mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
206 lines
8.4 KiB
Python
206 lines
8.4 KiB
Python
#!/usr/bin/env python
|
|
from __future__ import unicode_literals
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
'''
|
|
Recipe for web and magazine versions of the The Atlantic
|
|
'''
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
web_version = True
|
|
test_article = None
|
|
# test_article = 'https://www.theatlantic.com/health/archive/2020/12/covid-19-second-surge/617415/?utm_source=feed'
|
|
|
|
|
|
def classes(classes):
|
|
q = frozenset(classes.split(' '))
|
|
return dict(
|
|
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
|
|
)
|
|
|
|
|
|
def prefix_classes(classes):
|
|
q = classes.split()
|
|
|
|
def test(x):
|
|
if x:
|
|
for cls in x.split():
|
|
for c in q:
|
|
if cls.startswith(c):
|
|
return True
|
|
return False
|
|
return dict(attrs={'class': test})
|
|
|
|
|
|
class TheAtlantic(BasicNewsRecipe):
|
|
|
|
if web_version:
|
|
title = 'TheAtlantic.com'
|
|
description = 'News and editorial about politics, culture, entertainment, tech, etc. Contains many articles not seen in The Atlantic magazine'
|
|
else:
|
|
title = 'The Atlantic'
|
|
description = 'Current affairs and politics focussed on the US'
|
|
INDEX = 'https://www.theatlantic.com/magazine/'
|
|
|
|
__author__ = 'Kovid Goyal'
|
|
language = 'en'
|
|
encoding = 'utf-8'
|
|
|
|
keep_only_tags = [
|
|
dict(itemprop=['headline']),
|
|
classes(
|
|
'c-article-header__hed c-rubric article-header c-article-meta c-lead-media'
|
|
' lead-img article-cover-extra article-body article-magazine article-cover-content'
|
|
),
|
|
prefix_classes(
|
|
'ArticleHeader_root__ ArticleLayoutSection_main__'
|
|
),
|
|
dict(itemprop='articleBody'),
|
|
# these are for photos articles
|
|
dict(id='article-header'),
|
|
classes('photos'),
|
|
]
|
|
remove_tags = [
|
|
classes(
|
|
'c-ad c-share-social c-recirculation-link social-kit-top letter-writer-info callout secondary-byline embed-wrapper'
|
|
' offset-wrapper boxtop-most-popular social-icons hints read-more c-article-writer__social'
|
|
),
|
|
prefix_classes('ArticleRecirc_inline__'),
|
|
{
|
|
'name': ['meta', 'link', 'noscript', 'aside', 'h3']
|
|
},
|
|
{
|
|
'attrs': {
|
|
'class': ['offset-wrapper', 'boxtop-most-popular']
|
|
}
|
|
},
|
|
{
|
|
'attrs': {
|
|
'class': lambda x: x and 'article-tools' in x
|
|
}
|
|
},
|
|
{
|
|
'src': lambda x: x and 'spotxchange.com' in x
|
|
},
|
|
]
|
|
remove_tags_after = classes('article-body')
|
|
|
|
no_stylesheets = True
|
|
remove_attributes = ['style']
|
|
extra_css = '''
|
|
.credit { text-align: right; font-size: 75%; display: block }
|
|
.figcaption { font-size: 75% }
|
|
.caption { font-size: 75% }
|
|
.lead-img { display: block }
|
|
p.dropcap:first-letter {
|
|
float: left; text-transform: uppercase; font-weight: bold; font-size: 5.55em; line-height: 0.83;
|
|
margin: 0; padding-right: 7px; margin-bottom: -2px; text-align: center;
|
|
}
|
|
'''
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
br.set_cookie('inEuropeanUnion', '0', '.theatlantic.com')
|
|
return br
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-srcset': True}):
|
|
# img['src'] = img['data-srcset'].split()[0]
|
|
data_srcset = img['data-srcset']
|
|
if ',' in data_srcset:
|
|
img['src'] = data_srcset.split(',')[0]
|
|
else:
|
|
img['src'] = data_srcset.split()[0]
|
|
for img in soup.findAll('img', attrs={'data-src': True}):
|
|
img['src'] = img['data-src']
|
|
return soup
|
|
|
|
def print_version(self, url):
|
|
