def main():
pl_url = input("Enter YouTube Playlist URL : ")
pl = Playlist(pl_url)
pl.populate_video_urls()
# or if you want to download in a specific directory
print(pl.video_urls)
first_num = int(input("Enter first NUM : "))
download_path = '.'
for i, target_url in enumerate(pl.video_urls):
while True:
try:
yt = YouTube(target_url)
print(yt.title)
break
except Exception:
time.sleep(1)
print('retry')
continue
comment_data = get_chat(target_url)
prefix = str(i + first_num).zfill(3) + '.'
filename = prefix + re.sub(r'[\\/:*?"<>|]+', '_',
yt.title) + "_chat.json"
json_text = json.dumps(comment_data, ensure_ascii=False)
with open(filename, mode='w', encoding="utf-8") as f:
f.write(json_text)
def main(args):
collection_dir = args[1]
playlist_link = args[2]
quality = args[3]
collection_files = os.listdir(collection_dir)
collection = remove_extensions(collection_files)
playlist = Playlist(playlist_link)
playlist.populate_video_urls()
for link in playlist.video_urls:
try:
video = YouTube(link)
'''remove characters from video title that are not allowed in windows filenames.'''
video_title = video.title.translate(
{ord(c): None
for c in video.title if c in '\\\"/<>?:*|'})
if not is_video_in_collection(collection, video_title):
video_stream = video.streams.filter(progressive=True).first()
video_stream.download()
convert_to_audio(video_stream.default_filename, video_title,
collection_dir, quality)
os.remove(video_stream.default_filename)
except Exception as ex:
print(ex)
def download():
if (videotype.get() == 1):
downloadYouTube(str(urlInput.get()), path.get())
urlInput_label = tk.Label(frame,
text=YouTube(urlInput.get()).title +
" downloaded !",
bg="#041824",
fg="#ffffff",
font=("Courier", 10),
wraplength=400)
urlInput_label.place(y=370, relwidth=1, relheight=0.2)
elif (videotype.get() == 2):
pl = Playlist(urlInput.get())
pl.populate_video_urls()
for link in pl.parse_links():
videolink = 'https://www.youtube.com' + link
downloadYouTube(videolink, path.get())
urlInput_label = tk.Label(frame,
text=YouTube(videolink).title +
" downloaded !",
bg="#041824",
fg="#ffffff",
font=("Courier", 10),
wraplength=400)
urlInput_label.place(y=370, relwidth=1, relheight=0.2)
def download_playlist(url, list_path):
logger.info(f'trying to download youtube playlist {url}')
pl = Playlist(url)
pl.populate_video_urls()
with open(list_path, 'w') as f:
for video_url in pl.video_urls:
f.write(video_url + '\n')
def enter():
if (videotype.get() == 1):
yt1 = YouTube(urlInput.get())
urlInput_label = tk.Label(frame,
text=yt1.title,
bg="#041824",
fg="#ffffff",
font=("Courier", 10),
wraplength=400)
urlInput_label.place(y=240, relwidth=1, relheight=0.2)
urlInput_label = tk.Label(frame,
text=yt1.length + " seconds long",
bg="#041824",
fg="#ffffff",
font=("Courier", 10),
wraplength=400)
urlInput_label.place(y=330, relwidth=1, relheight=0.05)
elif (videotype.get() == 2):
pl = Playlist(urlInput.get())
pl.populate_video_urls()
urlInput_label = tk.Label(frame,
text='Playlist Name: ' + pl.title() + '\n' +
'Number of videos in playlist: ' +
str(len(pl.video_urls)),
bg="#041824",
fg="#ffffff",
font=("Courier", 10),
wraplength=400)
urlInput_label.place(y=260, relwidth=1, relheight=0.2)
def get_urls_from_entry_text(url_entry_text):
urls = []
if 'list' in url_entry_text:
url = construct_playlist_url(url_entry_text)
pl = Playlist(url)
pl.populate_video_urls()
return pl.video_urls
else:
return [url_entry_text]
