#!/usr/bin/env python
import urllib, re, time, rsslib
"""
Technorati.com doesn't seem to want to provide RSS feeds for their site.
Currently will create RSS for:
    http://technorati.com/pop/news/
    http://technorati.com/pop/books/
    http://technorati.com/pop/movies/
    http://technorati.com/pop/blogs/

Author: Cameron Mallory  http://YOURSITE

You may use this code below as you see fit, in any form whatsoever.
"""
# Fully qualified path to where the RSS files will be created.
outputDir = "/home/username/your/rss/files/"
url = "url"
title = "title"
desc = "desc"
file = "file"
regex = "regex"

# Our RSS files we will create.  
Popular = { 
        0 : { url   : 'http://technorati.com/pop/movies/' ,
              title : 'Popular Movies',
              desc  : 'Technorati Popular Movies RSS',
              file  : 'popmovies.xml',
              regex : '<!-- google_ad_section_start -->(.*?)<!-- google_ad_section_end -->'
            },
        1 : { url   : 'http://technorati.com/pop/news/' ,
              title : 'Popular News',
              desc  : 'Technorati Popular News RSS',
              file  : 'popnews.xml',
              regex : '<!-- google_ad_section_start -->(.*?)<!-- google_ad_section_end -->'
            },
        2 : { url   : 'http://technorati.com/pop/books/' ,
              title : 'Popular Books',
              desc  : 'Technorati Popular Books RSS',
              file  : 'popbooks.xml',
              regex : '<!-- google_ad_section_start -->(.*?)<!-- google_ad_section_end -->'
            },
        3 : { url   : 'http://technorati.com/pop/blogs/' ,
              title : 'Popular Blogs',
              desc  : 'Technorati Popular Blogs RSS',
              file  : 'popblogs.xml',
              regex : '<!-- google_ad_section_start -->(.*?)<!-- google_ad_section_end -->'
            }
}

TITLE = "Technorati RSS by YOURSITE"

def process ( d , p ):
    rss = rsslib.RSS()
    rss.channel.link = p[ url ]
    rss.channel.title = TITLE + " - " + p[ title ]
    rss.channel.description = p[ desc ]

    urls = re.compile( '<h2><a href="(.*?)"' ).findall( d )
    titles = re.compile(  '<h2><a href=.*?title=.*?">(.*?)<\/a><\/h2>' ).findall( d )
    viewAlls = re.compile('<a href="\/search\/(.*?)" class="more links"').findall( d )
    descriptions = re.compile('<blockquote.*?>(.*?)<\/blockquote>').findall( d )

    for i in range(0, len(urls) ):
        item = rsslib.Item()
        item.link = urls[ i ]
        va = '<a href="http://technorati.com/search/' + viewAlls[ i ] + '">View All</a>'
        item.description = descriptions[ i ] + "\n" + va 
        item.title = titles[ i ]
        rss.addItem( item )
        
    return rss.write()

"""
Let's get this party started
"""
for i in range( 0, len( Popular ) ):
    p = Popular[i]
    r = re.compile( p[ regex ] )
    d = urllib.urlopen( p[ url ] ).read().replace("\n","")
    d = r.findall( d )[0]
    open( outputDir + p[ file ] , 'w' ).write( process( d , p ) )

tags = re.compile( '<a href="/tag/(.*?)".*?>' ).findall( urllib.urlopen( "http://technorati.com/tags" ).read().replace("\n","") )
rss = rsslib.RSS()
rss.channel.link = "http://technorati.com/tags/"
rss.channel.title = "Technorati Top Tags RSS by YOURSITE";
rss.channel.description = "The top 200 tags from technorati.com"
for t in tags:
	item = rsslib.Item()
	item.link = "http://technorati.com/tag/" + t
	item.title = "Technorati tag: " + t
	item.description =  ""
	rss.addItem( item )
open( outputDir + "toptags.xml", "w").write( rss.write() )