Decomposing HTML to link text and target

<a href="urltxt" class="someclass" close="true">texttxt</a>

soup = BeautifulSoup.BeautifulSoup(urllib.urlopen(url))

links = soup.findAll('a')

for link in links:
    print "link content:", link.content," and attr:",link.attrs

*link content: None  and attr: [(u'href', u'_redirectGeneric.asp?genericURL=/root    /support.asp')]*  ...
...

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

import urlparse, urllib
from BeautifulSoup import BeautifulSoup

url = "http://www.example.com/index.html"
source = urllib.urlopen(url).read()

soup = BeautifulSoup(source)

for item in soup.fetchall('a'):
    try:
        link =  urlparse.urlparse(item['href'].lower())
    except:
        # Not a valid link
        pass
    else:
        print link

soup = BeautifulSoup.BeautifulSoup(urllib.urlopen(url))
for link in soup.findAll('a'):
    print link.attrs, link.contents

/<as+[^>]*?href="([^"]*)".*?>(.*?)</a>/

'<a href="url" close="true">text</a>'
// Parts: "url", "text"

'<a href="url" close="true">text<span>something</span></a>'
// Parts: "url", "text<span>something</span>"