mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
37 lines
1.2 KiB
Python
37 lines
1.2 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Habr(BasicNewsRecipe):
|
|
title = 'Habr'
|
|
__author__ = 'bugmen00t'
|
|
description = 'Russian collaborative blog about IT, computer science and anything related to the Internet'
|
|
publisher = 'Habr Blockchain Publishing LTD'
|
|
category = 'blog'
|
|
cover_url = u'https://hsto.org/webt/f1/lq/ka/f1lqkaveikdfqkb_rip_4vq4s_8.png'
|
|
language = 'en_RU'
|
|
no_stylesheets = True
|
|
remove_javascript = False
|
|
auto_cleanup = False
|
|
oldest_article = 30
|
|
max_articles_per_feed = 30
|
|
|
|
remove_tags_before = dict(name='h1')
|
|
|
|
remove_tags_after = dict(name='div', attrs={'class': 'tm-misprint-area'})
|
|
|
|
remove_tags = [
|
|
dict(name='div', attrs={'class': 'tm-article-presenter__meta'}),
|
|
dict(name='div', attrs={'class': 'tm-article-poll'})
|
|
]
|
|
|
|
feeds = [('News', 'https://habr.com/en/rss/news/?fl=en'),
|
|
('All materials', 'https://habr.com/en/rss/all?fl=en')]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-src': True}):
|
|
img['src'] = img['data-src']
|
|
return soup
|