Vimeo video downloader with Python 3

vimeo-download.py

#!/bin/env python3

import argparse
import base64
import os
import re
import subprocess
import sys
from tempfile import mkstemp

import requests
from tqdm import tqdm

if len(sys.argv) > 1:
    master_json_url = sys.argv[1]
    output_file = sys.argv[2]
else:
    print('master.json must be passed as argument', file=sys.stderr)
    exit(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]
video_base_url = base_url + video['base_url']
print('base url:', video_base_url)

filenameVideo = mkstemp(prefix='.mp4')[1]
print ('saving to {}'.format(filenameVideo))
video_file = open(filenameVideo, '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()

# Audio download here
bitrate = [(i, d['bitrate']) for (i, d) in enumerate(content['audio'])]

print('Bitrate', bitrate)

idx, _ = max(bitrate, key=lambda x: x[1])
audio = content['audio'][idx]
audio_base_url = base_url + audio['base_url']
print('Base url:', audio_base_url)

filenameAudio = mkstemp(prefix='.mp4')[1]
print('Saving AUDIO to %s' % filenameAudio)

audio_file = open(filenameAudio, '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']
    segment_url = re.sub(r'/[a-zA-Z0-9_-]*/\.\./',r'/',segment_url.rstrip())
    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()

print('Combining video and audio...')
cmd = 'ffmpeg -y -i '
cmd += filenameAudio
cmd += ' -i '
cmd += filenameVideo
cmd += ' ' + output_file
subprocess.call(cmd, shell=True)
print('Mixing Done!')

# Delete the remaining single audio and video files
os.remove(filenameAudio)
os.remove(filenameVideo)
print("Temporary files removed!")

print("Done!")

Thank you for script!

Unfortunately I was unable to get video because of /video/ and /audio/ part in master.json url:

...5fa435624613465457624/sep/video/234251241,324535,234254,23452352,53b36b3d/audio/5745456,3245345/master.json

So I've added line

base_url = base_url.split('/video/', 1)[0] + '/video/'

before line 29:

video_base_url = base_url + video['base_url']

And video urls became correct.

UPDATE: mkstemp argument 'prefix' is wrong - it leads to temp files like ''.mp4q3inl_k0".
mkstemp(suffix='.mp4')[1] might be better :)

Also add:

cmd += ' -c:v copy -c:a copy '

after cmd += filenameVideo

to avoid re-encoding

Where can i get master.json url for example for this video https://player.vimeo.com/video/819183591