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

Update American Spectator

Browse Source
This commit is contained in:
Kovid Goyal 2015-08-13 11:32:47 +05:30
parent e3b1de1131
commit cae14a92b9
1 changed files with 30 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
recipes/amspec.recipe
View File

@ -5,44 +5,45 @@ spectator.org
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from css_selectors import Select
class TheAmericanSpectator(BasicNewsRecipe): class TheAmericanSpectator(BasicNewsRecipe):
title = 'The American Spectator' title = 'The American Spectator'
__author__ = 'Darko Miletic' __author__ = 'Kovid Goyal'
description = 'News from USA' description = 'News from USA'
category = 'news, politics, USA, world'
publisher = 'The American Spectator'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
use_embedded_content = False use_embedded_content = False
language = 'en' language = 'en'
INDEX = 'http://spectator.org'
auto_cleanup = True auto_cleanup = True
encoding = 'utf-8' encoding = 'utf-8'
conversion_options = { def parse_index(self):
'comments' : description root = self.index_to_soup('http://spectator.org/issues/current', as_tree=True)
,'tags' : category select = Select(root)
,'language' : language main = tuple(select('div#block-system-main'))[0]
,'publisher' : publisher feeds = []
} for div in select('div.item-list', main):
for h3 in div.xpath('./h3'):
feeds = [ (u'Articles', u'http://feeds.feedburner.com/amspecarticles')] section_title = self.tag_to_string(h3)
self.log('\n' + section_title)
def get_cover_url(self): break
cover_url = None else:
soup = self.index_to_soup(self.INDEX) continue
link_item = soup.find('a',attrs={'class':'cover'}) articles = []
if link_item: for li in div.xpath('descendant::li'):
soup2 = self.index_to_soup(link_item['href']) for x in select('div.views-field-title', li):
link_item2 = soup2.find('div',attrs={'class':'post inner issues'}) title = self.tag_to_string(x)
cover_url = self.INDEX + link_item2.img['src'] break
return cover_url else:
raise ValueError('No article title found')
def print_version(self, url): url = 'http://spectator.org' + li.xpath('./a/@href')[0]
return url + '/print' desc = ''
for x in select('div.views-field-field-short-summary', li):
def get_article_url(self, article): desc = self.tag_to_string(x)
return article.get('guid', None) break
articles.append({'title':title, 'url':url, 'description':desc})
self.log('\t', title, 'at', url)
feeds.append((section_title, articles))
return feeds