Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #831622 (Updated recipe for MSDN Magazine)

Browse Source
This commit is contained in:
Kovid Goyal 2011-08-22 14:46:39 -06:00
parent e48e7932fa
commit 101817b1fc
1 changed files with 37 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
recipes/msdnmag_en.recipe
View File

@ -6,11 +6,13 @@ __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, Tag
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
@ -19,25 +21,45 @@ class MSDNMagazine_en(BasicNewsRecipe):
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'
feeds = [(u'Articles', u'http://msdn.microsoft.com/en-us/magazine/rss/default.aspx?z=z&iss=1')]
keep_only_tags = [dict(name='div', attrs={'class':'navpage'})]
keep_only_tags = [dict(name='div', attrs={'id':'MainContent'})]
remove_tags = [
dict(name=['object','link','base','table'])
,dict(name='div', attrs={'class':'MTPS_CollapsibleRegion'})
dict(name='div', attrs={'class':'DivRatingsOnly'})
,dict(name='div', attrs={'class':'ShareThisButton4'})
]
remove_tags_after = dict(name='div', attrs={'class':'navpage'})
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 preprocess_html(self, soup):
for item in soup.findAll('div',attrs={'class':['FeatureSmallHead','ColumnTypeSubTitle']}):
item.name="h2"
for item in soup.findAll('div',attrs={'class':['FeatureHeadline','ColumnTypeTitle']}):
item.name="h1"
for item in soup.findAll('div',attrs={'class':'ArticleTypeTitle'}):
item.name="h3"
return soup
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()))]