calibre/recipes/motherjones.recipe

104 lines
4.2 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
from calibre.ptempfile import PersistentTemporaryFile
class MotherJonesRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'en'
version = 1
title = u'Mother Jones'
publisher = u'Mother Jones'
category = u'News, Investigative journalism'
description = u'Independent investigative, political, and social justice reporting. Takes no prisoners, cleaves to no dogma, and tells it like it is.'
oldest_article = 14
max_articles_per_feed = 100
use_embedded_content = False
remove_empty_feeds = True
no_stylesheets = True
remove_javascript = True
simultaneous_downloads = 3
keep_only_tags = []
keep_only_tags.append(dict(name = 'h1'))
keep_only_tags.append(dict(name = 'div', attrs = {'class': 'dek'}))
keep_only_tags.append(dict(name = 'p', attrs = {'class': 'submitted'}))
keep_only_tags.append(dict(name = 'div', attrs = {'class': 'print-content'}))
#keep_only_tags.append(dict(name = '', attrs = {'': ''}))
remove_tags = []
remove_tags.append(dict(name = 'base'))
#remove_tags.append(dict(name = '', attrs = {'': ''}))
remove_attributes = ['style']
# feeds from http://motherjones.com/about/rss
feeds = []
feeds.append((u'Latest News', u'http://feeds.feedburner.com/motherjones/main?format=xml'))
feeds.append((u'Politics & Current Affairs', u'http://motherjones.com/rss/sections/Politics/feed&format=xml'))
feeds.append((u'Environment & Health', u'http://motherjones.com/rss/sections/Environment/feed'))
feeds.append((u'Media & Culture', u'http://motherjones.com/rss/sections/Media/feed'))
feeds.append((u'Blog: Kevin Drum', u'http://motherjones.com/rss/blogs/Kevin+Drum/feed'))
feeds.append((u'Blog: MoJo Blog', u'http://motherjones.com/rss/blogs/mojo/feed'))
feeds.append((u'Blog: Blue Marble', u'http://motherjones.com/rss/blogs/Blue+Marble/feed'))
feeds.append((u'Blog: The Riff', u'http://motherjones.com/rss/blogs/Riff/feed'))
##feeds.append((u'', u''))
extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
img {float: left; margin-right: 0.5em;}
div.dek {font-style: italic;}
p.submitted {font-size: x-small; color: #696969;}
div.mj_support {font-size: x-small; color: #0666666; border: 1px solid black; padding: 0.5em}
a, a[href] {text-decoration: none; color: blue;}
'''
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
'publisher': publisher}
temp_files = []
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
'''
The print version is sort of hard to get. I think they look at the referer header, and if
it is not right they serve the original. This method works around that.
'''
br = self.get_browser()
br.open(url)
response = br.follow_link(url_regex = r'/print/[0-9]+', nr = 0)
html = response.read()
self.temp_files.append(PersistentTemporaryFile('_motherjones.html'))
self.temp_files[-1].write(html)
self.temp_files[-1].close()
return self.temp_files[-1].name
def get_article_url(self, article):
'''
Some of the feeds are served by feedburner (grr). Then the workaround to get their
print version doesn't work anymore. This method provides a workaround.
'''
if hasattr(article, 'feedburner_origlink'):
return article.feedburner_origlink
else:
return article.link
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs = {'src': True}):
if not img['src'].startswith('http://'):
img['src'] = 'http://motherjones.com' + img['src']
div = Tag(soup, 'div', [('class', 'mj_support')])
div.append('''Your tax-deductible gifts help keep Mother Jones independent and uncompromised.
To make a contribution, visit MotherJones.com or call 877-GIV-MOJO.
''')
soup.body.append(div)
return soup