BeBeBeBeBörnd
Mittwoch, 23. Juni 2010שָׁלוֹם
/usr/local/bin/berndget
#!/usr/bin/env python
import urllib2
import urllib
import BeautifulSoup
import sys
import re
import os
def stripfilename(url):
base = urllib.unquote(os.path.basename(url))
return base
def contains(theString, theQueryValue):
return theString.find(theQueryValue) > -1
def _reporthook(numblocks, blocksize, filesize):
sys.stdout.write(".")
sys.stdout.flush()
request = urllib2.Request(sys.argv[1])
response = urllib2.urlopen(request)
soup = BeautifulSoup.BeautifulSoup(response)
for a in soup.findAll('a'):
link=a.get('href')
if (link):
if (contains(link, "/download/")):
base=stripfilename(link)
url="http://krautchan.net"+link
print url+" --> "+base
urllib.urlretrieve(url, base, _reporthook)
print
By Bernd (sometimes under public domain)
