python-webscraping

python

import urllib2

import re

import subprocess

from BeautifulSoup import BeautifulSoup, SoupStrainer



url='http://media.railscasts.com/assets/episodes/videos/'

soup = BeautifulSoup(urllib2.urlopen(url).read())

for tag in soup.findAll('a',href=True):

	a=tag['href']

	b=a.endswith('ogv')

	 

        if  b == True :

	     z=url+a

	     print z

             subprocess.call(["wget","-c" , z])