mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-03 11:07:02 -05:00
65 lines
2.2 KiB
Python
65 lines
2.2 KiB
Python
#!/usr/bin/env python2
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
msdn.microsoft.com/en-us/magazine
|
|
'''
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup, BeautifulStoneSoup
|
|
|
|
|
|
class MSDNMagazine_en(BasicNewsRecipe):
|
|
title = 'MSDN Magazine'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'The Microsoft Journal for Developers'
|
|
masthead_url = 'http://i3.msdn.microsoft.com/Platform/MasterPages/MsdnMagazine/smalllogo.png'
|
|
publisher = 'Microsoft Press'
|
|
category = 'news, IT, Microsoft, programming, windows'
|
|
oldest_article = 31
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
encoding = 'utf-8'
|
|
language = 'en'
|
|
|
|
base_url = 'http://msdn.microsoft.com/en-us/magazine/default.aspx'
|
|
rss_url = 'http://msdn.microsoft.com/en-us/magazine/rss/default.aspx?z=z&iss=1'
|
|
|
|
keep_only_tags = [dict(name='div', attrs={'id': 'MainContent'})]
|
|
|
|
remove_tags = [
|
|
dict(name='div', attrs={'class': 'DivRatingsOnly'}), dict(
|
|
name='div', attrs={'class': 'ShareThisButton4'})
|
|
]
|
|
|
|
def find_articles(self):
|
|
idx_contents = self.browser.open(self.rss_url).read()
|
|
idx = BeautifulStoneSoup(
|
|
idx_contents, convertEntities=BeautifulStoneSoup.XML_ENTITIES)
|
|
|
|
for article in idx.findAll('item'):
|
|
desc_html = self.tag_to_string(article.find('description'))
|
|
description = self.tag_to_string(BeautifulSoup(desc_html))
|
|
|
|
a = {
|
|
'title': self.tag_to_string(article.find('title')),
|
|
'url': self.tag_to_string(article.find('link')),
|
|
'description': description,
|
|
'date': self.tag_to_string(article.find('pubdate')),
|
|
}
|
|
yield a
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup(self.base_url)
|
|
|
|
# find issue name, eg "August 2011"
|
|
issue_name = self.tag_to_string(soup.find('h1'))
|
|
|
|
# find cover pic
|
|
img = soup.find('img', attrs={'alt': issue_name})
|
|
if img is not None:
|
|
self.cover_url = img['src']
|
|
|
|
return [(issue_name, list(self.find_articles()))]
|