admin based on bootstrap, thanks Paolo

2012-12-24 13:49:06 -06:00
parent 56295371a4
commit 3710d43cfc
112 changed files with 6839 additions and 1371 deletions
@@ -0,0 +1,12 @@
+import re
+import urllib
+import urllib2
+from BeautifulSoup import BeautifulSoup
+
+page = urllib2.urlopen('http://www.telegraph.co.uk/technology/internet/9524681/Sir-Tim-Berners-Lee-accuses-government-of-draconian-internet-snooping.html')
+soup = BeautifulSoup(page)
+
+items = soup.findAll(['h1','h2','h3','h4','h5','h6','p'])
+text =  '\n'.join(''.join(item.findAll(text=True)) for item in items).encode('utf8')
+text = re.sub('\s*\n\s*','\n',re.sub('[ \t]+',' ',text))
+print text