2chmatome.py

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import urllib2

from pyquery import PyQuery as pq

def get_matome_info(url):
    res = urllib2.urlopen(url)
    html = res.read().decode('utf-8')
    dom = pq(html)
    title_doms = dom('span.blomaga_name.matome span')
    url_doms = dom('span.blomaga_name.matome a')
    matome_info_doms = zip(title_doms, url_doms)
    matome_info = set()
    for title_dom, url_dom in matome_info_doms:
        matome_info.add((title_dom.text, url_dom.get('href')))
    return matome_info

def main():
    blomaga_url = u'http://ch.nicovideo.jp/portal/blomaga/matomemedia'
    matome_info = get_matome_info(blomaga_url)
    for title, url in matome_info:
        print title + u' | ' + url

if __name__ == '__main__':
    main()