mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
91 lines
3.4 KiB
Python
91 lines
3.4 KiB
Python
#!/usr/bin/env python2
|
|
# vim:fileencoding=utf-8
|
|
from __future__ import (unicode_literals, division, absolute_import,
|
|
print_function)
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
|
|
from collections import defaultdict, OrderedDict
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
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'),
|
|
dict(name='p', attrs={'class': 'dek'}),
|
|
dict(name='li', attrs={'class': 'author'}),
|
|
dict(attrs={'class': ['feature', 'post-inner',
|
|
'inline_photo', 'infographic']}),
|
|
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}),
|
|
]
|
|
|
|
def parse_index(self):
|
|
title_map = OrderedDict()
|
|
soup = self.index_to_soup('http://foreignpolicy.com/')
|
|
img = soup.find('img', alt='Current Issue',
|
|
attrs={'data-issue_slug': True})
|
|
self.cover_url = img['src']
|
|
slug = img['data-issue_slug']
|
|
url = 'https://foreignpolicymag.wordpress.com/wp-admin/admin-ajax.php?action=mag_issue_request&issue_slug=' + slug
|
|
soup = self.index_to_soup(url)
|
|
ul = soup.find(id='mag-terms')
|
|
self.timefmt = ' ' + self.tag_to_string(ul.find('li'))
|
|
for li in ul.findAll('li', attrs={'data-cat': True}):
|
|
title_map[li['data-cat']] = self.tag_to_string(li)
|
|
feeds = defaultdict(list)
|
|
for ul in soup.findAll('ul', attrs={'data-cat': lambda x: x and x in title_map}):
|
|
sec = ul['data-cat']
|
|
self.log('\nFound section:', title_map[sec])
|
|
articles = []
|
|
for li in ul.findAll('li'):
|
|
a = li.find('a', href=True)
|
|
url = a['href']
|
|
title = self.tag_to_string(a)
|
|
desc = ''
|
|
dek = li.find(attrs={'class': 'dek'})
|
|
if dek is not None:
|
|
desc += self.tag_to_string(dek)
|
|
aut = li.find(attrs={'class': 'author'})
|
|
if aut is not None:
|
|
desc += ' by ' + self.tag_to_string(aut)
|
|
self.log('\t', title, ' at ', url)
|
|
if desc:
|
|
self.log('\t\t', desc)
|
|
articles.append(
|
|
{'title': title, 'description': desc, 'url': url})
|
|
if articles:
|
|
feeds[sec].extend(articles)
|
|
|
|
return [(title_map[x], feeds[x]) for x in title_map if feeds[x]]
|
|
|
|
def preprocess_html(self, soup):
|
|
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
|