lxml_ex.py

import json
from lxml.html import fromstring
from urllib import urlopen

def get_tree(page):
    d = urlopen('http://audio.tutsplus.com/category/tutorials/production/page/%d' % page).read()
    h = fromstring(d)
    return h

def extract_art(head):
    a = head.find('a')
    link = a.get('href')
    text = a.text
    return link, text

def get_arts(tree):
    arts = [extract_art(head) for head in tree.cssselect('h1.post_title')]
    return arts

# arts = []
# for i in range(1, 48):
#     print i
#     arts.extend(get_arts(get_tree(i)))

# json.dump(arts, open('arts.json', 'w'))

arts = json.load(open('arts.json'))

def shorten(text):
    return text.replace('Quick Tip:', '').replace('How to', '').strip()

arts = sorted([[shorten(text), link] for link, text in arts])

print '<ol>'
for text, link in arts:
    t = '<li><a href="%s">%s</a></li>' % (link, text)
    print t.encode('utf-8')
print '</ol>'