def video(self, url, download_folder, logs):
logs_file = open(logs, 'a')
x = re.search('list=', url)
if x is not None:
playList = Playlist(url)
if playList is None:
playList._video_regex = re.compile(
r"\"url\":\"(/watch\?v=[\w-]*)")
for playlists_url in playList:
try:
print('Downloading...' + playlists_url)
playList.download_all(download_folder)
except Exception as ex:
logs_file.write('Unable to download: ' + playlists_url +
'\t' + str(ex) + '\n')
pass
else:
try:
print('Downloading...' + url)
self.__download_file(url, download_folder, False)
except Exception as ex:
logs_file.write('Unable to download: ' + url + '\t' + str(ex))
logs_file.close()
def option1():
w = 0
while (w == 0):
pl = input("Ingrese Url playlist completa:")
try:
playlist = Playlist(pl)
playlist._video_regex = compile(r"\"url\":\"(/watch\?v=[\w-]*)")
w = 1
except:
print(
"Url ingresada de manera incorrecta, por favor vuelva a intentarlo"
)
w = 0
print("Numero de videos añadidos:", len(playlist.video_urls))
urls = []
for url in playlist.video_urls:
urls.append((url + "\n"))
lista = open("video-list.txt", "w+")
lista.writelines(urls)
lista.close()
def doDownload(self):
playlistUrl = self.getPlaylistUrlFromClipboard()
if playlistUrl == None:
self.displayError('Playlist URL not in clipboard. Program closed.')
return
playlist = None
try:
playlist = Playlist(playlistUrl)
playlist._video_regex = re.compile(r"\"url\":\"(/watch\?v=[\w-]*)")
except KeyError as e:
self.displayError('Playlist URL not in clipboard. Program closed.')
return
except http.client.InvalidURL as e:
self.displayError(str(e))
return
playlistTitle = playlist.title()
if 'Oops' in playlistTitle:
self.displayError(
'The URL obtained from clipboard is not pointing to a playlist. Program closed.'
)
return
playlistName, timeInfo = self.splitPlayListTitle(playlistTitle)
targetAudioDir = AUDIO_DIR + DIR_SEP + playlistName
if not os.path.isdir(targetAudioDir):
targetAudioDirList = targetAudioDir.split(DIR_SEP)
targetAudioDirShort = DIR_SEP.join(targetAudioDirList[-2:])
if self.getConfirmation(
"Directory\n{}\nwill be created.\n\nContinue with download ?"
.format(targetAudioDirShort)) != 'yes':
return
os.makedirs(targetAudioDir)
for video in playlist.videos:
audioStream = video.streams.get_by_itag(YOUTUBE_STREAM_AUDIO)
videoTitle = video.title
self.msgText = self.msgText + 'downloading ' + videoTitle + '\n'
self.msg.configure(text=self.msgText)
self.root.update()
audioStream.download(output_path=targetAudioDir)
for file in [
n for n in os.listdir(targetAudioDir) if re.search('mp4', n)
]:
mp4FilePathName = os.path.join(targetAudioDir, file)
mp3FilePathName = os.path.join(targetAudioDir,
os.path.splitext(file)[0] + '.mp3')
if timeInfo:
timeStartSec, timeEndSec = self.splitTimeInfo(timeInfo)
import moviepy.editor as mp # not working on Android
clip = mp.AudioFileClip(mp4FilePathName).subclip(
timeStartSec,
timeEndSec) # disable if do not want any clipping
clip.write_audiofile(mp3FilePathName)
clip.close()
os.remove(mp4FilePathName)
else:
if os.path.isfile(mp3FilePathName):
os.remove(mp3FilePathName)
os.rename(mp4FilePathName, mp3FilePathName)
def __init__(self, playlist_url='', skip=False):
if not skip:
playlist = Playlist(playlist_url)
playlist._video_regex = re.compile(r"\"url\":\"(/watch\?v=[\w-]*)")
self.urls = playlist.video_urls
logging.info(f"[+] Number of tracks: {len(self.urls)}")
if dlType == "1":
videoFile = VideoFileClip(path)
videoFile.audio.write_audiofile(FOLDER + "/" + video.title +
".mp3")
videoFile.close()
os.remove(path)
print("Downloaded " + video.title)
print("\nSuccessfully downloaded YouTube video: " + video.title)
elif choice == "2":
playlist = Playlist(
input("\nPlease input the YouTube playlist link\n"))
playlist._video_regex = re.compile(
r"\"url\":\"(/watch\?v=[\w-]*)") # Fixes empty playlist
dlType = ""
while dlType != "1" and dlType != "2":
dlType = input(
"\nInsert\n- '1' to download only audio\n- '2' to download the full video\n"
)
print("\nDownloading...")
