| 1 |
__license__ = 'GPL v3' |
| 2 |
import re |
| 3 |
|
| 4 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 5 |
|
| 6 |
|
| 7 |
class Polter(BasicNewsRecipe): |
| 8 |
title = 'Polter.pl' |
| 9 |
__author__ = 'fenuks' |
| 10 |
description = 'Największy polski serwis poświęcony ogólno pojętej fantastyce - grom fabularnym (RPG), książkom, filmowi, komiksowi, grom planszowym, karcianym i bitewnym.' # noqa: E501 |
| 11 |
category = 'fantasy, books, rpg, games' |
| 12 |
language = 'pl' |
| 13 |
extra_css = '.image, .floatright {float: right; margin-left: 10px;} .floatleft {float: left; margin-right: 10px;} .calibre_navbar {clear: both;} .p_title {font-weight: bold;} .p_image {margin-left: auto; margin-right: auto; display: block;} .italic {font-style: italic;}' # noqa: E501 |
| 14 |
cover_url = 'http://static.polter.pl/sub/promo/bpromo2524.jpg' |
| 15 |
use_embedded_content = False |
| 16 |
oldest_article = 7 |
| 17 |
max_articles_per_feed = 100 |
| 18 |
no_stylesheets = True |
| 19 |
remove_empty_feeds = True |
| 20 |
remove_javascript = True |
| 21 |
remove_attributes = ['font', 'fieldset', 'onclick'] |
| 22 |
ignore_duplicate_articles = {'title', 'url'} |
| 23 |
|
| 24 |
keep_only_tags = [dict(attrs={'class': 'boxcontent'})] |
| 25 |
remove_tags = [dict(id='komentarze'), dict(name='div', attrs={'class': 'ostatnieArtykuly'})] |
| 26 |
remove_tags_after = dict(id='komentarze') |
| 27 |
|
| 28 |
feeds = [ |
| 29 |
('Wieści', 'http://polter.pl/wiesci,rss.html'), |
| 30 |
('RPG', 'http://rpg.polter.pl/wiesci,rss.html'), |
| 31 |
('Książki', 'http://ksiazki.polter.pl/wiesci,rss.html'), |
| 32 |
('Film', 'http://film.polter.pl/wiesci,rss.html'), |
| 33 |
('Komiks', 'http://komiks.polter.pl/wiesci,rss.html'), |
| 34 |
('Gry bitewne', 'http://bitewniaki.polter.pl/wiesci,rss.html'), |
| 35 |
('Gry karciane', 'http://karcianki.polter.pl/wiesci,rss.html'), |
| 36 |
('Gry planszowe', 'http://planszowki.polter.pl/wiesci,rss.html'), |
| 37 |
('Gry PC', 'http://gry.polter.pl/wiesci,rss.html'), |
| 38 |
('Gry konsolowe', 'http://konsole.polter.pl/wiesci,rss.html'), |
| 39 |
('Konwenty', 'http://konwenty.polter.pl/wiesci,rss.html'), |
| 40 |
] |
| 41 |
|
| 42 |
def preprocess_html(self, soup): |
| 43 |
for s in soup.findAll(attrs={'style': re.compile(r'float: ?left')}): |
| 44 |
s['class'] = 'floatleft' |
| 45 |
for s in soup.findAll(attrs={'style': re.compile(r'float: ?right')}): |
| 46 |
s['class'] = 'floatright' |
| 47 |
for s in soup.findAll(style=True): |
| 48 |
if 'bold;' in s['style']: |
| 49 |
if s.get('class', ''): |
| 50 |
s['class'] = ''.join(s['class']) + ' p_title' |
| 51 |
else: |
| 52 |
s['class'] = 'p_title' |
| 53 |
if 'italic;' in s['style']: |
| 54 |
if s.get('class', ''): |
| 55 |
s['class'] = ''.join(s['class']) + ' italic' |
| 56 |
else: |
| 57 |
s['class'] = 'italic' |
| 58 |
del s['style'] |
| 59 |
|
| 60 |
tag = soup.find(id='twoja_ocena') |
| 61 |
if tag: |
| 62 |
tag.parent.extract() |
| 63 |
for tag in soup.findAll(id='lista_chce_ile'): |
| 64 |
tag.parent.parent.extract() |
| 65 |
for r in soup.findAll(name='a', href=re.compile(r'^http://www.ceneo.pl/')): |
| 66 |
r.extract() |
| 67 |
return soup |
| 68 |
|
| 69 |
def preprocess_raw_html(self, raw_html, url): |
| 70 |
return raw_html.replace('<br /><br /><h3>Czytaj również</h3>', '') |