calibre/recipes/foreign_policy.recipe

95 lines
3.4 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 defaultdict
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
remove_empty_feeds = True
resolve_internal_links = True
encoding = 'utf-8'
remove_attributes = ['style', 'height', 'width']
extra_css = '''
img {display:block; margin:0 auto;}
.department-meta { font-size:small; color:#404040; }
.dek-heading, .author-bio, .date-time { font-size:small; color:#202020; }
.figure-image, .caption, .wp-caption { font-size:small; text-align:center; }
'''
keep_only_tags = [
dict(name='article', attrs={'class':'article'})
]
remove_tags = [
dict(name=['meta', 'link', 'svg', 'button', 'iframe', 'aside']),
classes(
'share-links content-ungated related-articles fp-lightbox--overlay more-text myfp-article '
'editors-note-in-post--v2 author-photo related-articles-carousel sidebar-box_right '
),
]
remove_tags_after = [classes('post-content-main')]
recipe_specific_options = {
'issue': {
'short': 'Enter the Issue ID you want to download ',
'long': 'For example, 411131563'
}
}
def parse_index(self):
issue_url = 'https://foreignpolicy.com/the-magazine'
d = self.recipe_specific_options.get('issue')
if d and isinstance(d, str):
issue_url = issue_url + '/?issue_id=' + d
soup = self.index_to_soup(issue_url)
img = soup.find('img', attrs={'src': lambda x: x and '-cover' in x})
if img:
self.cover_url = img['src'].split('?')[0] + '?w=800?quality=90'
current_section = None
feeds_dict = defaultdict(list)
soup = soup.find('main')
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']
desc = ''
meta = a.findNext(attrs={'class':'meta-data -excerpt'})
if meta:
desc += self.tag_to_string(meta)
dek = a.findNext(attrs={'class':'dek-heading -excerpt'})
if dek:
desc += ' | ' + self.tag_to_string(dek)
self.log('\t', title, url, '\n\t', desc)
feeds_dict[current_section].append({'title': title, 'url': url, 'description': desc})
return list(feeds_dict.items())
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'src':True}):
img['src'] = img['src'].split('?')[0] + '?w=600?quality=90'
return soup