| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 4 |
|
| 5 |
|
| 6 |
class Unz(BasicNewsRecipe): |
| 7 |
title = 'The Unz Review' |
| 8 |
description = 'A Collection of Interesting, Important, and Controversial Perspectives Largely Excluded from the American Mainstream Media.' |
| 9 |
__author__ = 'unkn0wn' |
| 10 |
oldest_article = 7 |
| 11 |
language = 'en_US' |
| 12 |
max_articles_per_feed = 100 |
| 13 |
use_embedded_content = False |
| 14 |
cover_url = 'https://www.unz.com/wp-content/themes/unzSite/IMAGES/unz_large_logo.png' |
| 15 |
encoding = 'utf-8' |
| 16 |
# browser_type = 'webengine' |
| 17 |
no_stylesheets = True |
| 18 |
remove_attributes = ['style', 'height', 'width'] |
| 19 |
extra_css = '.byline, .caption { font-size: small; }' |
| 20 |
|
| 21 |
keep_only_tags = [ |
| 22 |
dict( |
| 23 |
name='div', |
| 24 |
attrs={'class': ['head', 'byline', 'page-thumb', 'section-holder']}, |
| 25 |
), |
| 26 |
] |
| 27 |
|
| 28 |
remove_tags = [ |
| 29 |
dict(name=['audio', 'iframe', 'svg']), |
| 30 |
classes('commentlink replylink'), |
| 31 |
] |
| 32 |
|
| 33 |
remove_tags_after = [dict(name='div', attrs={'class': 'section-holder'})] |
| 34 |
|
| 35 |
recipe_specific_options = { |
| 36 |
'days': { |
| 37 |
'short': 'Oldest article to download from this news source. In days ', |
| 38 |
'long': 'For example, 0.5, gives you articles from the past 12 hours', |
| 39 |
'default': str(oldest_article), |
| 40 |
}, |
| 41 |
} |
| 42 |
|
| 43 |
def __init__(self, *args, **kwargs): |
| 44 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 45 |
d = self.recipe_specific_options.get('days') |
| 46 |
if d and isinstance(d, str): |
| 47 |
self.oldest_article = float(d) |
| 48 |
|
| 49 |
feeds = ['https://www.unz.com/feed'] |
| 50 |
|
| 51 |
def preprocess_html(self, soup): |
| 52 |
head = soup.find(**classes('head')) |
| 53 |
if head: |
| 54 |
head.name = 'h1' |
| 55 |
return soup |