| 1 |
#!/usr/bin/env python |
| 2 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 3 |
|
| 4 |
|
| 5 |
class znetwork(BasicNewsRecipe): |
| 6 |
title = 'ZNetwork' |
| 7 |
__author__ = 'unkn0wn' |
| 8 |
language = 'en' |
| 9 |
description = 'ZNetwork: Left News, Analysis, Vision & Strategy' |
| 10 |
oldest_article = 2 |
| 11 |
no_stylesheets = True |
| 12 |
encoding = 'utf-8' |
| 13 |
remove_javascript = True |
| 14 |
use_embedded_content = False |
| 15 |
remove_attributes = ['style', 'height', 'width'] |
| 16 |
masthead_url = 'https://znetwork.org/wp-content/uploads/2022/08/Z_logo_64.png' |
| 17 |
ignore_duplicate_articles = {'url'} |
| 18 |
browser_type = 'qt' |
| 19 |
|
| 20 |
recipe_specific_options = { |
| 21 |
'days': { |
| 22 |
'short': 'Oldest article to download from this news source. In days ', |
| 23 |
'long': 'For example, 0.5, gives you articles from the past 12 hours', |
| 24 |
'default': str(oldest_article), |
| 25 |
} |
| 26 |
} |
| 27 |
|
| 28 |
def __init__(self, *args, **kwargs): |
| 29 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 30 |
d = self.recipe_specific_options.get('days') |
| 31 |
if d and isinstance(d, str): |
| 32 |
self.oldest_article = float(d) |
| 33 |
|
| 34 |
extra_css = ''' |
| 35 |
.cat-labels { font-size:small; color:#404040; } |
| 36 |
.post-author, .date, .author-info, .z-post-source, .read-time { font-size:small; } |
| 37 |
.sub-title { font-style:italic; color:#202020; } |
| 38 |
em, blockquote { color:#202020; } |
| 39 |
.wp-caption-text, .wp-element-caption { font-size:small; text-align:center; } |
| 40 |
''' |
| 41 |
|
| 42 |
keep_only_tags = [classes('cat-labels post-title z-post-source sub-title post-author date read-time featured entry-content author-info')] |
| 43 |
|
| 44 |
remove_tags = [dict(name=['aside', 'svg', 'source', 'iframe']), classes('support-z-text yarpp-related yarpp-related-website')] |
| 45 |
|
| 46 |
remove_tags_after = [classes('author-info')] |
| 47 |
|
| 48 |
feeds = [('Articles', 'https://znetwork.org/feed/')] |
| 49 |
|
| 50 |
def preprocess_html(self, soup): |
| 51 |
for spn in soup.findAll(**classes('post-author date')): |
| 52 |
spn.string = spn.text + ' | ' |
| 53 |
div = soup.findAll(**classes('featured')) |
| 54 |
if div: |
| 55 |
div.name = 'p' |
| 56 |
p = soup.findAll(**classes('sub-title')) |
| 57 |
if p: |
| 58 |
p.name = 'p' |
| 59 |
for h in soup.findAll(['h2', 'h3']): |
| 60 |
h.name = 'h4' |
| 61 |
return soup |