Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #7561 (Updated recipe for The Moscow Times)

Browse Source
This commit is contained in:
Kovid Goyal 2010-11-16 08:22:21 -07:00
parent a6286dcfda
commit e5c8638af6
2 changed files with 41 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
resources/images/news/moscow_times.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.0 KiB

82
resources/recipes/moscow_times.recipe
View File

@ -1,31 +1,33 @@
#!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
moscowtimes.ru www.themoscowtimes.com
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Moscowtimes(BasicNewsRecipe): class Moscowtimes(BasicNewsRecipe):
title = u'The Moscow Times' title = 'The Moscow Times'
__author__ = 'Darko Miletic and Sujata Raman' __author__ = 'Darko Miletic and Sujata Raman'
description = 'News from Russia' description = 'The Moscow Times is a daily English-language newspaper featuring objective, reliable news on business, politics, sports and culture in Moscow, in Russia and the former Soviet Union (CIS).'
language = 'en' category = 'Russia, Moscow, Russian news, Moscow news, Russian newspaper, daily news, independent news, reliable news, USSR, Soviet Union, CIS, Russian politics, Russian business, Russian culture, Russian opinion, St Petersburg, Saint Petersburg'
lang = 'en' publisher = 'The Moscow Times'
oldest_article = 7 language = 'en'
oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
#encoding = 'utf-8' remove_empty_feeds = True
encoding = 'cp1252' encoding = 'cp1251'
remove_javascript = True masthead_url = 'http://www.themoscowtimes.com/bitrix/templates/tmt/img/logo.gif'
publication_type = 'newspaper'
conversion_options = { conversion_options = {
'comment' : description 'comment' : description
, 'language' : lang , 'tags' : category
} , 'publisher' : publisher
, 'language' : language
}
extra_css = ''' extra_css = '''
h1{ color:#0066B3; font-family: Georgia,serif ; font-size: large} h1{ color:#0066B3; font-family: Georgia,serif ; font-size: large}
@ -35,39 +37,37 @@ class Moscowtimes(BasicNewsRecipe):
.text{font-family:Arial,Tahoma,Verdana,Helvetica,sans-serif ; font-size:75%; } .text{font-family:Arial,Tahoma,Verdana,Helvetica,sans-serif ; font-size:75%; }
''' '''
feeds = [ feeds = [
(u'The Moscow Times Top Stories' , u'http://www.themoscowtimes.com/rss/top'), (u'Top Stories' , u'http://www.themoscowtimes.com/rss/top' )
(u'The Moscow Times Current Issue' , u'http://www.themoscowtimes.com/rss/issue'), ,(u'Current Issue' , u'http://www.themoscowtimes.com/rss/issue' )
(u'The Moscow Times News' , u'http://www.themoscowtimes.com/rss/news'), ,(u'News' , u'http://www.themoscowtimes.com/rss/news' )
(u'The Moscow Times Business' , u'http://www.themoscowtimes.com/rss/business'), ,(u'Business' , u'http://www.themoscowtimes.com/rss/business')
(u'The Moscow Times Art and Ideas' , u'http://www.themoscowtimes.com/rss/art'), ,(u'Art and Ideas' , u'http://www.themoscowtimes.com/rss/art' )
(u'The Moscow Times Opinion' , u'http://www.themoscowtimes.com/rss/opinion') ,(u'Opinion' , u'http://www.themoscowtimes.com/rss/opinion' )
] ]
keep_only_tags = [ keep_only_tags = [dict(name='div', attrs={'id':'content'})]
dict(name='div', attrs={'class':['newstextblock']})
]
remove_tags = [ remove_tags = [
dict(name='div', attrs={'class':['photo_nav']}) dict(name='div', attrs={'class':['photo_nav','phototext']})
] ,dict(name=['iframe','meta','base','link','embed','object'])
]
def preprocess_html(self, soup): def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang for lnk in soup.findAll('a'):
soup.html['lang'] = self.lang if lnk.string is not None:
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">' ind = self.tag_to_string(lnk)
soup.head.insert(0,mtag) lnk.replaceWith(ind)
return soup
return self.adeify_images(soup)
def print_version(self, url):
return url.replace('.themoscowtimes.com/','.themoscowtimes.com/print/')
def get_cover_url(self): def get_cover_url(self):
cover_url = None
href = 'http://www.themoscowtimes.com/pdf/' href = 'http://www.themoscowtimes.com/pdf/'
soup = self.index_to_soup(href)
soup = self.index_to_soup(href)
div = soup.find('div',attrs={'class':'left'}) div = soup.find('div',attrs={'class':'left'})
a = div.find('a') if div:
print a a = div.find('a')
if a : if a :
cover_url = a.img['src'] cover_url = 'http://www.themoscowtimes.com' + a.img['src']
return cover_url return cover_url