mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
72 lines
2.8 KiB
Plaintext
72 lines
2.8 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010,2014, Hiroshi Miura <miurahr@linux.com>'
|
|
'''
|
|
www.yomiuri.co.jp
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import re
|
|
|
|
|
|
class YOLNews(BasicNewsRecipe):
|
|
title = u'Yomiuri Online (World)'
|
|
__author__ = 'Hiroshi Miura'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 50
|
|
description = 'Japanese traditional newspaper Yomiuri Online News/world news'
|
|
publisher = 'Yomiuri Online News'
|
|
category = 'news, japan'
|
|
language = 'ja'
|
|
encoding = 'UTF-8'
|
|
index = 'http://www.yomiuri.co.jp/world/'
|
|
remove_javascript = True
|
|
masthead_title = u"YOMIURI ONLINE"
|
|
|
|
keep_only_tags = [{'class': "article text-resizeable"}]
|
|
|
|
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'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 = []
|
|
newsarticles = []
|
|
soup = self.index_to_soup(self.index)
|
|
mainspan = soup.find('div', attrs={'class': 'pbNested span-main-inr'})
|
|
if mainspan:
|
|
topstories = mainspan.find('ul', attrs={'class': 'list-top'})
|
|
if topstories:
|
|
for itt in topstories.findAll('li'):
|
|
itema = itt.find('a', href=True)
|
|
if itema:
|
|
item_headline = itema.find(
|
|
'span', attrs={'class': 'headline'})
|
|
item_date = item_headline.find(
|
|
'span', attrs={'class': 'update'})
|
|
newsarticles.append({
|
|
'title': item_headline.contents[0], 'date': item_date, 'url': itema['href'], 'description': ''
|
|
})
|
|
secondstories = mainspan.find('ul', attrs={'class': 'list-common'})
|
|
if secondstories:
|
|
for itt in secondstories.findAll('li'):
|
|
itema = itt.find('a', href=True)
|
|
if itema:
|
|
item_headline = itema.find(
|
|
'span', attrs={'class': 'headline'})
|
|
item_date = item_headline.find(
|
|
'span', attrs={'class': 'update'})
|
|
newsarticles.append({
|
|
'title': item_headline.contents[0], 'date': item_date, 'url': itema['href'], 'description': ''
|
|
})
|
|
feeds.append(('World', newsarticles))
|
|
return feeds
|