calibre/recipes/foreign_policy.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

82 lines
2.8 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
from collections import OrderedDict
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 ForeignPolicy(BasicNewsRecipe):
title = u'Foreign Policy'
language = 'en'
__author__ = 'Kovid Goyal'
description = 'International News'
no_stylesheets = True
remove_javascript = True
keep_only_tags = [
dict(name='h1'),
classes('dek-heading meta-data figure-image post-content-main'),
dict(attrs={'class': lambda x: x and set(x.split()).intersection(
{'wide_header_bg', 'wide_header_text'})}),
]
remove_tags = [
dict(name=['meta', 'link']),
dict(attrs={'class': ['fp-lightbox--overlay']}),
dict(attrs={'class': lambda x: x and 'share-links' in x}),
]
remove_tags_after = [classes('post-content-main')]
def parse_index(self):
soup = self.index_to_soup('https://foreignpolicy.com/the-magazine')
img = soup.find('img', src=True, attrs={'alt': lambda x: x and 'foreign-policy-magazine-cover' in x})
self.cover_url = img['src']
current_section = None
amap = OrderedDict()
for x in soup.findAll(name=('h2', 'h3')):
if x.name == 'h2':
current_section = self.tag_to_string(x)
self.log(current_section)
if current_section.lower() == 'recent issues':
break
else:
title = self.tag_to_string(x)
a = x.parent
url = a['href']
self.log('\t', title, 'url')
amap.setdefault(current_section, []).append({'title': title, 'url': url})
ans = []
for sec_name in sorted(amap, key=lambda x: x.lower()):
articles = amap[sec_name]
if articles:
ans.append((sec_name, articles))
return ans
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-srcset': True}):
img['src'] = img['data-srcset'].split()[0]
body = soup.find('body')
div = soup.find(
attrs={'class': lambda x: x and 'wide_header_bg' in x.split()})
if div is not None:
div.extract()
body.insert(0, div)
div = soup.find(
attrs={'class': lambda x: x and 'wide_header_text' in x.split()})
if div is not None:
div.extract()
body.insert(0, div)
for div in soup.findAll(id='footer-logo'):
div.parent.extract()
return soup