mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
104 lines
3.6 KiB
Python
104 lines
3.6 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
'''
|
|
theatlantic.com
|
|
'''
|
|
import re
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Tag, NavigableString
|
|
|
|
class TheAtlantic(BasicNewsRecipe):
|
|
|
|
title = 'The Atlantic'
|
|
__author__ = 'Kovid Goyal and Sujata Raman'
|
|
description = 'Current affairs and politics focussed on the US'
|
|
INDEX = 'http://www.theatlantic.com/magazine/toc/0/'
|
|
language = 'en'
|
|
|
|
remove_tags_before = dict(name='div', id='articleHead')
|
|
remove_tags_after = dict(id='copyright')
|
|
remove_tags = [dict(id=['header', 'printAds', 'pageControls'])]
|
|
no_stylesheets = True
|
|
|
|
preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
|
|
|
|
|
|
def print_version(self, url):
|
|
return url.replace('/archive/', '/print/')
|
|
|
|
def parse_index(self):
|
|
articles = []
|
|
|
|
soup = self.index_to_soup(self.INDEX)
|
|
ts = soup.find(id='magazineTopStories')
|
|
ds = self.tag_to_string(ts.find('h1')).split(':')[-1]
|
|
self.timefmt = ' [%s]'%ds
|
|
|
|
cover = soup.find('img', src=True, attrs={'class':'cover'})
|
|
if cover is not None:
|
|
self.cover_url = cover['src']
|
|
|
|
feeds = []
|
|
seen_titles = set([])
|
|
for section in soup.findAll('div', attrs={'class':'magazineSection'}):
|
|
section_title = self.tag_to_string(section.find('h2'))
|
|
self.log('Found section:', section_title)
|
|
articles = []
|
|
for post in section.findAll('div', attrs={'class':lambda x : x and
|
|
'post' in x}):
|
|
h = post.find(['h3', 'h4'])
|
|
title = self.tag_to_string(h)
|
|
if title in seen_titles:
|
|
continue
|
|
seen_titles.add(title)
|
|
a = post.find('a', href=True)
|
|
url = a['href']
|
|
if url.startswith('/'):
|
|
url = 'http://www.theatlantic.com'+url
|
|
p = post.find('p', attrs={'class':'dek'})
|
|
desc = None
|
|
self.log('\tFound article:', title, 'at', url)
|
|
if p is not None:
|
|
desc = self.tag_to_string(p)
|
|
self.log('\t\t', desc)
|
|
articles.append({'title':title, 'url':url, 'description':desc,
|
|
'date':''})
|
|
if articles:
|
|
feeds.append((section_title, articles))
|
|
|
|
poems = []
|
|
self.log('Found section: Poems')
|
|
pd = soup.find('h2', text='Poetry').parent.parent
|
|
for poem in pd.findAll('h4'):
|
|
title = self.tag_to_string(poem)
|
|
url = poem.find('a')['href']
|
|
if url.startswith('/'):
|
|
url = 'http://www.theatlantic.com' + url
|
|
self.log('\tFound article:', title, 'at', url)
|
|
poems.append({'title':title, 'url':url, 'description':'',
|
|
'date':''})
|
|
if poems:
|
|
feeds.append(('Poems', poems))
|
|
|
|
return feeds
|
|
|
|
def postprocess_html(self, soup, first):
|
|
for table in soup.findAll('table', align='right'):
|
|
img = table.find('img')
|
|
if img is not None:
|
|
img.extract()
|
|
caption = self.tag_to_string(table).strip()
|
|
div = Tag(soup, 'div')
|
|
div['style'] = 'text-align:center'
|
|
div.insert(0, img)
|
|
div.insert(1, Tag(soup, 'br'))
|
|
if caption:
|
|
div.insert(2, NavigableString(caption))
|
|
table.replaceWith(div)
|
|
|
|
return soup
|
|
|