Quote:
Originally Posted by unkn0wn
Code:
"""
www.mainichi.jp/english
"""
from calibre.ptempfile import PersistentTemporaryFile
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'}
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
br = self.get_browser()
try:
br.open(url)
except Exception as e:
url = e.hdrs.get('location')
soup = self.index_to_soup(url)
link = soup.find('a', href=True)
html = br.open(link['href']).read()
pt = PersistentTemporaryFile('.html')
pt.write(html)
pt.close()
return pt.name
feeds = [
('Articles', 'https://news.google.com/rss/search?q=when:48h+allinurl:mainichi.jp%2Fenglish%2Farticles%2F&hl=en-US&gl=US&ceid=US:en')
]
|
Is the fix to add "www"???