mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
51 lines
1.4 KiB
Python
51 lines
1.4 KiB
Python
#!/usr/bin/env python
|
|
'''
|
|
www.mainichi.jp/english
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class MainichiEnglishNews(BasicNewsRecipe):
|
|
title = u'The Mainichi'
|
|
__author__ = 'unkn0wn'
|
|
|
|
description = 'Japanese traditional newspaper Mainichi news in English'
|
|
publisher = 'Mainichi News'
|
|
publication_type = 'newspaper'
|
|
category = 'news, japan'
|
|
language = 'en_JP'
|
|
|
|
index = 'http://mainichi.jp/english/'
|
|
masthead_url = index + 'images/themainichi.png'
|
|
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
auto_cleanup = True
|
|
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
|
|
def parse_index(self):
|
|
index = 'https://mainichi.jp/english/'
|
|
sections = [
|
|
'articles'
|
|
]
|
|
feeds = []
|
|
soup = self.index_to_soup(index)
|
|
for sec in sections:
|
|
section = sec.capitalize()
|
|
self.log(section)
|
|
articles = []
|
|
for a in soup.findAll('a', attrs={'href':lambda x: x and 'articles' in x}):
|
|
if a.find('img'):
|
|
continue
|
|
url = a['href']
|
|
if not url.startswith('http'):
|
|
url = 'https:' + url
|
|
title = self.tag_to_string(a)
|
|
self.log('\t', title, '\n\t\t', url)
|
|
articles.append({'title': title, 'url': url})
|
|
if articles:
|
|
feeds.append((section, articles))
|
|
return feeds
|