| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=UTF-8 |
| 3 |
|
| 4 |
__license__ = 'GPL v3' |
| 5 |
__author__ = 'Mori' |
| 6 |
__version__ = 'v. 0.5' |
| 7 |
''' |
| 8 |
di.com.pl |
| 9 |
''' |
| 10 |
|
| 11 |
import re |
| 12 |
|
| 13 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 14 |
|
| 15 |
|
| 16 |
class DziennikInternautowRecipe(BasicNewsRecipe): |
| 17 |
__author__ = 'Mori' |
| 18 |
language = 'pl' |
| 19 |
|
| 20 |
title = 'Dziennik Internautów' |
| 21 |
publisher = 'Dziennik Internaut\u00f3w Sp. z o.o.' |
| 22 |
description = 'Internet w \u017cyciu i biznesie. Porady, wywiady, interwencje, bezpiecze\u0144stwo w Sieci, technologia.' |
| 23 |
|
| 24 |
max_articles_per_feed = 100 |
| 25 |
oldest_article = 7 |
| 26 |
cover_url = 'http://di.com.pl/pic/logo_di_norm.gif' |
| 27 |
|
| 28 |
no_stylesheets = True |
| 29 |
remove_javascript = True |
| 30 |
encoding = 'utf-8' |
| 31 |
|
| 32 |
extra_css = ''' |
| 33 |
.fotodesc{font-size: 75%;} |
| 34 |
.pub_data{font-size: 75%;} |
| 35 |
.fotonews{clear: both; padding-top: 10px; padding-bottom: 10px;} |
| 36 |
#pub_foto{font-size: 75%; float: left; padding-right: 10px;} |
| 37 |
''' |
| 38 |
|
| 39 |
feeds = [('Dziennik Internaut\u00f3w', 'http://feeds.feedburner.com/glowny-di')] |
| 40 |
|
| 41 |
keep_only_tags = [dict(name='div', attrs={'id': 'pub_head'}), dict(name='div', attrs={'id': 'pub_content'})] |
| 42 |
|
| 43 |
remove_tags = [ |
| 44 |
dict(name='div', attrs={'class': 'poradniki_context'}), |
| 45 |
dict(name='div', attrs={'class': 'uniBox'}), |
| 46 |
dict(name='object', attrs={}), |
| 47 |
dict(name='h3', attrs={}), |
| 48 |
dict(attrs={'class': 'twitter-share-button'}), |
| 49 |
] |
| 50 |
|
| 51 |
preprocess_regexps = [ |
| 52 |
(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) |
| 53 |
for i in [ |
| 54 |
(r', <a href="http://di.com.pl/komentarze,.*?</div>', lambda match: '</div>'), |
| 55 |
(r'<div class="fotonews".*?">', lambda match: '<div class="fotonews">'), |
| 56 |
(r'http://di.com.pl/pic/photo/mini/', lambda match: 'http://di.com.pl/pic/photo/oryginal/'), |
| 57 |
(r'\s*</', lambda match: '</'), |
| 58 |
] |
| 59 |
] |
| 60 |
|
| 61 |
def skip_ad_pages(self, soup): |
| 62 |
if 'Advertisement' in soup.title: |
| 63 |
nexturl = soup.find('a')['href'] |
| 64 |
return self.index_to_soup(nexturl, raw=True) |