scrape some obama speeches

scrape.py

from bs4 import BeautifulSoup
import requests
import urllib

#if that shit doesn't load, do from terminal 

#python -m pip install module name or pip install module

url = "http://www.americanrhetoric.com/barackobamaspeeches.htm"
response = requests.get(url)
soup = BeautifulSoup(response.text)


"""
actual pattern
http://www.americanrhetoric.com/mp3clipsXE/barackobama/barackobamanursesassociationARXE.mp3


mp3clipsXE/barackobama/barackobamaguantanimobayclosingARXE.mp3
mp3clipsXE/barackobama/barackobamaISILupdate02-25-16ARXE.mp3
mp3clipsXE/barackobama/barackobamarecoveryact2016ARXE.mp3



"""

stub = "http://www.americanrhetoric.com/"
files = [] #put all files in a list

for a in soup.findAll('a'):
  if '.mp3' in a['href']:
    files.append(stub + a['href']) # add them to a list but since relative paths use stub each time

somefiles =  files[:10] #first 10 files to test download (just use files for all of em)
print len(files)

#Download the fuckers - just ave as last 9 chars of file
#added basic try except in case one flops you won't kill the script, the terminal will print the error
try:
	for x in somefiles:
		urllib.urlretrieve(x, x.split("/")[5])
except Exception, e:
	print str(e)
	pass