YouTube Scrapper

gistfile1.py

import gdata.youtube
import gdata.youtube.service
import Queue
import threading
import string
valid_chars = "-_.() %s%s" % (string.ascii_letters, string.digits)
from urllib import urlopen, unquote
import urllib
from urlparse import parse_qs, urlparse
yt_service = gdata.youtube.service.YouTubeService()
from pytube import YouTube 
class AppURLopener(urllib.FancyURLopener):
    version = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.77 Safari/535.7"
 
urllib._urlopener = AppURLopener()
 
def Search(search_terms):
  yt_service = gdata.youtube.service.YouTubeService()
  query = gdata.youtube.service.YouTubeVideoQuery()
  query.vq = search_terms
  query.orderby = 'relevance'
  query.racy = 'include'
  feed = yt_service.YouTubeQuery(query)
  return feed
 
 
    
##def PrintEntryDetails(entry):
##  print 'Video title: %s' % entry.media.title.text
##  print 'Video published on: %s ' % entry.published.text
##  print 'Video description: %s' % entry.media.description.text
##  print 'Video category: %s' % entry.media.category[0].text
##  print 'Video tags: %s' % entry.media.keywords.text
##  print 'Video watch page: %s' % entry.media.player.url
##  print 'Video flash player URL: %s' % entry.GetSwfUrl()
##  print 'Video duration: %s' % entry.media.duration.seconds
##
##
####  print 'Video rating: %s' % entry.rating.average
##
##  # show alternate formats
##  for alternate_format in entry.media.content:
##    if 'isDefault' not in alternate_format.extension_attributes:
##      print 'Alternate format: %s | url: %s ' % (alternate_format.type,
####                                                 alternate_format.url)
####
##  # show thumbnails
##  for thumbnail in entry.media.thumbnail:
##    print 'Thumbnail url: %s' % thumbnail.url
 
def Download_mp4(id):
    video_id = id
 
    print 'http://www.youtube.com/watch?v=' + video_id
    yt = YouTube()
    yt.url = 'http://www.youtube.com/watch?v=' + video_id
    video = yt.filter(extension="mp4")[0]
    video.download()
##    elif "token" in stuff :
##        url = stuff['token'][0]
##        print url
##        data = urlopen(url).read()        
##        return data
    return
    # open(video_id+'.mp4', 'wb').write(data)
 
def SearchnDownload (term):
    feed = Search(term)
    id = feed.entry[0].id.text.split("/")[-1]
    data = Download_mp4(id)


class downloader(threading.Thread):
    def __init__(self, queue):
        threading.Thread.__init__(self)
        self.queue = queue
    def run(self):
        while True:
            video = self.queue.get()
            SearchnDownload(video)
            self.queue.task_done()
        
a=""""""

queue = Queue.Queue()

for i in range(10):
              t = downloader(queue)
              t.setDaemon(True)
              t.start()
              
for line in a.split("\n"):
	queue.put(line.strip())
queue.join()