def get_playlist_info(URL):
playlistInfo = dict()
playlist = Playlist(URL)
playlist.populate_video_urls()
urls = playlist.video_urls
playlistInfo = get_video_details(urls[0])
playlistInfo['title'] = playlist.title
playlistInfo.update({'linkCount': len(playlist.video_urls)})
return playlistInfo
def downloadList(url, maxCount=None, start=None, end=None):
print("download Youtube playlist:%s, maxCount:%s" % (url, str(maxCount)))
# taskCount = cpu_count() -1
# print("we have %d cpus" % (taskCount + 1))
taskCount = DOWNLOAD_TASK_CUNT
pl = Playlist(url)
pl.populate_video_urls()
videoUrls = pl.video_urls
if maxCount:
videoUrls = videoUrls[0:maxCount:1]
elif start and end:
videoUrls = videoUrls[start - 1:end]
elif start and end is None:
videoUrls = videoUrls[start - 1::]
elif start is None and end:
videoUrls = videoUrls[:end:]
prefix_gen = pl._path_num_prefix_generator()
playlistTitle = getPlaylistTitle(pl.construct_playlist_url())
#single thread
# for link in videoUrls:
# prefix = next(prefix_gen)
# print('file prefix is: %s' % prefix)
# downloadSingle(link, filename_prefix=prefix, subFolder=playlistTitle)
# multiple thread
argsArrayList = []
for i in range(0, taskCount):
argsArrayList.append([])
i = 0
for link in videoUrls:
idx = i % taskCount
i += 1
prefix = next(prefix_gen)
argsArrayList[idx].append((link, prefix, playlistTitle))
s_linkStatusDic[link] = False
downloadListMultipleThread(argsArrayList)
times = 1
while hasToDownloadTask():
times += 1
toDownloadFileDic = {
k: v
for k, v in s_linkStatusDic.items() if v == False
}
print("=>try %d times, file to download count: %d" %
(times, len(toDownloadFileDic)))
print(" %s", str(toDownloadFileDic))
downloadListMultipleThread(argsArrayList)
print("all download task done.")
def generate_playlist(url, filename='playlist.csv'):
playlist = Playlist(url)
playlist.populate_video_urls()
with open(filename, 'w') as fp:
wrt = csv.writer(fp)
header = ['url', 'start', 'end']
wrt.writerow(header)
for url in playlist.video_urls:
wrt.writerow([url, '', ''])
return filename
def test_populate():
ob = Playlist(short_test_pl)
expected = [
'https://www.youtube.com/watch?v=m5q2GCsteQs',
'https://www.youtube.com/watch?v=5YK63cXyJ2Q',
'https://www.youtube.com/watch?v=Rzt4rUPFYD4',
]
ob.populate_video_urls()
assert ob.video_urls == expected
def load_playlist_urls(self, playlists):
all_playlist_urls = []
for playlist in playlists:
p = Playlist(playlist)
p.populate_video_urls()
urls = p.video_urls
all_playlist_urls.extend(urls)
return all_playlist_urls
def test_populate():
ob = Playlist(
'https://www.youtube.com/watch?v=m5q2GCsteQs&list='
'PL525f8ds9RvsXDl44X6Wwh9t3fCzFNApw', )
expected = [
'https://www.youtube.com/watch?v=m5q2GCsteQs',
'https://www.youtube.com/watch?v=5YK63cXyJ2Q',
'https://www.youtube.com/watch?v=Rzt4rUPFYD4',
]
ob.populate_video_urls()
assert ob.video_urls == expected
def download_playlist(url, target, codec=None):
from concurrent.futures import ThreadPoolExecutor
pl = Playlist(url)
pl.populate_video_urls()
urls = pl.video_urls
with ThreadPoolExecutor(max_workers=len(urls)) as works:
futures = []
for item in urls:
futures.append(works.submit(download, item, target, codec=codec))
[item.result() for item in futures]
print("All %d jobs Done." % len(urls))
def download_youtube_list(pl_url, folder="."):
pl = Playlist(pl_url)
pl.populate_video_urls()
print "List size is %s:" % len(pl.video_urls)
videos = []
