mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
72 lines
3.2 KiB
Python
72 lines
3.2 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, matek09, matek09@gmail.com'
|
|
__copyright__ = 'Modified 2011, Mariusz Wolek <mariusz_dot_wolek @ gmail dot com>'
|
|
__copyright__ = 'Modified 2012, Artur Stachecki <artur.stachecki@gmail.com>'
|
|
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import re
|
|
|
|
class Wprost(BasicNewsRecipe):
|
|
title = u'Wprost (RSS)'
|
|
__author__ = 'matek09'
|
|
description = 'Weekly magazine'
|
|
encoding = 'ISO-8859-2'
|
|
no_stylesheets = True
|
|
language = 'pl'
|
|
remove_javascript = True
|
|
recursions = 0
|
|
use_embedded_content = False
|
|
remove_empty_feeds = True
|
|
remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
|
|
remove_tags_after = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
|
|
'''
|
|
keep_only_tags =[]
|
|
keep_only_tags.append(dict(name = 'table', attrs = {'id' : 'title-table'}))
|
|
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-header'}))
|
|
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-content'}))
|
|
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'def element-autor'}))
|
|
'''
|
|
|
|
preprocess_regexps = [(re.compile(r'style="display: none;"'), lambda match: ''),
|
|
(re.compile(r'display: block;'), lambda match: ''),
|
|
(re.compile(r'\<td\>\<tr\>\<\/table\>'), lambda match: ''),
|
|
(re.compile(r'\<table .*?\>'), lambda match: ''),
|
|
(re.compile(r'\<tr>'), lambda match: ''),
|
|
(re.compile(r'\<td .*?\>'), lambda match: ''),
|
|
(re.compile(r'\<div id="footer"\>.*?\</footer\>'), lambda match: '')]
|
|
|
|
remove_tags =[]
|
|
remove_tags.append(dict(name = 'div', attrs = {'class' : 'def element-date'}))
|
|
remove_tags.append(dict(name = 'div', attrs = {'class' : 'def silver'}))
|
|
remove_tags.append(dict(name = 'div', attrs = {'id' : 'content-main-column-right'}))
|
|
|
|
|
|
extra_css = '''.div-header {font-size: x-small; font-weight: bold}'''
|
|
#h2 {font-size: x-large; font-weight: bold}
|
|
|
|
feeds = [(u'Tylko u nas', u'http://www.wprost.pl/rss/rss_wprostextra.php'),
|
|
(u'Wydarzenia', u'http://www.wprost.pl/rss/rss.php'),
|
|
(u'Komentarze', u'http://www.wprost.pl/rss/rss_komentarze.php'),
|
|
(u'Wydarzenia: Kraj', u'http://www.wprost.pl/rss/rss_kraj.php'),
|
|
(u'Komentarze: Kraj', u'http://www.wprost.pl/rss/rss_komentarze_kraj.php'),
|
|
(u'Wydarzenia: Świat', u'http://www.wprost.pl/rss/rss_swiat.php'),
|
|
(u'Komentarze: Świat', u'http://www.wprost.pl/rss/rss_komentarze_swiat.php'),
|
|
(u'Wydarzenia: Gospodarka', u'http://www.wprost.pl/rss/rss_gospodarka.php'),
|
|
(u'Komentarze: Gospodarka', u'http://www.wprost.pl/rss/rss_komentarze_gospodarka.php'),
|
|
(u'Wydarzenia: Życie', u'http://www.wprost.pl/rss/rss_zycie.php'),
|
|
(u'Komentarze: Życie', u'http://www.wprost.pl/rss/rss_komentarze_zycie.php'),
|
|
(u'Wydarzenia: Sport', u'http://www.wprost.pl/rss/rss_sport.php'),
|
|
(u'Komentarze: Sport', u'http://www.wprost.pl/rss/rss_komentarze_sport.php'),
|
|
(u'Przegląd prasy', u'http://www.wprost.pl/rss/rss_prasa.php')
|
|
]
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup('http://www.wprost.pl/tygodnik')
|
|
cover = soup.find(attrs={'class':'wprost-cover'})
|
|
if cover:
|
|
self.cover_url = cover['src']
|
|
return getattr(self, 'cover_url', self.cover_url)
|