mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
65 lines
2.2 KiB
Plaintext
65 lines
2.2 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 MainichiEnglishNews(BasicNewsRecipe):
|
|
title = u'The Mainichi'
|
|
__author__ = 'Hiroshi Miura'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 40
|
|
description = 'Japanese traditional newspaper Mainichi news in English'
|
|
publisher = 'Mainichi News'
|
|
category = 'news, japan'
|
|
language = 'en_JP'
|
|
index = 'http://mainichi.jp/english/english/index.html'
|
|
remove_javascript = True
|
|
masthead_url = 'http://mainichi.jp/english/images/themainichi.png'
|
|
|
|
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)
|
|
for section in soup.findAll('section'):
|
|
newsarticles = []
|
|
section_name = 'news'
|
|
hds = section.find('div', attrs={'class': 'CategoryHead clr'})
|
|
if hds:
|
|
section_item = hds.find('h1')
|
|
if section_item:
|
|
section_name = section_item.find('a').string
|
|
items = section.find('ul', attrs={'class': 'MaiLink'})
|
|
for item in items.findAll('li'):
|
|
if item:
|
|
itema = item.find('a')
|
|
newsarticles.append({
|
|
'title': itema.string, 'date': '', 'url': itema['href'], 'description': ''
|
|
})
|
|
feeds.append((section_name, newsarticles))
|
|
return feeds
|