mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
73 lines
2.3 KiB
Plaintext
73 lines
2.3 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import re
|
|
|
|
class IncMagazineRecipe(BasicNewsRecipe):
|
|
__license__ = 'GPL v3'
|
|
__author__ = 'kwetal'
|
|
language = 'en'
|
|
version = 1
|
|
|
|
title = u'Inc Magazine'
|
|
publisher = u'Mansueto Ventures LLC'
|
|
category = u'News, Business'
|
|
description = u'Handbook of the American Entrepeneur'
|
|
|
|
use_embedded_content = False
|
|
remove_empty_feeds = True
|
|
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
|
|
INDEX = 'http://www.inc.com/magazine'
|
|
|
|
remove_tags = []
|
|
remove_tags.append(dict(name = 'div', attrs = {'id' : 'advt'}))
|
|
|
|
extra_css = '''
|
|
body{font-family:verdana,arial,helvetica,geneva,sans-serif ;}
|
|
div#deck {font-weight: bold;}
|
|
div.byline {font-size: x-small; color: #696969; margin-top: 0.4em;}
|
|
'''
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup(self.INDEX)
|
|
self.browser.open(self.INDEX)
|
|
|
|
url = self.browser.geturl()
|
|
date = url.rpartition('/')[0].rpartition('/')[2]
|
|
self.title = self.title + ' ' + date[4:6] + ', ' + date[0:4]
|
|
|
|
answer = []
|
|
|
|
for feature in soup.findAll('div', attrs = {'class': re.compile('magazinesection.*')}):
|
|
h2 = feature.find('h2')
|
|
if h2:
|
|
feedTitle = self.tag_to_string(h2)
|
|
else:
|
|
img = feature.find('img', attrs = {'class': 'howtohead'})
|
|
if img:
|
|
feedTitle = img['alt']
|
|
else:
|
|
feedTitle = 'Unknown Feature'
|
|
|
|
articles = []
|
|
for div in feature.findAll('div', attrs = {'class': re.compile('article.*|column.*')}):
|
|
h3 = div.find('h3')
|
|
title = self.tag_to_string(h3)
|
|
href = h3.a['href'].replace('.html', '_Printer_Friendly.html')
|
|
p = div.find('p', attrs = {'class': 'deck'})
|
|
description = self.tag_to_string(p)
|
|
|
|
articles.append({'title': title, 'date': u'', 'url': href, 'description': description})
|
|
|
|
answer.append((feedTitle, articles))
|
|
|
|
return answer
|
|
|
|
def preprocess_html(self, soup):
|
|
img = soup.find('img', attrs = {'src': 'http://images.inc.com/nav/lofi_logo.gif'})
|
|
if img:
|
|
img.parent.extract()
|
|
|
|
return soup
|