calibre/recipes/mainichi.recipe

62 lines
2.0 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
'''
www.mainichi.jp
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class MainichiDailyNews(BasicNewsRecipe):
title = u'\u6bce\u65e5\u65b0\u805e'
__author__ = 'Hiroshi Miura'
oldest_article = 2
max_articles_per_feed = 20
description = 'Japanese traditional newspaper Mainichi Daily News'
publisher = 'Mainichi Daily News'
category = 'news, japan'
language = 'ja'
index = 'http://mainichi.jp/select/'
remove_javascript = True
masthead_title = u'MAINICHI DAILY NEWS'
remove_tags_before = {'class':"NewsTitle"}
remove_tags_after = {'class':"NewsBody clr"}
def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self)
for curfeed in feeds:
delList = []
for a,curarticle in enumerate(curfeed.articles):
if re.search(r'pheedo.jp', curarticle.url):
delList.append(curarticle)
if re.search(r'rssad.jp', curarticle.url):
delList.append(curarticle)
if len(delList)>0:
for d in delList:
index = curfeed.articles.index(d)
curfeed.articles[index:index+1] = []
return feeds
def parse_index(self):
feeds = []
soup = self.index_to_soup(self.index)
topstories = soup.find('ul',attrs={'class':'MaiLink'})
if topstories:
newsarticles = []
for itt in topstories.findAll('li'):
itema = itt.find('a',href=True)
if itema:
newsarticles.append({
'title' :itema.string
,'date' :''
,'url' :itema['href']
,'description':''
})
feeds.append(('latest', newsarticles))
return feeds