for url in pl.video_urls:
title, video_hash = download_youtube(url, folder=folder)
videos.append((video_hash, title))
return videos
def test_populate():
ob = Playlist(
'https://www.youtube.com/watch?v=m5q2GCsteQs&list='
'PL525f8ds9RvsXDl44X6Wwh9t3fCzFNApw',
)
expected = [
'https://www.youtube.com/watch?v=m5q2GCsteQs',
'https://www.youtube.com/watch?v=5YK63cXyJ2Q',
'https://www.youtube.com/watch?v=Rzt4rUPFYD4',
]
ob.populate_video_urls()
assert ob.video_urls == expected
def test_numbering():
ob = Playlist(short_test_pl)
ob.populate_video_urls()
gen = ob._path_num_prefix_generator(reverse=False)
assert '1' in next(gen)
assert '2' in next(gen)
ob = Playlist(short_test_pl)
ob.populate_video_urls()
gen = ob._path_num_prefix_generator(reverse=True)
assert str(len(ob.video_urls)) in next(gen)
assert str(len(ob.video_urls) - 1) in next(gen)
ob = Playlist(long_test_pl)
ob.populate_video_urls()
gen = ob._path_num_prefix_generator(reverse=False)
nxt = next(gen)
assert len(nxt) > 1
assert '1' in nxt
nxt = next(gen)
assert len(nxt) > 1
assert '2' in nxt
ob = Playlist(long_test_pl)
ob.populate_video_urls()
gen = ob._path_num_prefix_generator(reverse=True)
assert str(len(ob.video_urls)) in next(gen)
assert str(len(ob.video_urls) - 1) in next(gen)
def from_playlist_url(url):
pli = Playlist(url)
pli.parse_links()
pli.populate_video_urls()
output = dict()
output['type'] = 'playlist'
output['title'] = pli.title()
url = pli.construct_playlist_url()
output['url'] = url
output['playlist_id'] = _get_playlist_id(url)
video_urls = pli.parse_links()
output['video_urls'] = video_urls
output['video_ids'] = [v.split('=')[1] for v in video_urls]
return output
def __init__(self: VideoPlaylist,
url: str,
sort_by: VideoPlaylist.SortBy,
custom_filter: Optional[str] = None):
playlist = Playlist(url)
playlist.populate_video_urls()
self._urls: List[str] = playlist.video_urls
if sort_by is VideoPlaylist.SortBy.NEWEST:
self._urls.reverse()
self._filter: Optional[str] = None
if custom_filter:
self._filter = f'"simpleText":"{custom_filter}"'
def youtube_playlist_download(playlist_url):
print("---Youtube Playlist Download---")
playlist = Playlist(playlist_url)
playlist.populate_video_urls()
print("Number of Videos in Playlist: ", len(playlist.video_urls))
print(playlist.video_urls)
cont = input("Continue? (y/n): ")
if (cont == "y"):
try:
multiprocessing_download(playlist.video_urls, True)
except Exception as e:
print(e)
pass
else:
print("Aborted")
return
def main():
pathlib.Path(output_dir).mkdir(parents=True, exist_ok=True)
if args.source == 'list':
with open(args.path, 'r') as f:
links = [line for line in f.readlines() if len(line.strip()) > 0]
download_list(links)
elif args.source == 'link':
download_link(args.path)
elif args.source == 'playlist':
pl = Playlist(args.path)
pl.populate_video_urls()
with open(os.path.join(output_dir, 'urls.txt'), 'w') as f:
for line in pl.video_urls:
print(line, file=f)
download_list(pl.video_urls)
def download_playlist(url_link):
pl = Playlist(url_link)
n=1
succes = 0
pl.populate_video_urls()
urls = pl.video_urls
length = (len(pl.video_urls))
for url in urls:
print('------------------------------------')
print(f'Video {str(n)} out of {str(length)}')
try:
download_video (url)
n = n + 1
succes = succes + 1
except KeyError as e:
print ('I got a KeyError - reason "%s"' % str(e))
n = n + 1
continue
print(f'Finished downloading {str(succes)} of {str(length)} videos.')
