| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
|
| 4 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 5 |
|
| 6 |
|
| 7 |
class Habr(BasicNewsRecipe): |
| 8 |
title = 'Habr' |
| 9 |
__author__ = 'bugmen00t' |
| 10 |
description = 'Russian collaborative blog about IT, computer science and anything related to the Internet' |
| 11 |
publisher = 'Habr Blockchain Publishing LTD' |
| 12 |
category = 'blog' |
| 13 |
cover_url = 'https://hsto.org/webt/f1/lq/ka/f1lqkaveikdfqkb_rip_4vq4s_8.png' |
| 14 |
language = 'en_RU' |
| 15 |
no_stylesheets = True |
| 16 |
remove_javascript = False |
| 17 |
auto_cleanup = False |
| 18 |
oldest_article = 30 |
| 19 |
max_articles_per_feed = 30 |
| 20 |
|
| 21 |
remove_tags_before = dict(name='h1') |
| 22 |
|
| 23 |
remove_tags_after = dict(name='div', attrs={'class': 'tm-misprint-area'}) |
| 24 |
|
| 25 |
remove_tags = [dict(name='div', attrs={'class': 'tm-article-presenter__meta'}), dict(name='div', attrs={'class': 'tm-article-poll'})] |
| 26 |
|
| 27 |
feeds = [('News', 'https://habr.com/en/rss/news/?fl=en'), ('All materials', 'https://habr.com/en/rss/all?fl=en')] |
| 28 |
|
| 29 |
def preprocess_html(self, soup): |
| 30 |
for img in soup.findAll('img', attrs={'data-src': True}): |
| 31 |
img['src'] = img['data-src'] |
| 32 |
return soup |