mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
70 lines
2.3 KiB
Python
70 lines
2.3 KiB
Python
#!/usr/bin/env python
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
class znetwork(BasicNewsRecipe):
|
|
title = 'ZNetwork'
|
|
__author__ = 'unkn0wn'
|
|
language = 'en'
|
|
description = 'ZNetwork: Left News, Analysis, Vision & Strategy'
|
|
oldest_article = 2
|
|
no_stylesheets = True
|
|
encoding = 'utf-8'
|
|
remove_javascript = True
|
|
use_embedded_content = False
|
|
remove_attributes = ['style', 'height', 'width']
|
|
masthead_url = 'https://znetwork.org/wp-content/uploads/2022/08/Z_logo_64.png'
|
|
ignore_duplicate_articles = {'url'}
|
|
browser_type = 'qt'
|
|
|
|
recipe_specific_options = {
|
|
'days': {
|
|
'short': 'Oldest article to download from this news source. In days ',
|
|
'long': 'For example, 0.5, gives you articles from the past 12 hours',
|
|
'default': str(oldest_article)
|
|
}
|
|
}
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
BasicNewsRecipe.__init__(self, *args, **kwargs)
|
|
d = self.recipe_specific_options.get('days')
|
|
if d and isinstance(d, str):
|
|
self.oldest_article = float(d)
|
|
|
|
extra_css = '''
|
|
.cat-labels { font-size:small; color:#404040; }
|
|
.post-author, .date, .author-info, .z-post-source, .read-time { font-size:small; }
|
|
.sub-title { font-style:italic; color:#202020; }
|
|
em, blockquote { color:#202020; }
|
|
.wp-caption-text, .wp-element-caption { font-size:small; text-align:center; }
|
|
'''
|
|
|
|
keep_only_tags = [
|
|
classes(
|
|
'cat-labels post-title z-post-source sub-title post-author date'
|
|
' read-time featured entry-content author-info'
|
|
)
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['aside', 'svg', 'source', 'iframe']),
|
|
classes('support-z-text yarpp-related yarpp-related-website')
|
|
]
|
|
|
|
remove_tags_after = [classes('author-info')]
|
|
|
|
feeds = [('Articles', 'https://znetwork.org/feed/')]
|
|
|
|
def preprocess_html(self, soup):
|
|
for spn in soup.findAll(**classes('post-author date')):
|
|
spn.string = spn.text + ' | '
|
|
div = soup.findAll(**classes('featured'))
|
|
if div:
|
|
div.name = 'p'
|
|
p = soup.findAll(**classes('sub-title'))
|
|
if p:
|
|
p.name = 'p'
|
|
for h in soup.findAll(['h2', 'h3']):
|
|
h.name = 'h4'
|
|
return soup
|