| 1 |
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai |
| 2 |
from __future__ import unicode_literals |
| 3 |
|
| 4 |
import re |
| 5 |
|
| 6 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 7 |
|
| 8 |
|
| 9 |
class bleskRecipe(BasicNewsRecipe): |
| 10 |
__author__ = 'bubak' |
| 11 |
title = 'Blesk' |
| 12 |
publisher = '' |
| 13 |
description = 'blesk.cz' |
| 14 |
oldest_article = 1 |
| 15 |
max_articles_per_feed = 20 |
| 16 |
use_embedded_content = False |
| 17 |
|
| 18 |
feeds = [ |
| 19 |
('Zprávy', 'http://www.blesk.cz/rss/7'), |
| 20 |
('Blesk', 'http://www.blesk.cz/rss/1'), |
| 21 |
('Sex a tabu', 'http://www.blesk.cz/rss/2'), |
| 22 |
('Celebrity', 'http://www.blesk.cz/rss/5'), |
| 23 |
('Cestování', 'http://www.blesk.cz/rss/12'), |
| 24 |
] |
| 25 |
|
| 26 |
language = 'cs' |
| 27 |
cover_url = 'http://img.blesk.cz/images/blesk/blesk-logo.png' |
| 28 |
remove_javascript = True |
| 29 |
no_stylesheets = True |
| 30 |
extra_css = ''' |
| 31 |
''' |
| 32 |
|
| 33 |
remove_attributes = [] |
| 34 |
remove_tags_before = dict(name='div', attrs={'id': ['boxContent']}) |
| 35 |
remove_tags_after = dict(name='div', attrs={'class': ['artAuthors']}) |
| 36 |
remove_tags = [ |
| 37 |
dict(name='div', attrs={'class': ['link_clanek']}), |
| 38 |
dict(name='div', attrs={'id': ['partHeader']}), |
| 39 |
dict(name='div', attrs={'id': ['top_bottom_box', 'lista_top']}), |
| 40 |
] |
| 41 |
preprocess_regexps = [(re.compile(r'<div class="(textovytip|related)".*', re.DOTALL | re.IGNORECASE), lambda match: '</body>')] |
| 42 |
|
| 43 |
keep_only_tags = [dict(name='div', attrs={'class': 'articleContent'})] |
| 44 |
|
| 45 |
visited_urls = {} |
| 46 |
|
| 47 |
def get_article_url(self, article): |
| 48 |
url = BasicNewsRecipe.get_article_url(self, article) |
| 49 |
if url in self.visited_urls: |
| 50 |
self.log.debug('Ignoring duplicate: ' + url) |
| 51 |
return None |
| 52 |
else: |
| 53 |
self.visited_urls[url] = True |
| 54 |
self.log.debug('Accepting: ' + url) |
| 55 |
return url |