| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 4 |
|
| 5 |
|
| 6 |
class EpochTimes(BasicNewsRecipe): |
| 7 |
title = 'The Epoch Times' |
| 8 |
__author__ = 'Kovid Goyal' |
| 9 |
description = 'US general news' |
| 10 |
language = 'en' |
| 11 |
encoding = 'utf-8' |
| 12 |
oldest_article = 1.2 |
| 13 |
max_articles_per_feed = 20 |
| 14 |
ignore_duplicate_articles = {'url'} |
| 15 |
remove_attributes = ['height', 'width', 'style'] |
| 16 |
remove_empty_feeds = True |
| 17 |
no_stylesheets = True |
| 18 |
resolve_internal_links = True |
| 19 |
masthead_url = 'https://epochtimes-ny.newsmemory.com/eeLayout/epochtimes/1.0.a/images/webapp/banner.png' |
| 20 |
extra_css = '.post_caption, .text-sm, .uppercase {font-size:small;}' |
| 21 |
|
| 22 |
recipe_specific_options = { |
| 23 |
'days': { |
| 24 |
'short': 'Oldest article to download from this news source. In days ', |
| 25 |
'long': 'For example, 0.5, gives you articles from the past 12 hours', |
| 26 |
'default': str(oldest_article), |
| 27 |
} |
| 28 |
} |
| 29 |
|
| 30 |
def __init__(self, *args, **kwargs): |
| 31 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 32 |
d = self.recipe_specific_options.get('days') |
| 33 |
if d and isinstance(d, str): |
| 34 |
self.oldest_article = float(d) |
| 35 |
|
| 36 |
keep_only_tags = [dict(name='article')] |
| 37 |
remove_tags = [ |
| 38 |
classes('print:hidden h-header shortcode aspect-square'), |
| 39 |
dict(name=['button', 'svg']), |
| 40 |
dict(name='img', attrs={'src': lambda x: x and x.endswith('svg')}), |
| 41 |
] |
| 42 |
|
| 43 |
# feeds can be found at https://www.theepochtimes.com/rssfeeds |
| 44 |
feeds = [ |
| 45 |
('Special Series', 'https://feed.theepochtimes.com/health/special-series/feed'), |
| 46 |
('US', 'https://feed.theepochtimes.com/us/feed'), |
| 47 |
('China News', 'https://feed.theepochtimes.com/china/feed'), |
| 48 |
('World', 'https://feed.theepochtimes.com/world/feed'), |
| 49 |
('Opinion', 'https://feed.theepochtimes.com/opinion/feed'), |
| 50 |
('Business & Markets', 'https://feed.theepochtimes.com/business/feed'), |
| 51 |
('Science', 'https://feed.theepochtimes.com/science/feed'), |
| 52 |
('Tech', 'https://feed.theepochtimes.com/tech/feed'), |
| 53 |
('Health & Wellness', 'https://feed.theepochtimes.com/wellness/feed'), |
| 54 |
('Epoch Taste', 'https://feed.theepochtimes.com/epoch-taste/feed'), |
| 55 |
('Entertainment', 'https://feed.theepochtimes.com/entertainment/feed'), |
| 56 |
] |
| 57 |
|
| 58 |
def preprocess_html(self, soup): |
| 59 |
for img in soup.findAll('img', attrs={'data-src': True}): |
| 60 |
img['src'] = img['data-src'] |
| 61 |
for fig_c in soup.findAll('figcaption'): |
| 62 |
fig_c['class'] = 'post_caption' |
| 63 |
return soup |