| 1 |
__license__ = 'GPL v3' |
| 2 |
__copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>' |
| 3 |
''' |
| 4 |
www.variety.com |
| 5 |
''' |
| 6 |
|
| 7 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 8 |
|
| 9 |
|
| 10 |
class Variety(BasicNewsRecipe): |
| 11 |
title = 'Variety' |
| 12 |
__author__ = 'Darko Miletic' |
| 13 |
description = 'Breaking entertainment movie news, movie reviews, entertainment industry events, news and reviews from Cannes, Oscars, and Hollywood awards. Featuring box office charts, archives and more.' # noqa: E501 |
| 14 |
oldest_article = 2 |
| 15 |
max_articles_per_feed = 100 |
| 16 |
no_stylesheets = True |
| 17 |
use_embedded_content = False |
| 18 |
encoding = 'utf8' |
| 19 |
publisher = 'Red Business Information' |
| 20 |
category = 'Entertainment Industry News, Daily Variety, Movie Reviews, TV, Awards, Oscars, Cannes, Box Office, Hollywood' |
| 21 |
language = 'en' |
| 22 |
masthead_url = 'http://images1.variety.com/graphics/variety/Variety_logo_green_tm.gif' |
| 23 |
extra_css = ''' |
| 24 |
body{font-family: Arial,Helvetica,sans-serif; font-size: 1.275em} |
| 25 |
.date{font-size: small; border: 1px dotted rgb(204, 204, 204); font-style: italic; color: rgb(102, 102, 102); margin: 5px 0px; padding: 0.5em;} |
| 26 |
.author{margin: 5px 0px 5px 20px; padding: 0.5em; background: none repeat scroll 0% 0% rgb(247, 247, 247);} |
| 27 |
.art h2{color: rgb(153, 0, 0); font-size: 1.275em; font-weight: bold;} |
| 28 |
img{margin-bottom: 1em} |
| 29 |
''' |
| 30 |
|
| 31 |
conversion_options = {'comments': description, 'tags': category, 'language': language, 'publisher': publisher} |
| 32 |
|
| 33 |
remove_tags = [dict(name=['object', 'link', 'map'])] |
| 34 |
remove_attributes = ['lang', 'vspace', 'hspace', 'xmlns:ms', 'xmlns:dt'] |
| 35 |
keep_only_tags = [dict(name='div', attrs={'class': 'art control'})] |
| 36 |
|
| 37 |
feeds = [('News & Articles', 'http://feeds.feedburner.com/variety/headlines')] |
| 38 |
|
| 39 |
def print_version(self, url): |
| 40 |
rpt = url.rpartition('.html')[0] |
| 41 |
return rpt + '?printerfriendly=true' |
| 42 |
|
| 43 |
def preprocess_raw_html(self, raw, url): |
| 44 |
return '<html><head>' + raw[raw.find('</head>') :] |
| 45 |
|
| 46 |
def get_article_url(self, article): |
| 47 |
url = BasicNewsRecipe.get_article_url(self, article) |
| 48 |
return url.rpartition('?')[0] |
| 49 |
|
| 50 |
def preprocess_html(self, soup): |
| 51 |
for item in soup.findAll('a'): |
| 52 |
limg = item.find('img') |
| 53 |
if item.string is not None: |
| 54 |
str = item.string |
| 55 |
item.replaceWith(str) |
| 56 |
elif limg: |
| 57 |
item.name = 'div' |
| 58 |
item.attrs = [] |
| 59 |
else: |
| 60 |
str = self.tag_to_string(item) |
| 61 |
item.replaceWith(str) |
| 62 |
for item in soup.findAll('img', alt=False): |
| 63 |
item['alt'] = 'image' |
| 64 |
return soup |