def get_cc(self, lang="en"):
# sets self.title
# self.srt_file
# self.vocap_file
# and downloads self.srt_file
if not isinstance(self.vid, unicode):
self.vid = unicode(self.vid, 'utf-8')
######### Get subtitles and title
cc = getyoutubecc.getyoutubecc(self.vid,lang)
if not cc:
return 0
print cc.name
self.title = cc.name
self.srt_file = self.dir_name+u'/'+self.vid+u'.srt'
if not isinstance(self.srt_file, unicode):
self.srt_file = unicode(self.srt_file, 'utf-8')
self.title_file = self.dir_name+u'/'+self.vid+u'.title'
if not isinstance(self.title_file, unicode):
self.title_file = unicode(self.title_file, 'utf-8')
self.vocap_file = self.dir_name+u'/'+self.vid+u'.vocap'
if not isinstance(self.vocap_file, unicode):
self.vocap_file = unicode(self.vocap_file, 'utf-8')
print "saving the file: "+self.srt_file
cc.writeSrtFile(self.path+"/"+self.srt_file)
fileobj=codecs.open(self.path+"/"+self.title_file, "w", "utf-8")
fileobj.write(self.title)
fileobj.close()
def get_single_url(url, youtube_object=YouTube()):
# try:
youtube_object.url = url
video = youtube_object.get('mp4', '720p')
filename = youtube_object.filename
video.download()
cc = getyoutubecc.getyoutubecc(youtube_object.video_id, 'en')
cc_filename = filename + '.srt'
cc.writeSrtFile(cc_filename)
return {'filename': filename, 'cc_filename': cc_filename}
def get_single_url(url, youtube_object=YouTube()):
# try:
youtube_object.url = url
video = youtube_object.get('mp4', '720p')
filename = youtube_object.filename
video.download()
cc = getyoutubecc.getyoutubecc(youtube_object.video_id,'en')
cc_filename = filename + '.srt'
cc.writeSrtFile(cc_filename)
return {'filename' : filename,
'cc_filename': cc_filename}
def search_all_files(search_url, youtube_object=YouTube()):
search_url = search_url
urls = get_urls(search_url)
yt = youtube_object
for url in urls:
try:
print "downloading " + url
yt.url = url
video = yt.get('mp4', '720p')
filename = yt.filename
video.download()
time.sleep(.1)
cc = getyoutubecc.getyoutubecc(yt.video_id, 'en')
cc.writeSrtFile(filename + '.srt')
time.sleep(.1)
except:
print "couldn't download " + url
def search_all_files(search_url, youtube_object=YouTube()):
search_url = search_url
urls = get_urls(search_url)
yt = youtube_object
for url in urls:
try:
print "downloading " + url
yt.url = url
video = yt.get('mp4', '720p')
filename = yt.filename
video.download()
time.sleep(.1)
cc = getyoutubecc.getyoutubecc(yt.video_id,'en')
cc.writeSrtFile(filename + '.srt')
time.sleep(.1)
except:
print "couldn't download " + url
from pytube import YouTube
import getyoutubecc
from bs4 import BeautifulSoup
def get_urls(url):
data = urllib.urlopen(url).read()
soup = BeautifulSoup(data)
soupy_links = soup.select('a.yt-uix-sessionlink')
urls = ['http://youtube.com' + link.get('href') for link in soupy_links if 'watch' in link.get('href')]
return set(urls)
search_url = sys.argv[1]
urls = get_urls(search_url)
yt = YouTube()
for url in urls:
try:
print "downloading " + url
yt.url = url
video = yt.get('mp4', '720p')
filename = yt.filename
video.download()
time.sleep(.1)
cc = getyoutubecc.getyoutubecc(yt.video_id,'en')
cc.writeSrtFile(filename + '.srt')
time.sleep(.1)
except:
print "couldn't download " + url
from bs4 import BeautifulSoup
def get_urls(url):
data = urllib.urlopen(url).read()
soup = BeautifulSoup(data)
soupy_links = soup.select('a.yt-uix-sessionlink')
urls = [
'http://youtube.com' + link.get('href') for link in soupy_links
if 'watch' in link.get('href')
]
return set(urls)
search_url = sys.argv[1]
urls = get_urls(search_url)
yt = YouTube()
for url in urls:
try:
print "downloading " + url
yt.url = url
video = yt.get('mp4', '720p')
filename = yt.filename
video.download()
time.sleep(.1)
cc = getyoutubecc.getyoutubecc(yt.video_id, 'en')
cc.writeSrtFile(filename + '.srt')
time.sleep(.1)
except:
print "couldn't download " + url
def home(request):
cc = getyoutubecc.getyoutubecc(u"T8X15QkS-N8")
return render_to_response("home/home.html", {"name": cc.name})