def YouTube(session):
lic_id = _create_or_use_youtube_license(session)
dataset_id = _create_or_use_youtube_dataset(session)
for playlist_uri in PLAYLISTS:
playlist = Playlist(playlist_uri)
playlist.populate_video_urls()
for video_uri in playlist.video_urls:
video = PyYouTube(video_uri)
example = Example(dataset_id=dataset_id,
type=Type.MP4,
lifecycle=Lifecycle.FLEXIBLE,
license_id=lic_id)
session.add(example)
session.flush()
video.streams.filter(file_extension='mp4', only_video=True) \
.order_by('resolution').desc().first() \
.download(output_path=str(VIDEO_DIR), filename=str(example.id))
video = Video(id=example.id, orig_url=video_uri)
session.add(video)
session.commit()
def test_populate_video_urls(request_get, playlist_html):
url = "https://www.fakeurl.com/playlist?list=whatever"
request_get.return_value = playlist_html
playlist = Playlist(url)
playlist._find_load_more_url = MagicMock(return_value=None)
playlist.populate_video_urls()
request_get.assert_called()
assert playlist.video_urls == [
"https://www.youtube.com/watch?v=ujTCoH21GlA",
"https://www.youtube.com/watch?v=45ryDIPHdGg",
"https://www.youtube.com/watch?v=1BYu65vLKdA",
"https://www.youtube.com/watch?v=3AQ_74xrch8",
"https://www.youtube.com/watch?v=ddqQUz9mZaM",
"https://www.youtube.com/watch?v=vwLT6bZrHEE",
"https://www.youtube.com/watch?v=TQKI0KE-JYY",
"https://www.youtube.com/watch?v=dNBvQ38MlT8",
"https://www.youtube.com/watch?v=JHxyrMgOUWI",
"https://www.youtube.com/watch?v=l2I8NycJMCY",
"https://www.youtube.com/watch?v=g1Zbuk1gAfk",
"https://www.youtube.com/watch?v=zixd-si9Q-o",
]
def getPlaylistLinks(self, url):
"""Gets youtube playlist from a url.
Args:
url (str): The youtube url.
Returns:
output (list[str]): a list of urls of individual videos from the playlist if success
Raises:
IOError: if unable to retrive the links from the playlist
"""
playlist = Playlist(url)
try:
playlist.populate_video_urls()
except:
raise IOError
output = playlist.video_urls
return output
def download_playlist():
youtube_playlist = input("Enter Youtube Playlist URL : ")
pl = Playlist(youtube_playlist)
pl.populate_video_urls()
print('Title of the playlist: %s' % pl.title())
print('Number of videos in playlist: %s' % len(pl.video_urls))
pl_video_list = pl.video_urls
print("Downloading Playlist Videos \n")
# printing the list using loop
for x in range(len(pl_video_list)):
print(str(x) + " >> " + pl_video_list[x])
individual_video_stream = YouTube(
pl_video_list[x]).streams.filter(mime_type="video/mp4").first()
individual_video_stream.download(download_destination,
"PhysicsSession" + str(x),
"unAcademy-ClassXI-JEE")
# print(*pl_video_list, sep="\n")
# pl.download_all(download_destination)
return
def main():
parser = get_parser()
args = parser.parse_args()
pl_url = input("Enter YouTube Playlist URL : ")
pl = Playlist(pl_url)
pl.populate_video_urls()
# or if you want to download in a specific directory
print(pl.video_urls)
first_num = int(input("Enter first NUM : "))
download_path = '.'
