俺ガイル公式ページの最新ニュースを拾ってくるやつ

oregairu_hook.py

#!/usr/bin/env python2
# coding: utf-8

import re
import requests
import lxml.html
from selenium import webdriver

class oregairu_hook(object):
    def __init__(self):
        self.target_url = 'http://www.tbs.co.jp/anime/oregairu/'
        self.driver = webdriver.PhantomJS()
        self.latest_data = {}

    def get_html(self):
        self.driver.get(self.target_url)
        #driver.save_screenshot('oregairu.jpg')
        return self.driver.page_source

    def main(self):
        page = self.get_html()
        root =  lxml.html.fromstring(page)
        
        article = root.cssselect('.cbox h4')
        
        """ get latest article's publish date and title """
        str = article_title[0].text_content()
        date = re.search('[0-9]*\.[0-9]*\.[0-9]*',str).group(0)
        title = str[10:]

        links = root.cssselect('.cbox a') # relative url
        url = self.target_url+links[0].values()[0] # absolute url
        
        self.latest_data['date'] = date
        self.latest_data['title'] = title
        self.latest_data['url'] = url
        
        print self.latest_data['date']
        print self.latest_data['title']
        print self.latest_data['url']

if __name__ == '__main__':
    oh = oregairu_hook()
    oh.main()