Multipage implemented for multiple page articles,
New feeds,
Miscellaneous advertising and junk removed.
Code:
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
'''
discovermagazine.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
class DiscoverMagazine(BasicNewsRecipe):
title = u'Discover Magazine'
description = u'Science, Technology and the Future'
__author__ = 'Starson17'
language = 'en'
oldest_article = 33
max_articles_per_feed = 20
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
encoding = 'utf-8'
extra_css = '.headline {font-size: x-large;} \n .fact {padding-top: 10pt}'
remove_tags = [
dict(name='div', attrs={'id':['searchModule', 'mainMenu', 'tool-box']}),
dict(name='div', attrs={'id':['footer','teaser','already-subscriber','teaser-suite','related-articles']}),
dict(name='div', attrs={'class':['column']}),
dict(name='img', attrs={'src':'http://discovermagazine.com/onebyone.gif'})]
remove_tags_after = [dict(name='div', attrs={'class':'listingBar'})]
def append_page(self, soup, appendtag, position):
pager = soup.find('span',attrs={'class':'next'})
if pager:
nexturl = pager.a['href']
soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'class':'articlebody'})
newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos)
texttag.extract()
appendtag.insert(position,texttag)
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Language" content="en-US"/>\n<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
soup.head.insert(0,mtag)
self.append_page(soup, soup.body, 3)
pager = soup.find('div',attrs={'class':'listingBar'})
if pager:
pager.extract()
return soup
def postprocess_html(self, soup, first_fetch):
for tag in soup.findAll(text=re.compile('^This article is a sample')):
tag.parent.extract()
for tag in soup.findAll(['table', 'tr', 'td']):
tag.name = 'div'
for tag in soup.findAll('div', attrs={'class':'discreet advert'}):
tag.extract()
for tag in soup.findAll('hr', attrs={'size':'1'}):
tag.extract()
for tag in soup.findAll('br'):
tag.extract()
return soup
feeds = [
(u'Technology', u'http://discovermagazine.com/topics/technology/rss.xml'),
(u'Health - Medicine', u'http://discovermagazine.com/topics/health-medicine/rss.xml'),
(u'Mind Brain', u'http://discovermagazine.com/topics/mind-brain/rss.xml'),
(u'Space', u'http://discovermagazine.com/topics/space/rss.xml'),
(u'Human Origins', u'http://discovermagazine.com/topics/human-origins/rss.xml'),
(u'Living World', u'http://discovermagazine.com/topics/living-world/rss.xml'),
(u'Environment', u'http://discovermagazine.com/topics/environment/rss.xml'),
(u'Physics & Math', u'http://discovermagazine.com/topics/physics-math/rss.xml'),
(u"20 Things you didn't know about...", u'http://discovermagazine.com/columns/20-things-you-didnt-know/rss.xml'),
(u'Fuzzy Math', u'http://discovermagazine.com/columns/fuzzy-math/rss.xml'),
(u'The Brain', u'http://discovermagazine.com/columns/the-brain/rss.xml'),
(u'What is This', u'http://discovermagazine.com/columns/what-is-this/rss.xml'),
(u'Vital Signs', u'http://discovermagazine.com/columns/vital-signs/rss.xml'),
(u'Think Tech', u'http://discovermagazine.com/columns/think-tech/rss.xml'),
(u'Future Tech', u'http://discovermagazine.com/columns/future-tech/rss.xml'),
(u'Discover Interview', u'http://discovermagazine.com/columns/discover-interview/rss.xml'),
]