| 1 |
from calibre.ebooks.BeautifulSoup import BeautifulSoup |
| 2 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 3 |
|
| 4 |
|
| 5 |
class Elektroda(BasicNewsRecipe): |
| 6 |
title = 'Elektroda' |
| 7 |
oldest_article = 8 |
| 8 |
__author__ = 'fenuks' |
| 9 |
description = 'Międzynarodowy portal elektroniczny udostępniający bogate zasoby z dziedziny elektroniki oraz forum dyskusyjne.' |
| 10 |
cover_url = 'http://demotywatory.elektroda.pl/Thunderpic/logo.gif' |
| 11 |
category = 'electronics' |
| 12 |
language = 'pl' |
| 13 |
max_articles_per_feed = 100 |
| 14 |
no_stylesheets = True |
| 15 |
feeds = [('Elektroda', 'http://www.elektroda.pl/rtvforum/rss.php')] |
| 16 |
|
| 17 |
keep_only_tags = [dict(name='div', attrs={'class': 'title-wrap pull-left'}), dict(name='ul', attrs={'class': 'topic-lists clearfix'})] |
| 18 |
|
| 19 |
def preprocess_html(self, soup): |
| 20 |
tag = soup.find('span', attrs={'class': 'postbody'}) |
| 21 |
if tag: |
| 22 |
pos = len(tag.contents) |
| 23 |
tag.insert(pos, BeautifulSoup('<br />')) |
| 24 |
return soup |
| 25 |
|
| 26 |
def parse_feeds(self): |
| 27 |
feeds = BasicNewsRecipe.parse_feeds(self) |
| 28 |
for feed in feeds: |
| 29 |
for article in feed.articles[:]: |
| 30 |
article.title = article.title[article.title.find('::') + 3 :] |
| 31 |
return feeds |