英語のニュースをKindleに送信する

newssender.py

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

import feedparser
import requests
import lxml.html
import gmail
import re
import os
from time import mktime
from datetime import datetime

#Kindleのアドレス
KINDLE_ADDRESS = "[email protected]"

class News:
    """
    ニュースを格納するクラス
    """
    def __init__(self, title, content, url, date):
        self.title = title
        self.url = url
        self.date = date
        self.content = content
    def showinfo(self):
        print '%s (%s)' % (self.title, self.date)

def create_html(list, filename):
    from jinja2 import Environment, FileSystemLoader
    path = os.path.abspath(os.path.dirname(__file__))
    env = Environment(loader=FileSystemLoader(path, encoding='utf8'))
    tpl = env.get_template('template.html')

    news_list = []
    for news in list:
        content = news.content
        news_list.append({'title':news.title, 'body':content})

    #現在時刻を取得
    now = datetime.today()
    title = now.strftime("News_%Y-%m-%d_%H:%M:%S")

    html = tpl.render({'title':title, 'news_list':news_list})

    tmpfile = open(path + "/" + filename, 'w') #書き込みモードで開く
    tmpfile.write(html.encode('utf-8'))
    tmpfile.close()


if __name__ == '__main__':

    #RSSのURL
    rss_url = "http://www.japantoday.com/feed/"
    #interval_time時間以内のニュースを取得
    interval_time = 24

    #空のNewsリスト
    news_list = []

    #現在時刻を取得
    now = datetime.today()

    feed = feedparser.parse(rss_url)
    for entry in range(len(feed.entries)):

        #RSSの内容を一件づつ処理する
        title = feed.entries[entry].title
        link = feed.entries[entry].link

        #現在時刻から更新日時の時間差を確認
        tmp = feed.entries[entry].updated_parsed
        date = datetime.fromtimestamp(mktime(tmp))
        diff_time = now - date
        diff_hours = (diff_time.seconds/3600) + (diff_time.days*24)

        if diff_hours <= interval_time:
            #interval_time時間以内に更新された記事のみを対象とする

            #Webページ(HTML)の取得
            req = requests.get(link)
            root = lxml.html.fromstring(req.text)

            #HTMLから記事の抽出(Japan Today)
            title = root.get_element_by_id('main_title').text
            content = lxml.html.tostring(root.get_element_by_id('article_content'))
            p = re.compile(r"<[^>]*?>")
            content = p.sub("", content)

            #記事リストの中に追加
            news = News(title, content, link, date)
            news_list.append(news)

    filename = now.strftime("News_%Y-%m-%d_%H:%M:%S") + ".html"

    create_html(news_list, filename)

    #メッセージの作成
    to_addr = KINDLE_ADDRESS
    subject = filename
    body = ""
    mime={'type':'text', 'subtype':'comma-separated-values'}
    attach_file={'name':filename, 'path':filename}
    msg = gmail.create_message(gmail.ADDRESS, to_addr, subject, body, mime, attach_file)

    #メールの送信
    gmail.send(gmail.ADDRESS, [to_addr], msg)