calibre/recipes/the_federalist.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

58 lines
1.8 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
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 Federalist(BasicNewsRecipe):
title = 'The Federalist'
__author__ = 'Kovid Goyal'
language = 'en'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
remove_attributes = ['xmlns', 'lang', 'style', 'width', 'height']
extra_css = '''
.shortbio { margin: 1em; padding: 1em; font-style: italic }
'''
keep_only_tags = [
classes('entry-header'),
classes('wp-post-image post-categories entry-content shortbio byline-month byline-standard alpha-byline'),
]
remove_tags = [
dict(name=['meta', 'link']),
classes('auth-ad attachment-post-thumbnail attachment-author-bio'),
]
feeds = [
('All', 'http://thefederalist.com/feed/'),
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-lazy-src': True}):
img['src'] = img['data-lazy-src']
seen = set()
for img in soup.findAll('img', src=True):
src = img['src']
if src in seen:
img.extract()
seen.add(src)
return soup
# def parse_index(self):
# return [('Articles', [
# {'title':'img', 'url':'http://thefederalist.com/2018/05/09/venezuelas-economic-problems-caused-socialism-not-falling-oil-prices/'},
# {'title':'xxx', 'url':'http://thefederalist.com/2018/05/04/fans-take-on-marvel-dc-and-the-comic-book-industrys-sjw-self-destruction/'},
# ])]