calibre/recipes/entrepeneur.recipe

95 lines
3.5 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
import re
class EntrepeneurMagRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'en'
version = 1
title = u'Entrepeneur Magazine'
publisher = u'Entrepreneur Media, Inc'
category = u'Business'
description = u'Online magazine on business, small business, management and economy'
encoding = 'utf-8'
no_stylesheets = True
remove_javascript = True
keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'printbody'}))
remove_tags = []
remove_tags.append(dict(name = 'base'))
remove_tags.append(dict(name = 'a', attrs = {'id': 'ctl00_privacyPolicyLink'}))
remove_attributes = ['style']
INDEX = 'http://www.entrepeneur.com'
extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
img {float: left; margin-right: 0.5em;}
a, a[href] {text-decoration: none; color: blue;}
div#ctl00_bodyContentPlaceHolder_articleHeader_divHeaderText {font-weight: bold;
font-size: medium;}
h1 {font-size: xx-large; font-weight: bold;}
div.byline {font-size: small; color: #696969; font-weight: normal;}
a.h2 {font-size: medium; font-weight: bold; color: #666666; text-decoration: none;
margin-bottom: 0em;}
'''
conversion_options = {'comments': description, 'language': 'en',
'publisher': publisher}
def parse_index(self):
soup = self.index_to_soup('http://www.entrepreneur.com/magazine/entrepreneur/index.html')
answer = []
div = soup.find('div', attrs = {'id': 'magfeature'})
if div:
a = div.find('a', attrs = {'class': 'headline'})
if a:
title = self.tag_to_string(a)
url = self.INDEX + a['href']
description = a.findNextSibling(text = True)
articles = [{'title': title, 'date': None, 'url': url, 'description': description}]
answer.append(('Cover Story', articles))
for div in soup.findAll('div', attrs = {'class': 'subhead-special'}):
articles = []
for tag in div.findNextSiblings(['a', 'div'], attrs = {'class': ['h2', 'subhead-special']}):
if tag.name == 'div' and tag['class'] == 'subhead-special':
break
if tag.name == 'a' and tag['class'] == 'h2':
title = self.tag_to_string(tag)
url = tag['href']
description = tag.findNextSibling(text = True)
articles.append({'title': title, 'date': None, 'url': url, 'description': description})
answer.append((self.tag_to_string(div), articles))
return answer
def print_version(self, url):
id = url.rpartition('/')[2]
return 'http://www.entrepreneur.com/article/printthis/' + id
def preprocess_html(self, soup):
div = soup.find('div', attrs = {'id': 'printbody'})
if div:
a = div.find(lambda tag: tag.name == 'a' and len(tag.attrs) == 1)
if a:
txt = a.findPreviousSibling(text = re.compile('URL:.*'))
if txt:
txt.extract()
for br in a.findNextSiblings('br'):
br.extract()
a.extract()
return soup