Skip to content

Instantly share code, notes, and snippets.

@neoadventist

neoadventist/getNaruto.py

Last active Dec 27, 2015
Embed
What would you like to do?
Downloads a Naruto video from www.narutonine.com! Run: python getNaruto.py <a> <b> where a<b and a and b is an episode number in Naruto.
#BELEIVE IT!!
print("Jesus Saves");
#import libaries
import sys;
import time;
import urllib;
from urllib import FancyURLopener;
from random import choice;
#declare global variables
global num;
global numEnd;
num = int(sys.argv[1]);
if(len(sys.argv)==2):
numEnd = num;
else:
numEnd = int(sys.argv[2]);
#use random user agent so that the server doesn't kick us out!
user_agents = [
'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
'Opera/9.25 (Windows NT 5.1; U; en)',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9'
];
def getWebPage(episode):
naruto = 'http://www.narutonine.com/NarutoEpisode'+str(episode)+'EnglishDubbed.html';
print("Naruto URL: "+naruto);
class MyOpener(FancyURLopener, object):
version = choice(user_agents)
fileName = 'file';
myopener = MyOpener()
myopener.retrieve(naruto, fileName)
return fileName
def verifyPage(fileName):
f=open(fileName, 'r');
lines = f.readlines();
f.close();
lineArray = [];
for x in lines:
lineArray.append(x);
escaped = False;
for idx, val in enumerate(lineArray):
msg = str(idx)+' = '+str(lineArray[idx]);
if (msg.find("unescape")!=-1):
escaped = str(lineArray[idx]);
elif (msg.find("Error 406")!=-1):
print("ERROR 406 FOUND!!!");
return(406);
if(escaped==False): #if for some reason it doesn't work, return an error!
return("ERROR");
unescape = escaped.split("unescape");
needtoclean = unescape[1];
needtoclean = needtoclean.replace("(","");
needtoclean = needtoclean.replace(")","");
iframe = urllib.unquote(needtoclean);
src = iframe.split("src=");
url = src[1].replace('"></iframe><br>','');
url = url.replace('"','');
url = url.split("&");
return url[0];
def getMp4(url):
global num;
class MyOpener(FancyURLopener, object):
version = choice(user_agents)
myopener = MyOpener()
myopener.retrieve(url, 'closer');
f=open('closer', 'r');
lines = f.readlines();
f.close();
lineArray = [];
for x in lines:
lineArray.append(x);
for idx, val in enumerate(lineArray):
msg = str(idx)+' = '+str(lineArray[idx]);
if(msg.find("Bad Request")!=-1):
print ("ERROR: "+msg);
return (400);
elif(msg.find("so.addVariable('file',")!=1):
doc = str(lineArray[idx]);
doc = doc.split("so.addVariable('file','");
for i, v in enumerate(doc):
if(doc[i].find("mp4")!=-1):
mp4 = doc[i].replace("');","");
print("MP4 URL: "+str(mp4));
name = str(num)+'.mp4';
myopener.retrieve(mp4, name);
print(name+" DONE!!");
def main():
global num;
global numEnd;
print("Downloading Naruto Episodes "+str(num)+" to "+str(numEnd));
completedCount =0;
while(num<=numEnd):
c=0;
url='';
while (True):
f = getWebPage(num);
url = verifyPage(f);
if(url!=406):
break;
if(c>10):
break;
c+=1;
if(url==406):
time.sleep(c*10); #if we can't get the webpage, wait and retry--we might be asking for too much too fast!
if(url!=''):
getMp4(url);
num+=1;
completedCount+=1;
print("Finished! Downloaded "+str(completedCount)+" Episodes!");
main(); #go!
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.