| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
""" |
| 4 |
rt.com |
| 5 |
""" |
| 6 |
|
| 7 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 8 |
|
| 9 |
|
| 10 |
class RT_eng(BasicNewsRecipe): |
| 11 |
title = 'Russia Today' |
| 12 |
__author__ = 'unkn0wn' |
| 13 |
description = ''' |
| 14 |
RT creates news with an edge for viewers who want to Question More. RT covers stories overlooked by the mainstream |
| 15 |
media, provides alternative perspectives on current affairs, and acquaints international audiences with a Russian |
| 16 |
viewpoint on major global events. |
| 17 |
''' |
| 18 |
publisher = 'Autonomous Nonprofit Organization "TV-Novosti"' |
| 19 |
category = 'news, politics, economy, finances, Russia, world' |
| 20 |
oldest_article = 1.2 |
| 21 |
no_stylesheets = True |
| 22 |
encoding = 'utf-8' |
| 23 |
ignore_duplicate_articles = {'url', 'title'} |
| 24 |
use_embedded_content = False |
| 25 |
remove_empty_feeds = True |
| 26 |
remove_javascript = True |
| 27 |
language = 'en' |
| 28 |
remove_attributes = ['height', 'width', 'style'] |
| 29 |
publication_type = 'newsportal' |
| 30 |
|
| 31 |
recipe_specific_options = { |
| 32 |
'days': { |
| 33 |
'short': 'Oldest article to download from this news source. In days ', |
| 34 |
'long': 'For example, 0.5, gives you articles from the past 12 hours', |
| 35 |
'default': str(oldest_article), |
| 36 |
} |
| 37 |
} |
| 38 |
|
| 39 |
def __init__(self, *args, **kwargs): |
| 40 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 41 |
d = self.recipe_specific_options.get('days') |
| 42 |
if d and isinstance(d, str): |
| 43 |
self.oldest_article = float(d) |
| 44 |
|
| 45 |
extra_css = ''' |
| 46 |
img {display:block; margin:0 auto;} |
| 47 |
em { color:#202020; } |
| 48 |
.date { font-size:small; color:#404040; } |
| 49 |
.article__summary { font-style:italic; color:#202020; } |
| 50 |
.media__footer { font-size:small; text-align:center; } |
| 51 |
''' |
| 52 |
|
| 53 |
conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language} |
| 54 |
|
| 55 |
keep_only_tags = [dict(name='div', attrs={'class': 'article'})] |
| 56 |
|
| 57 |
remove_tags = [ |
| 58 |
dict(name=['meta', 'link', 'svg', 'button', 'style', 'iframe', 'noscript']), |
| 59 |
classes('update_date_visible breadcrumbs read-more Read-more-text-only article__share article__social-wrapper article__share_bottom'), |
| 60 |
] |
| 61 |
|
| 62 |
feeds = [ |
| 63 |
('Russia', 'https://www.rt.com/rss/russia/'), |
| 64 |
('India', 'https://www.rt.com/rss/india/'), |
| 65 |
('Africa', 'https://www.rt.com/rss/africa/'), |
| 66 |
('World News', 'https://www.rt.com/rss/news/'), |
| 67 |
('Business', 'https://www.rt.com/rss/business/'), |
| 68 |
('Opinion', 'https://www.rt.com/rss/op-ed/'), |
| 69 |
('Culture', 'https://www.rt.com/rss/pop-culture/'), |
| 70 |
('Others', 'https://www.rt.com/rss/'), |
| 71 |
] |
| 72 |
|
| 73 |
def get_article_url(self, article): |
| 74 |
url = BasicNewsRecipe.get_article_url(self, article) |
| 75 |
return url.split('?')[0] |
| 76 |
|
| 77 |
def preprocess_html(self, soup): |
| 78 |
for img in soup.findAll('img'): |
| 79 |
srcset = img.find_previous_sibling('source', attrs={'data-srcset': True}) |
| 80 |
if srcset: |
| 81 |
for x in srcset['data-srcset'].split(','): |
| 82 |
if '/l/' in x.split()[0].strip(): |
| 83 |
img['src'] = x.split()[0].strip() |
| 84 |
for src in soup.findAll('source'): |
| 85 |
src.decompose() |
| 86 |
return soup |