for i, target_url in enumerate(pl.video_urls):
while True:
try:
yt = YouTube(target_url)
print(yt.title)
break
except Exception:
time.sleep(1)
print('retry')
continue
video_id = target_url.split('=')[1]
comment_data = []
pageToken = 'HEAD'
while pageToken != 'NONE':
resource = get_video_comment(video_id, args.n, pageToken)
comment_data += resource['items']
if 'nextPageToken' in resource.keys():
pageToken = resource['nextPageToken']
else:
pageToken = 'NONE'
prefix = str(i + first_num).zfill(3) + '.'
filename = prefix + re.sub(r'[\\/:*?"<>|]+', '_',
yt.title) + "_comment.json"
json_text = json.dumps(comment_data, ensure_ascii=False)
with open(filename, mode='w', encoding="utf-8") as f:
f.write(json_text)
def get_resolution():
playlists = []
with open('playlists.txt') as fin:
for line in fin.readlines():
playlists.append(line.strip())
for idx, list_id in enumerate(playlists):
playlist_url = "https://www.youtube.com/playlist?list=%s" % list_id
pl = Playlist(playlist_url)
pl.populate_video_urls()
for url in pl.video_urls:
yt = YouTube(url)
parsed = urlparse.urlparse(url)
video_hash = urlparse.parse_qs(parsed.query)['v'][0]
# print "downloading ", video_hash, yt.title
streams = yt.streams.filter(progressive=True, file_extension='mp4')
stream = streams.order_by('resolution').desc().first()
print idx, list_id, stream.resolution
break
def downloadYouTube(videourl, path):
yt = YouTube(videourl)
yt = yt.streams.filter(
progressive=True,
file_extension='mp4').order_by('resolution').desc().first()
if not os.path.exists(path):
os.makedirs(path)
yt.download(path)
'''
downloadYouTube(url, '/home/botao/share/youtube_videos/yangyi_lee/')
'''
pl = Playlist(url)
pl.populate_video_urls()
l = pl.video_urls
print 'len %d' % len(l)
#pl.download_all('/home/botao/share/youtube_videos/yangyi_lee')
i = 0
while i < len(l):
print "downloading %d/154, u %s" % (i, l[i])
try:
downloadYouTube(l[i], '/home/botao/share/youtube_videos/yangyi_lee/')
except:
print 'failed at %d, retry' % i
#sys.exit(1)
continue
i = i + 1
from os import path
from os import remove
from moviepy.audio.io.ffmpeg_audiowriter import ffmpeg_audiowrite
from moviepy.audio.io.AudioFileClip import AudioFileClip
from pathlib import Path
from datetime import datetime
errorList = []
print('Playlist to MP4 v3.0')
print('Program started: ' + datetime.now().strftime("%Y-%m-%d %H:%M:%S") +
'\n')
file = open('downloadplaylist.txt', 'r')
for line in file:
#create a playlist from the line in the file and iterate over each video
newPlaylist = Playlist(Playlist(line).construct_playlist_url())
newPlaylist.populate_video_urls()
for url in newPlaylist.video_urls:
#open the youtube video, get the mp4 audio stream, and save it to a file
ogVid = YouTube(url)
yt = ogVid.streams.filter(only_audio=True, subtype='mp4')
if yt.count() == 0:
yt = ogVid.streams.filter(subtype='mp4')
yt.first().download(getcwd() + '/.trash')
#erase special characters from file name search to match the file created by the YouTube downloader
vidTitle = ogVid.title
vidTitle = vidTitle.replace(',', '')
vidTitle = vidTitle.replace('\'', '')
vidTitle = vidTitle.replace('\"', '')
vidTitle = vidTitle.replace('.', '')
vidTitle = vidTitle.replace(';', '')
def download_clips(selected_season=None):
try:
shutil.rmtree("clips")
except Exception as e:
pass
time.sleep(3)
os.mkdir("clips")
with requests.Session() as session:
url = "https://www.youtube.com/user/BobRossInc/playlists?shelf_id=7&view=50&sort=dd"
session.get(url)
sauce = session.get(url)
soup = bs(sauce.content, 'html')
for season, playlist in enumerate(
tqdm(soup.find_all('h3', {'class': 'yt-lockup-title'}))):
if season == selected_season or selected_season == None:
season_url = "https://www.youtube.com/{}".format(
playlist.find('a').get('href'))
pl = Playlist(season_url)
pl.populate_video_urls()
for episode, episode_url in enumerate(tqdm(pl.video_urls)):
clip_titles = []
try:
vid = YouTube(episode_url)
vid.streams.filter(subtype='mp4').first().download()
except:
try:
time.sleep(3)
vid = YouTube(episode_url)
vid.streams.filter(
subtype='mp4').first().download()
except:
print(
"Couldn't download season {}, skipping season."
