#!/usr/bin/python3
# Name: youParse.py
# Author: pantuts
# Email: pantuts@gmail.com
# Description: Parse URLs in Youtube User's Playlist (Video Playlist not Favorites)
# Use python3 and later
# Agreement: You can use, modify, or redistribute this tool under
# the terms of GNU General Public License (GPLv3).
# This tool is for educational purposes only. Any damage you make will not affect the author.
# Usage: python3 youParse.py youtubeURLhere
import re
import urllib.request
import sys
def crawl(url):
sTUBE = ''
cPL = ''
tmp = 0
amp = 0
if 'PL' in url:
tmp = url.index('L') + 1
cPL = url[tmp:]
if '&' in url:
amp = url.index('&')
cPL = url[tmp:amp]
else:
print('Incorrect Playlist.\nSample playlist at the end of url: PL1894B2B763FBC580')
exit(1)
try:
yTUBE = urllib.request.urlopen(url).read()
sTUBE = str(yTUBE)
except urllib.error.URLError as e:
print(e.reason)
mat = re.findall(r'watch\?v=\w.+?' + cPL, sTUBE)
if mat:
if mat[0] == mat[1]:
mat.remove(mat[0]) #if there is duplicate, remove
# print('Videos in Playlist: ' + str(len(mat)))
for PL in mat:
yPL = str(PL)
if '&' in yPL:
yPL_amp = yPL.index('&')
print('[+] http://www.youtube.com/' + yPL[:yPL_amp])
else:
print('No videos found.')
exit(1)
if len(sys.argv) < 2 or len(sys.argv) > 2:
print('USAGE: python3 youParse.py YOUTUBEurl')
exit(1)
else:
url = sys.argv[1]
if 'http' not in url:
url = 'http://' + url
print('Extracting...')
crawl(url)
Diff to Previous Revision
--- revision 9 2012-10-17 05:25:56
+++ revision 10 2012-10-18 08:58:25
@@ -36,7 +36,7 @@
except urllib.error.URLError as e:
print(e.reason)
- mat = re.findall(r'watch\S+list=PL+' + cPL, sTUBE)
+ mat = re.findall(r'watch\?v=\w.+?' + cPL, sTUBE)
if mat:
if mat[0] == mat[1]: