Vimeo downloader with tweaks

vimeo_download.py

#!/bin/env python3

import base64
import os
import re
import sys
import tempfile
from urllib.parse import urlparse

import requests
from tqdm import tqdm

def download_video(url, content, base_url, path_split):
    global session

    base_video_url = base_url

    path_offset = content['base_url'].count('../')

    sep_path = path_split[-1].split('/')
    base_sep_url = '/'.join(sep_path[0:len(sep_path) - 1 - path_offset])
    base_video_url += base_sep_url + '/'

    heights = [(i, d['height']) for (i, d) in enumerate(content['video'])]
    idx, _ = max(heights, key=lambda h: h[1])
    video = content['video'][idx]
    video_path = base_video_url + video['base_url']

    filenameVideo = tempfile.NamedTemporaryFile(prefix='video.', suffix='.mp4', dir=cwd, delete=False)
    print ('Saving video to {}'.format(filenameVideo.name))

    with open(filenameVideo.name, 'wb') as video_file:
        init_segment = base64.b64decode(video['init_segment'])
        video_file.write(init_segment)

        for segment in tqdm(video['segments']):
            segment_url = url._replace(path=video_path + segment['url'])
            segment_url = segment_url._replace(query='')

            resp = session.get(segment_url.geturl(), stream=True)
            if resp.status_code != 200:
                print('not 200!')
                print(resp)
                print(segment_url)
                raise ValueError('Video segment could not be downloaded: ' + str(resp.status_code))
            for chunk in resp:
                video_file.write(chunk)

        video_file.flush()

def download_audio(url, content, base_url, path_split):
    global session

    base_audio_url = base_url
    path_offset = content['base_url'].count('../')

    sep_path = path_split[-1].split('/')

    # 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]

    track_offset = audio['base_url'].count('../')
    base_sep_url = '/'.join(sep_path[0:len(sep_path) - 1 - path_offset - track_offset])
    base_audio_url += base_sep_url + '/'

    audio_path = base_audio_url + audio['base_url'].replace('../','')
    print('Audio Base url:', audio_path)

    filenameAudio = tempfile.NamedTemporaryFile(prefix='audio.', suffix='.mp4', dir=cwd, delete=False)
    print('Saving audio to %s' % filenameAudio.name)

    with open(filenameAudio.name, 'wb') as audio_file:
        init_segment = base64.b64decode(audio['init_segment'])
        audio_file.write(init_segment)

        for segment in tqdm(audio['segments']):
            segment_url = url._replace(path=audio_path + segment['url'])
            segment_url = segment_url._replace(query='')

            resp = session.get(segment_url.geturl(), stream=True)
            if resp.status_code != 200:
                print('not 200!')
                print(resp)
                print(segment_url)
                raise ValueError('Audio segment could not be downloaded: ' + str(resp.status_code))

            for chunk in resp:
                audio_file.write(chunk)

        audio_file.flush()

if len(sys.argv) >= 1:
    master_json_url = sys.argv[1]
else:
    print('master.json must be passed as argument', file=sys.stderr)
    exit(1)

cwd = os.getcwd()
base_url = master_json_url[:master_json_url.rfind('/', 0, -26) + 1]
url = urlparse(master_json_url)

session = requests.Session()

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

path_split = url.path.split(f"/{content['clip_id']}/")
base_url = path_split[0] + "/" + content['clip_id'] + "/"

download_video(url, content, base_url, path_split)
download_audio(url, content, base_url, path_split)

print("Done!")