mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
100 lines
3.8 KiB
Python
100 lines
3.8 KiB
Python
#!/usr/bin/env python2
|
|
from __future__ import unicode_literals
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
'''
|
|
theatlantic.com
|
|
'''
|
|
import html5lib
|
|
from lxml import html
|
|
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 TheAtlantic(BasicNewsRecipe):
|
|
|
|
title = 'The Atlantic'
|
|
__author__ = 'Kovid Goyal'
|
|
description = 'Current affairs and politics focussed on the US'
|
|
INDEX = 'http://www.theatlantic.com/magazine/'
|
|
language = 'en'
|
|
encoding = 'utf-8'
|
|
|
|
keep_only_tags = [
|
|
classes(
|
|
'article-header article-body article-magazine metadata article-cover-content lead-img'),
|
|
]
|
|
remove_tags = [
|
|
{'name': ['meta', 'link', 'noscript']},
|
|
{'attrs': {'class': ['offset-wrapper', 'ad-boxfeatures-wrapper']}},
|
|
{'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']
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
br.set_cookie('inEuropeanUnion', '0', '.theatlantic.com')
|
|
return br
|
|
|
|
def preprocess_raw_html(self, raw, url):
|
|
return html.tostring(html5lib.parse(raw, treebuilder='lxml', namespaceHTMLElements=False), method='html', encoding=unicode)
|
|
|
|
def print_version(self, url):
|
|
return url + '?single_page=true'
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-src': True}):
|
|
img['src'] = img['data-src']
|
|
return soup
|
|
|
|
def parse_index(self):
|
|
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}):
|
|
if 'section-name' in h2['class'].split():
|
|
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 h2['class'].split():
|
|
title = self.tag_to_string(h2)
|
|
a = h2.findParent('a', href=True)
|
|
url = a['href']
|
|
if url.startswith('/'):
|
|
url = 'http://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
|