for video in playlist.videos:
try:
path = video.streams.first().download(output_path=FOLDER)
if dlType == "1":
videoFile = VideoFileClip(path)
videoFile.audio.write_audiofile(FOLDER + "/" +
from pytube import Playlist, YouTube
from termcolor import colored
from tqdm import tqdm
import re
print(colored("Please give us the link of the playlist:", 'yellow'), end=" ")
urlOfPlayList = input()
videosOfPlaylist = Playlist(urlOfPlayList)
videosOfPlaylist._video_regex = re.compile(r"\"url\":\"(/watch\?v=[\w-]*)")
videosUrls = videosOfPlaylist.video_urls
print(colored(
"If you want the hight resolution or the lowerst resolution:(l/h)[l]",
'yellow'),
end=' ')
chose = input()
k = 0
loop = tqdm(total=len(videosUrls), position=0, leave=True)
for url in videosUrls:
while True:
try:
if chose == "h":
YouTube(url).streams.filter(
type="video").get_highest_resolution().download()
else:
YouTube(url).streams.filter(
type="video").get_lowest_resolution().download()
loop.set_description("Downloading".format(k))
def __download__playlist(self, playlist_url):
playlist = Playlist(playlist_url)
playlist._video_regex = re.compile(r"\"url\":\"(/watch\?v=[\w-]*)")
for url in playlist.video_urls:
self.__download__(url)
while True:
print("\n" + "Output Format" + "\n" + "===================" + "\n" +
"1) mp4" + "\n" + "2) mp3" + "\n" + "\n")
a = input("Choice --> ")
if a == "1":
url = input("Url --> ")
if "&list=" not in url:
p1 = Process(target=mp4)
p1.start()
p2 = Process(target=vbar(0.0000001))
p2.start()
p1.join()
p2.join()
if "&list=" in url:
name1 = Playlist(url)
name1._video_regex = re.compile(
r"\"url\":\"(/watch\?v=[\w-]*)")
try:
print((name1.title()))
except:
pass
print("Total videos " + str(len(name1.video_urls)) + "\n")
print("Start Progressing...")
