There are very few recipes in Japanese so I wrote a recipe which scrapes the NHK news site. But it sometimes downloads and sometimes hang and I'm not sure why it's so inconsistent. Does anyone have any advice?
from calibre.web.feeds.news import BasicNewsRecipe
class ReutersJa(BasicNewsRecipe):
# feed source: https://www.nhk.or.jp/toppage/rss/index.html
title = 'NHK News'
description = 'NHK News in Japanese'
__author__ = 'Richard A. Steps'
use_embedded_content = False
language = 'ja'
max_articles_per_feed = 30
remove_javascript = True
auto_cleanup = True
feeds = [(
'主要ニュース', 'https://www.nhk.or.jp/rss/news/cat0.xml?format=xml'),
('社会', 'https://www.nhk.or.jp/rss/news/cat1.xml?format=xml'),
('科学・医療', 'https://www.nhk.or.jp/rss/news/cat3.xml?format=xml'),
('政治', 'https://www.nhk.or.jp/rss/news/cat4.xml?format=xml'),
('経済', 'https://www.nhk.or.jp/rss/news/cat5.xml?format=xml'),
('国際', 'https://www.nhk.or.jp/rss/news/cat6.xml?format=xml'),
('スポーツ', 'https://www.nhk.or.jp/rss/news/cat7.xml?format=xml'),
('文化・エンタメ', 'https://www.nhk.or.jp/rss/news/cat2.xml?format=xml')
]
from calibre.web.feeds.news import BasicNewsRecipe
class ReutersJa(BasicNewsRecipe):
# feed source: https://www.nhk.or.jp/toppage/rss/index.html
title = 'NHK News'
description = 'NHK News in Japanese'
__author__ = 'Richard A. Steps'
use_embedded_content = False
language = 'ja'
max_articles_per_feed = 30
remove_javascript = True
auto_cleanup = True
feeds = [(
'主要ニュース', 'https://www.nhk.or.jp/rss/news/cat0.xml?format=xml'),
('社会', 'https://www.nhk.or.jp/rss/news/cat1.xml?format=xml'),
('科学・医療', 'https://www.nhk.or.jp/rss/news/cat3.xml?format=xml'),
('政治', 'https://www.nhk.or.jp/rss/news/cat4.xml?format=xml'),
('経済', 'https://www.nhk.or.jp/rss/news/cat5.xml?format=xml'),
('国際', 'https://www.nhk.or.jp/rss/news/cat6.xml?format=xml'),
('スポーツ', 'https://www.nhk.or.jp/rss/news/cat7.xml?format=xml'),
('文化・エンタメ', 'https://www.nhk.or.jp/rss/news/cat2.xml?format=xml')
]






