| 1 |
#!/usr/bin/env python |
| 2 |
""" |
| 3 |
www.mainichi.jp/english |
| 4 |
""" |
| 5 |
|
| 6 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 7 |
|
| 8 |
|
| 9 |
class MainichiEnglishNews(BasicNewsRecipe): |
| 10 |
title = 'The Mainichi' |
| 11 |
__author__ = 'unkn0wn' |
| 12 |
|
| 13 |
description = 'Japanese traditional newspaper Mainichi news in English' |
| 14 |
publisher = 'Mainichi News' |
| 15 |
publication_type = 'newspaper' |
| 16 |
category = 'news, japan' |
| 17 |
language = 'en_JP' |
| 18 |
|
| 19 |
index = 'http://mainichi.jp/english/' |
| 20 |
masthead_url = index + 'images/themainichi.png' |
| 21 |
|
| 22 |
no_stylesheets = True |
| 23 |
remove_javascript = True |
| 24 |
auto_cleanup = True |
| 25 |
|
| 26 |
ignore_duplicate_articles = {'title', 'url'} |
| 27 |
|
| 28 |
def parse_index(self): |
| 29 |
index = 'https://mainichi.jp/english/' |
| 30 |
sections = ['articles'] |
| 31 |
feeds = [] |
| 32 |
soup = self.index_to_soup(index) |
| 33 |
for sec in sections: |
| 34 |
section = sec.capitalize() |
| 35 |
self.log(section) |
| 36 |
articles = [] |
| 37 |
for a in soup.findAll('a', attrs={'href': lambda x: x and 'articles' in x}): |
| 38 |
if a.find('img'): |
| 39 |
continue |
| 40 |
url = a['href'] |
| 41 |
if not url.startswith('http'): |
| 42 |
url = 'https:' + url |
| 43 |
title = self.tag_to_string(a) |
| 44 |
self.log('\t', title, '\n\t\t', url) |
| 45 |
articles.append({'title': title, 'url': url}) |
| 46 |
if articles: |
| 47 |
feeds.append((section, articles)) |
| 48 |
return feeds |