mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Pull from trunk
This commit is contained in:
commit
e54b79a455
49
resources/recipes/skeptic.recipe
Normal file
49
resources/recipes/skeptic.recipe
Normal file
@ -0,0 +1,49 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
class Skeptic(BasicNewsRecipe):
|
||||
title = u'The Skeptic'
|
||||
description = 'Discussions with leading experts and investigation of fringe science and paranormal claims.'
|
||||
language = 'en'
|
||||
__author__ = 'Starson17'
|
||||
oldest_article = 31
|
||||
cover_url = 'http://www.skeptricks.com/images/Skeptic_Magazine.jpg'
|
||||
remove_empty_feeds = True
|
||||
remove_javascript = True
|
||||
max_articles_per_feed = 50
|
||||
no_stylesheets = True
|
||||
|
||||
remove_tags = [dict(name='div', attrs={'class':['Introduction','divider']}),
|
||||
dict(name='div', attrs={'id':['feature', 'podcast']}),
|
||||
dict(name='div', attrs={'id':re.compile(r'follow.*', re.DOTALL|re.IGNORECASE)}),
|
||||
dict(name='hr'),
|
||||
]
|
||||
|
||||
|
||||
feeds = [
|
||||
('The Skeptic', 'http://www.skeptic.com/feed'),
|
||||
('E-Skeptic', 'http://www.skeptic.com/eskeptic'),
|
||||
('All-SkepticBlog', 'http://skepticblog.org/feed'),
|
||||
('Brian Dunning', 'http://skepticblog.org/author/dunning/feed/'),
|
||||
('Daniel Loxton', 'http://skepticblog.org/author/loxton/feed/'),
|
||||
('Kirsten Sanford', 'http://skepticblog.org/author/sanford/feed/'),
|
||||
('Mark Edward', 'http://skepticblog.org/author/edward/feed/'),
|
||||
('Michael Shermer', 'http://skepticblog.org/author/shermer/feed/'),
|
||||
('Phil Plait', 'http://skepticblog.org/author/plait/feed/'),
|
||||
('Ryan Johnson', 'http://skepticblog.org/author/johnson/feed/'),
|
||||
('Steven Novella', 'http://skepticblog.org/author/novella/feed/'),
|
||||
('Yau-Man Chan', 'http://skepticblog.org/author/chan/feed/'),
|
||||
]
|
||||
|
||||
def get_browser(self):
|
||||
br = BasicNewsRecipe.get_browser(self)
|
||||
br.addheaders = [('Accept', 'text/html')]
|
||||
return br
|
||||
|
||||
extra_css = '''
|
||||
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
||||
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
||||
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
||||
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
||||
'''
|
||||
|
50
resources/recipes/skeptical_enquirer.recipe
Normal file
50
resources/recipes/skeptical_enquirer.recipe
Normal file
@ -0,0 +1,50 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
class TheSkepticalInquirer(BasicNewsRecipe):
|
||||
title = u'The Skeptical Inquirer'
|
||||
description = 'Investigation of fringe science and paranormal claims.'
|
||||
language = 'en'
|
||||
__author__ = 'Starson17'
|
||||
oldest_article = 31
|
||||
cover_url = 'http://www.skeptricks.com/images/Skeptical_Inquirer_Magazine.jpg'
|
||||
remove_empty_feeds = True
|
||||
remove_javascript = True
|
||||
max_articles_per_feed = 50
|
||||
no_stylesheets = True
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':['content', 'bio']})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id':['socialMedia']}),
|
||||
]
|
||||
|
||||
preprocess_regexps = [
|
||||
(re.compile(r'\.\(JavaScript must be enabled to view this email address\)', re.DOTALL|re.IGNORECASE), lambda match: ''),
|
||||
]
|
||||
|
||||
def parse_index(self):
|
||||
feeds = []
|
||||
for title, url in [("The Skeptical Inquirer", "http://www.csicop.org")]:
|
||||
articles = self.make_links(url)
|
||||
if articles:
|
||||
feeds.append((title, articles))
|
||||
return feeds
|
||||
|
||||
def make_links(self, url):
|
||||
soup = self.index_to_soup(url)
|
||||
title = ''
|
||||
current_articles = []
|
||||
for item in soup.findAll(attrs={'class':['article-single bigger']}):
|
||||
page_url = url + str(item.a["href"])
|
||||
title = str(item.a.string)
|
||||
current_articles.append({'title': title, 'url': page_url, 'description':'', 'date':''})
|
||||
return current_articles
|
||||
|
||||
extra_css = '''
|
||||
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
||||
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
||||
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
||||
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
||||
'''
|
||||
|
Loading…
x
Reference in New Issue
Block a user