Downloading segmented video from vimeo

vimeo-download.py

import requests
import base64
from tqdm import tqdm


master_json_url = 'https://178skyfiregce-a.akamaihd.net/exp=1474107106~acl=%2F142089577%2F%2A~hmac=0d9becc441fc5385462d53bf59cf019c0184690862f49b414e9a2f1c5bafbe0d/142089577/video/426274424,426274425,426274423,426274422/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)
video = content['video'][idx]
video_base_url = base_url + video['base_url']
print 'base url:', video_base_url

filename = 'video_%d.mp4' % video['id']
print 'saving to %s' % filename

video_file = open(filename, 'wb')

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

for segment in tqdm(video['segments']):
    segment_url = video_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()

This re-encodes the video - is there a way to avoid doing that?

see my previous comment

https://gist.github.com/alexeygrigorev/a1bc540925054b71e1a7268e50ad55cd?permalink_comment_id=5112477#gistcomment-5112477

so I skidded modifications from comments and added a bit of multi threading. It downloads video and audio, accepts playlist.json and master.json (mainly for playlist.json).

import os
import sys
import base64
import requests
import subprocess
from concurrent.futures import ThreadPoolExecutor

from tqdm import tqdm
from moviepy.editor import *
import ffmpeg


url = input('enter [master|playlist].json url: ')
name = input('enter output name: ')

if 'master.json' in url:
    url = url[:url.find('?')] + '?query_string_ranges=1'
    url = url.replace('master.json', 'master.mpd')
    print(url)
    subprocess.run(['youtube-dl', url, '-o', name])
    sys.exit(0)


def download_segment(segment_url, segment_path):
    resp = requests.get(segment_url, stream=True)
    if resp.status_code != 200:
        print('not 200!')
        print(segment_url)
        return
    with open(segment_path, 'wb') as segment_file:
        for chunk in resp:
            segment_file.write(chunk)

def download(what, to, base):
    print('saving', what['mime_type'], 'to', to)
    init_segment = base64.b64decode(what['init_segment'])
    
    segment_urls = [base + segment['url'] for segment in what['segments']]
    segment_paths = [f"segment_{i}.tmp" for i in range(len(segment_urls))]

    with ThreadPoolExecutor(max_workers=15) as executor:
        list(tqdm(executor.map(download_segment, segment_urls, segment_paths), total=len(segment_urls)))

    with open(to, 'wb') as file:
        file.write(init_segment)
        for segment_path in segment_paths:
            with open(segment_path, 'rb') as segment_file:
                file.write(segment_file.read())
            os.remove(segment_path)
    
    print('done')


name += '.mp4'
base_url = url[:url.rfind('/', 0, -26) + 1]
content = requests.get(url).json()

vid_heights = [(i, d['height']) for (i, d) in enumerate(content['video'])]
vid_idx, _ = max(vid_heights, key=lambda _h: _h[1])

audio_quality = [(i, d['bitrate']) for (i, d) in enumerate(content['audio'])]
audio_idx, _ = max(audio_quality, key=lambda _h: _h[1])

video = content['video'][vid_idx]
audio = content['audio'][audio_idx]
base_url = base_url + content['base_url']

video_tmp_file = 'video.mp4'
audio_tmp_file = 'audio.mp4'

download(video, video_tmp_file, base_url + video['base_url'])
download(audio, audio_tmp_file, base_url + audio['base_url'])

def combine_video_audio(video_file, audio_file, output_file):
    try:
        video_stream = ffmpeg.input(video_file)
        audio_stream = ffmpeg.input(audio_file)
        
        ffmpeg.output(video_stream, audio_stream, output_file, vcodec='copy', acodec='copy').run(overwrite_output=True)
        
        print(f"Archivo combinado guardado como {output_file}")
    except ffmpeg.Error as e:
        print(f"Error al combinar archivos: {e.stderr.decode()}")

combine_video_audio('video.mp4', 'audio.mp4', name)

os.remove(video_tmp_file)
os.remove(audio_tmp_file)