for url in name1.video_urls:
name2 = YouTube(url)
print(name2.title)
p1 = Process(target=mp4)
p1.start()
p2 = Process(target=vbar(1))
p2.start()
p1.join()
p2.join()
def create_youtube_playlist(self):
play_list = Playlist(self.url)
play_list._video_regex = re.compile(r"\"url\":\"(/watch\?v=[\w-]*)")
return play_list
def downloadplaylist(url, path_to_save, what, ask, wait, START):
"""Downlaods the sound of the videos in a playlist
Args:
url (string): the URL with the word list in it
"""
try:
playlist = Playlist(url)
except:
print("Not a valid list URL and/or no list/videos found")
sys.exit()
# this fixes the empty playlist.videos list
playlist._video_regex = re.compile(r"\"url\":\"(/watch\?v=[\w-]*)")
STOP = 9990
#test purposes
for n, video in enumerate(playlist.videos):
if n >= START and n < STOP:
try:
mp4 = cleanup(video.title) + ".mp4"
if ask:
dl_yes = input(
f"Download {n+1}/{len(playlist.video_urls)} - {video.title} ? (y/n/q) "
)
else:
dl_yes = "y"
if dl_yes == "y" or dl_yes == "Y":
print(
f"Downloading {n+1}/{len(playlist.video_urls)} - {video.title}"
)
if what == "audio":
#video.streams.first().download(filename=mp4) # for music
video.streams.get_by_itag(140).download(filename=mp4)
new_filename = path_to_save + left(
mp4, (len(mp4) - 4)
) + "mp4.mp4" # for some reason files are saved as namemp4.mp4
#convert_to_mp3(new_filename)
elif what == "video":
video.streams.get_by_itag(18).download(
filename=mp4) # for video 360p
if wait:
wait_time = randint(10, 30)
countdown(wait_time)
elif dl_yes == "q" or dl_yes == "Q":
sys.exit()
except SystemExit:
print()
print("Thank you for using this script.")
sys.exit()
except:
print(
f"ERROR Downloading or finding the name of {n+1}/{len(playlist.video_urls)} "
)
# some videos give 403 error
# too lazy to implement this (yet)
# https://github.com/pytube/pytube/issues/399
main_convert(path_to_save)
def main():
# list of podcast video ids already present in the raw data archive
processed_podcasts = get_processed_podcasts()
# playlist to download the podcasts from
playlist_link = "https://www.youtube.com/watch?v=c9AbECvRt20&list=PLrAXtmErZgOdP_8GztsuKi9nrraNbKKp4"
playlist = Playlist(playlist_link)
# this fixes the empty playlist.videos list
playlist._video_regex = re.compile(r"\"url\":\"(/watch\?v=[\w-]*)")
print('Total number of podcasts in the playlist: ',
str(len(playlist.video_urls)))
limit = 0 # counter used to limit number of files to be downloaded
for video in playlist.videos:
# download no more than these many podcasts
if (limit == 80):
break
# ignore podcasts that are already loaded to the raw data archive
if (video.video_id in processed_podcasts):
limit = limit + 1
continue
# ignore podcasts without segment information by timestamps
if (video.description == ""):
limit = limit + 1
continue
# extract metadata for this podcast
metadata = {}
metadata['video_id'] = video.video_id
metadata['title'] = re.sub('[^a-zA-Z0-9 \n\.]', '_', video.title)
metadata['description'] = video.description
metadata['rating'] = video.rating
metadata['length'] = video.length
metadata['views'] = video.views
metadata['author'] = video.author
aware_local_now = datetime.now(timezone.utc).astimezone()
metadata['downloaded_at'] = str(aware_local_now)
# create directory for this podcast
download_dir = 'podcast_' + metadata['video_id']
os.makedirs(download_dir, exist_ok=True)
# open a new text file to write metadata for this podcast
with open(os.path.join(download_dir, metadata['title'] + '.txt'),
'w+') as f:
# append metadata to text file
f.write(str(metadata) + '\n')
# start audio mp4 download stream for this podcast
ys = video.streams.filter(only_audio=True, file_extension='mp4')
print('Downloading : ', metadata['title'])
ys[0].download(filename=metadata['title'])
# to ensure mp4 is fully downloaded before further processing
time.sleep(2)
'''
convert downloaded mp4 to wav file
RIFF (little-endian) data, WAVE audio, Microsoft PCM, 16 bit, mono 16000 Hz
and save in the directory created for this podcast
'''
subprocess.call(['ffmpeg', \
'-i', metadata['title']+'.mp4', '-acodec', 'pcm_s16le', '-ac', '1', '-ar', '16000', \
os.path.join(download_dir, metadata['title']+'.wav')])
# delete raw mp4 file
delete_file_from_path(metadata['title'] + '.mp4')
limit = limit + 1