from DiggSearch import digg_search
digg_search('twitter', sort='newest')  #sort by newest first
digg_search('twitter', sort='digg')  # sort by number of diggs
digg_search('twitter -d')  # sort by best match

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# (C) 2009 HalOtis Marketing
# written by Matt Warren
# http://halotis.com/
 
import urllib,urllib2
import re
 
from BeautifulSoup import BeautifulSoup
 
USER_AGENT = 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)'
 
def remove_extra_spaces(data):
    p = re.compile(r'\s+')
    return p.sub(' ', data)
 
def digg_search(query, sort=None, pages=10):
    """Returns a list of the information I need from a digg query
    sort can be one of [None, 'digg', 'newest']
    """
 
    digg_results = []
    for page in range (1,pages):
 
        #create the URL
        address = "http://digg.com/search?s=%s" % (urllib.quote_plus(query))
        if sort:
            address = address + '&sort=' + sort
        if page > 1:
            address = address + '&page=' + str(page)
 
        #GET the page
        request = urllib2.Request(address, None, {'User-Agent':USER_AGENT} )
        urlfile = urllib2.urlopen(request)
        page = urlfile.read(200000)
        urlfile.close()
 
        #scrape it
        soup = BeautifulSoup(page)
        links = soup.findAll('h3', id=re.compile("title\d"))
        comments = soup.findAll('a', attrs={'class':'tool comments'})
        diggs = soup.findAll('strong', id=re.compile("diggs-strong-\d"))
        body = soup.findAll('a', attrs={'class':'body'})
        for i in range(0,len(links)):
            item = {'title':remove_extra_spaces(' '.join(links[i].findAll(text=True))).strip(), 
                    'destination':links[i].find('a')['href'],
                    'comment_count':int(comments[i].string.split()[0]),
                    'digg_link':comments[i]['href'],
                    'digg_count':diggs[i].string,
                    'summary':body[i].find(text=True)
                    }
            digg_results.append(item)
 
        #last page early exit
        if len(links) < 10:
            break
 
    return digg_results
 
if __name__=='__main__':
    #for testing
    results = digg_search('twitter -d', 'digg', 2)
    for r in results:
        print r