calibre/recipes/noaa.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

49 lines
1.6 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
noaa.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
def new_tag(soup, name, attrs=()):
impl = getattr(soup, 'new_tag', None)
if impl is not None:
return impl(name, attrs=dict(attrs))
return Tag(soup, name, attrs=attrs or None)
class NOAA(BasicNewsRecipe):
title = 'NOAA Online'
__author__ = 'Darko Miletic'
description = 'NOAA'
publisher = 'NOAA'
category = 'news, science, US, ocean'
oldest_article = 15
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
simultaneous_downloads = 1
encoding = 'utf-8'
lang = 'en-US'
language = 'en'
remove_tags = [dict(name=['embed', 'object']), dict(name='div', attrs={'id': 'leftNav'}), dict(name='div', attrs={'id': 'topNav'}), dict(name='div', attrs={'class': 'feedback_box'}), dict(name='div', attrs={'id': 'midBlock'}), dict(name='div', attrs={'id': 'footer'}) ] # noqa
feeds = [(u'NOAA articles', u'http://www.noaa.gov/rss/noaarss.xml')]
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
mlang = new_tag(soup, 'meta', [
("http-equiv", "Content-Language"), ("content", self.lang)])
mcharset = new_tag(soup, 'meta', [
("http-equiv", "Content-Type"), ("content", "text/html; charset=UTF-8")])
soup.head.insert(0, mlang)
soup.head.insert(1, mcharset)
return self.adeify_images(soup)