Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Recipes - Fix and improve Japan Times recipe

Browse Source
This commit is contained in:
Albert Aparicio 2022-02-18 11:32:45 +01:00
parent 484d5ee5d6
commit 4a01a799f1
1 changed files with 46 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
recipes/japan_times.recipe
View File

@ -1,58 +1,69 @@
__license__ = 'GPL v3'
__copyright__ = '2008-2013, Darko Miletic <darko.miletic at gmail.com>'
'''
#!/usr/bin/env python
# -*- coding: utf-8 -*-
__license__ = "GPL v3"
__copyright__ = (
"2008-2013, Darko Miletic <darko.miletic at gmail.com>. "
"2022, Albert Aparicio Isarn <aaparicio at posteo.net>"
)
"""
japantimes.co.jp
'''
"""
from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class JapanTimes(BasicNewsRecipe):
title = 'The Japan Times'
__author__ = 'Darko Miletic'
description = "Daily news and features on Japan from the most widely read English-language newspaper in Japan. Coverage includes national news, business news, sports news, commentary and features on living in Japan, entertainment, the arts, education and more." # noqa
language = 'en_JP'
category = 'news, politics, japan'
publisher = 'The Japan Times'
title = "The Japan Times"
__author__ = "Albert Aparicio Isarn (original recipe by Darko Miletic)"
description = (
"The latest news from Japan Times, Japan's leading English-language daily newspaper"
)
language = "en_JP"
category = "news, politics, japan"
publisher = "The Japan Times"
oldest_article = 2
max_articles_per_feed = 150
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
encoding = 'utf8'
publication_type = 'newspaper'
extra_css = 'body{font-family: Geneva,Arial,Helvetica,sans-serif}'
encoding = "utf8"
publication_type = "newspaper"
masthead_url = "https://cdn-japantimes.com/wp-content/themes/jt_theme/library/img/japantimes-logo-tagline.png"
extra_css = "body{font-family: Geneva,Arial,Helvetica,sans-serif}"
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
"comment": description,
"tags": category,
"publisher": publisher,
"language": language,
}
remove_tags_after = dict(name='div', attrs={'class': 'entry'}),
keep_only_tags = [dict(name='div', attrs={'class': 'padding_block'})]
remove_tags_before = {"name": "h1"}
remove_tags_after = {"name": "ul", "attrs": {"class": "single-sns-area"}}
keep_only_tags = [
{"name": "div", "attrs": {"class": "padding_block"}},
# {"name": "h5", "attrs": {"class": "writer", "role": "author"}},
# {"name": "p", "attrs": {"class": "credit"}},
]
remove_tags = [
dict(name=['iframe', 'embed', 'object', 'base', 'form']), dict(attrs={'class': [
'meta_extras', 'related_articles']}), dict(attrs={'id': 'content_footer_menu'}),
dict(id='no_js_blocker'),
classes('single-sns-area jt-related-stories'),
{"name": "div", "id": "no_js_blocker", "attrs": {"class": "padding_block"}},
{"name": "div", "attrs": {"class": "single-upper-meta"}},
{"name": "ul", "attrs": {"class": "single-sns-area"}},
]
feeds = [
(u'News', u'http://www.japantimes.co.jp/news/feed/'),
(u'Opinion', u'http://www.japantimes.co.jp/opinion/feed/'),
(u'Life', u'http://www.japantimes.co.jp/opinion/feed/'),
(u'Community', u'http://www.japantimes.co.jp/community/feed/'),
(u'Culture', u'http://www.japantimes.co.jp/culture/feed/'),
(u'Sports', u'http://www.japantimes.co.jp/sports/feed/')
(u"Top Stories", u"https://www.japantimes.co.jp/feed/topstories/"),
(u"News", u"https://www.japantimes.co.jp/news/feed/"),
(u"Opinion", u"https://www.japantimes.co.jp/opinion/feed/"),
(u"Life", u"https://www.japantimes.co.jp/life/feed/"),
(u"Community", u"https://www.japantimes.co.jp/community/feed/"),
(u"Culture", u"https://www.japantimes.co.jp/culture/feed/"),
(u"Sports", u"https://www.japantimes.co.jp/sports/feed/"),
]
def get_article_url(self, article):
rurl = BasicNewsRecipe.get_article_url(self, article)
return rurl.partition('?')[0]
return rurl.partition("?")[0]
def preprocess_raw_html(self, raw, url):
return '<html><head>' + raw[raw.find('</head>'):]
return "<html><head>" + raw[raw.find("</head>") :]