mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
Update Foreign Policy
This commit is contained in:
parent
350494d016
commit
dadef1ffb9
@ -5,11 +5,17 @@ from __future__ import absolute_import, division, print_function, unicode_litera
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
|
||||
from collections import defaultdict, OrderedDict
|
||||
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'
|
||||
@ -20,10 +26,7 @@ class ForeignPolicy(BasicNewsRecipe):
|
||||
|
||||
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']}),
|
||||
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'})}),
|
||||
]
|
||||
@ -32,47 +35,36 @@ class ForeignPolicy(BasicNewsRecipe):
|
||||
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):
|
||||
title_map = OrderedDict()
|
||||
soup = self.index_to_soup('http://foreignpolicy.com/')
|
||||
img = soup.find('img', alt='Current Issue',
|
||||
attrs={'data-issue_slug': True})
|
||||
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']
|
||||
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)
|
||||
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']
|
||||
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})
|
||||
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:
|
||||
feeds[sec].extend(articles)
|
||||
|
||||
return [(title_map[x], feeds[x]) for x in title_map if feeds[x]]
|
||||
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()})
|
||||
|
Loading…
x
Reference in New Issue
Block a user