.format(season + 1))
continue # skip season
episode_filename = "{}.mp4".format(
vid.title.replace(".", "").replace("'", ""))
xml_caps = vid.captions.get_by_language_code(
'en').xml_captions
root = ET.fromstring(xml_caps)
for child in root:
start = child.attrib["start"]
dur = child.attrib["dur"]
text = child.text
if "(" in text:
text = text.replace("(", "").replace(")",
"").replace(
" ", "_")
try:
clip = VideoFileClip(episode_filename)
time_stamp = time.strftime(
"%M_%S", time.gmtime(float(start)))
clip.subclip(
float(start),
float(start) + float(dur)).write_videofile(
"clips/S{}E{}-{}-{}-{}.mp4".format(
season + 1, episode + 1,
time_stamp, text,
clip_titles.count(text)),
fps=30,
codec='mpeg4')
# clip.subclip(float(start),float(start) + float(dur)).write_videofile("clips/S1E{}-{}-{}.gif".format(episode+1,text,clip_titles.count(text)),fps=30,codec='gif')
clip_titles.append(text)
clip.reader.close()
clip.audio.reader.close_proc()
except:
print("Could not get clip {}.".format(text))
time.sleep(
3) # give clip audio/reader enough time to close
try:
os.remove(episode_filename) # delete episode file
except:
print(
"Couldn't delete episode file {}, please do so manually."
.format(episode_filename))
print(FILE_PATH)
except:
FILE_PATH = '/home/oscar/Tec/'
pass
for INDEX in range(len(DICTIONARY_YT)):
YT_NAME = list(DICTIONARY_YT.keys())[INDEX]
YT_PLAYLIST = list(DICTIONARY_YT.values())[INDEX]
PATH_DONWLOAD = FILE_PATH + '/YT/' + YT_NAME + '/'
if not os.path.exists(PATH_DONWLOAD):
os.makedirs(PATH_DONWLOAD, exist_ok=True)
print('BUSCANDO URLS EN PLAYLIST')
playlist = Playlist(YT_PLAYLIST)
playlist.populate_video_urls()
VIDEOS_PLAYLIST = playlist.video_urls
try:
with open(PATH_DONWLOAD + 'URLS_CHECKED.txt', 'r') as file:
URLS_CHECKED = file.read().splitlines()
except:
URLS_CHECKED = []
print('TODAVÍA NO EXISTE URLS_CHECKED.txt')
NEW_URLS = [item for item in VIDEOS_PLAYLIST if item not in URLS_CHECKED]
BUSCAR_LINKS_BANDCAMP = True
if BUSCAR_LINKS_BANDCAMP:
LINKS_bandcamp = []
VIDEOS_WITHOUT_BANDCAMP = []