what do you find that is strange?
On Aug 21, 7:32 am, Stef Mientki <stef.mien...@gmail.com> wrote:
> > Graphical representation of links or pages that don't get linked to.
>
> I tried to test the links (with 2 algorithms, code below) in a generated
> webpage, but the result I
> get are very weird.
> Probably one you knows a better way ?
>
> cheers,
> Stef
>
> from BeautifulSoup import BeautifulSoup
> from urllib import urlopen
> from httplib import HTTP
> from urlparse import urlparse
>
> def Check_URL_1 ( URL ) :
> try:
> fh = urlopen ( URL )
> return fh.code == 200
> except :
> return False
>
> def Check_URL_2 ( URL ) :
> p = urlparse ( URL )
> h = HTTP ( p[1] )
> h.putrequest ( 'HEAD', p[2] )
> h.endheaders()
> if h.getreply()[0] == 200:
> return True
> else:
> return False
>
> def Verify_Links ( URL ) :
> Parts = URL.split('/')
> Site = '/'.join ( Parts [:3] )
> Current = '/'.join ( Parts [:-1] )
>
> fh = urlopen ( URL )
> lines = fh.read ()
> fh.close()
>
> Soup = BeautifulSoup ( lines )
> hrefs = lines = Soup.findAll ( 'a' )
>
> for href in hrefs :
> href = href [ 'href' ] #[:-1] ## <== remove "#" to generate all errors
>
> if href.startswith ( '/' ) :
> href = Site + href
> elif href.startswith ('#' ) :
> href = URL + href
> elif href.startswith ( 'http' ) :
> pass
> else :
> href = Current + href
>
> try:
> fh = urllib.urlopen ( href )
> except :
> pass
> print Check_URL_1 ( href ), Check_URL_2 ( href ), href
>
> URL = 'http://127.0.0.1:8000/welcome/default/index'
> fh = Verify_Links ( URL )
