlib import Path

import requests
import base64
from tqdm import tqdm


def execute(cmd):
    popen = subprocess.Popen(cmd,
                             stdout=subprocess.PIPE,
                             stderr=subprocess.STDOUT,  # redirect stderr to stdout
                             universal_newlines=True)

    for stdout_line in iter(popen.stdout.readline, ""):
        yield stdout_line

    popen.stdout.close()
    return_code = popen.wait()

    if return_code:
        raise subprocess.CalledProcessError(return_code, cmd)


if __name__ == '__main__':

    master_json_url = sys.argv[1]
    ffmpeg_video_audio_path_mp4 = sys.argv[2]
    # master_json_url = 'https://31vod-adaptive.akamaized.net/exp=1701029749~acl=%2F201c3bca-a4f7-459a-bf25-ae5cc875ac66%2F%2A~hmac=0fb553666be653b92f01fb63e0e8fe60c8ce4c2f60086b9c5651405450a631ec/201c3bca-a4f7-459a-bf25-ae5cc875ac66/sep/video/289fc95d,3bf78ab1,3e6ffd1a,88ea7314,a864b8ef/master.json?base64_init=1'
    base_url = master_json_url[:master_json_url.rfind('/', 0, -26) + 1]

    resp = requests.get(master_json_url)
    content = resp.json()

    heights = [(i, d['height']) for (i, d) in enumerate(content['video'])]
    idx, _ = max(heights, key=lambda __h: __h[1])
    video = content['video'][idx]
    audio_base_url = base_url + video['base_url']
    print('base url:', audio_base_url)

    video_fname = f'{video["id"]}_video.mp4'
    print(f'saving to {video_fname}')

    video_path = Path(video_fname)

    if not video_path.exists():

        video_file = open(video_fname, 'wb')

        init_segment = base64.b64decode(video['init_segment'])
        video_file.write(init_segment)

        for segment in tqdm(video['segments']):
            segment_url = audio_base_url + segment['url']
            resp = requests.get(segment_url, stream=True)
            if resp.status_code != 200:
                print('not 200!')
                print(resp)
                print(segment_url)
                break
            for chunk in resp:
                video_file.write(chunk)

        video_file.flush()
        video_file.close()
        print(f'Wrote {video_path.absolute()}')
    else:
        print(f'File already exists {video_fname}!')

    audio_path = None

    if content['audio']:
        audio = content['audio'][0]  ## AUDIO QUALITY <<<<< take 1st ??????
        audio_fname = f'{video["id"]}_audio.m4a'

        audio_path = Path(audio_fname)
        if not audio_path.exists():

            audio_base_url = base_url + audio['base_url']
            print('base url:', audio_base_url)

            print(f'saving to {audio_fname}')

            audio_file = open(audio_fname, 'wb')

            init_segment = base64.b64decode(audio['init_segment'])
            audio_file.write(init_segment)

            for segment in tqdm(audio['segments']):
                segment_url = audio_base_url + segment['url']
                resp = requests.get(segment_url, stream=True)
                if resp.status_code != 200:
                    print('not 200!')
                    print(resp)
                    print(segment_url)
                    break
                for chunk in resp:
                    audio_file.write(chunk)

            audio_file.flush()
            audio_file.close()
        else:
            print(f'file already exists [{audio_fname}]')

        if audio_path.exists():

            for output in execute(['ffmpeg',
                                      '-i', video_fname,
                                      '-i', audio_fname,
                                      '-codec', 'copy', ffmpeg_video_audio_path_mp4]):
                print(output)

        video_path.unlink()
        audio_path.unlink()
        print(f'Wrote merged video+audio: {ffmpeg_video_audio_path_mp4}')
    else:
        video_path.rename(ffmpeg_video_audio_path_mp4)
        print(f'Wrote video: {ffmpeg_video_audio_path_mp4}')