ans = url.partition('?')[0] + '?single_page=true'
|
|
if '/video/' in ans:
|
|
ans = None
|
|
return ans
|
|
|
|
if web_version and not test_article:
|
|
|
|
use_embedded_content = False
|
|
|
|
feeds = [
|
|
('The Atlantic', 'https://www.theatlantic.com/feed/all/'),
|
|
('Best of The Atlantic', 'https://www.theatlantic.com/feed/best-of/'),
|
|
('Politics | The Atlantic', 'https://www.theatlantic.com/feed/channel/politics/'),
|
|
('Business | The Atlantic', 'https://www.theatlantic.com/feed/channel/business/'),
|
|
('Culture | The Atlantic', 'https://www.theatlantic.com/feed/channel/entertainment/'),
|
|
('Global | The Atlantic', 'https://www.theatlantic.com/feed/channel/international/'),
|
|
('Technology | The Atlantic', 'https://www.theatlantic.com/feed/channel/technology/'),
|
|
('U.S. | The Atlantic', 'https://www.theatlantic.com/feed/channel/national/'),
|
|
('Health | The Atlantic', 'https://www.theatlantic.com/feed/channel/health/'),
|
|
('Video | The Atlantic', 'https://www.theatlantic.com/feed/channel/video/'),
|
|
('Sexes | The Atlantic', 'https://www.theatlantic.com/feed/channel/sexes/'),
|
|
('Education | The Atlantic', 'https://www.theatlantic.com/feed/channel/education/'),
|
|
('Science | The Atlantic', 'https://www.theatlantic.com/feed/channel/science/'),
|
|
('News | The Atlantic', 'https://www.theatlantic.com/feed/channel/news/'),
|
|
('Press Releases | The Atlantic', 'https://www.theatlantic.com/feed/channel/press-releases/'),
|
|
('Newsletters | The Atlantic', 'https://www.theatlantic.com/feed/channel/newsletters/'),
|
|
('The Atlantic Photo', 'https://feeds.feedburner.com/theatlantic/infocus'),
|
|
('Notes | The Atlantic', 'https://feeds.feedburner.com/TheAtlanticNotes'),
|
|
]
|
|
else:
|
|
def parse_index(self):
|
|
if test_article:
|
|
return [('Articles', [{'title': 'Test article', 'url': test_article}])]
|
|
soup = self.index_to_soup(self.INDEX)
|
|
figure = soup.find('figure', id='cover-image')
|
|
if figure is not None:
|
|
img = figure.find('img', src=True)
|
|
if img:
|
|
self.cover_url = img['src']
|
|
current_section, current_articles = 'Cover Story', []
|
|
feeds = []
|
|
for div in soup.findAll('div', attrs={'class': lambda x: x and set(x.split()).intersection({'top-sections', 'bottom-sections'})}):
|
|
for h2 in div.findAll('h2', attrs={'class': True}):
|
|
cls = h2['class']
|
|
if hasattr(cls, 'split'):
|
|
cls = cls.split()
|
|
if 'section-name' in cls:
|
|
if current_articles:
|
|
feeds.append((current_section, current_articles))
|
|
current_articles = []
|
|
current_section = self.tag_to_string(h2)
|
|
self.log('\nFound section:', current_section)
|
|
elif 'hed' in cls:
|
|
title = self.tag_to_string(h2)
|
|
a = h2.findParent('a', href=True)
|
|
if a is None:
|
|
continue
|
|
url = a['href']
|
|
if url.startswith('/'):
|
|
url = 'https://www.theatlantic.com' + url
|
|
li = a.findParent(
|
|
'li',
|
|
attrs={'class': lambda x: x and 'article' in x.split()}
|
|
)
|
|
desc = ''
|
|
dek = li.find(
|
|
attrs={'class': lambda x: x and 'dek' in x.split()}
|
|
)
|
|
if dek is not None:
|
|
desc += self.tag_to_string(dek)
|
|
byline = li.find(
|
|
attrs={'class': lambda x: x and 'byline' in x.split()}
|
|
)
|
|
if byline is not None:
|
|
desc += ' -- ' + self.tag_to_string(byline)
|
|
self.log('\t', title, 'at', url)
|
|
if desc:
|
|
self.log('\t\t', desc)
|
|
current_articles.append({
|
|
'title': title,
|
|
'url': url,
|
|
'description': desc
|
|
})
|
|
if current_articles:
|
|
feeds.append((current_section, current_articles))
|
|
return feeds
|