set of updates for Polish recipes

This commit is contained in:
fenuks 2013-06-23 14:52:01 +02:00
parent c56989ea1a
commit f97f69a207
6 changed files with 57 additions and 31 deletions

View File

@ -9,6 +9,7 @@ class ForsalPL(BasicNewsRecipe):
oldest_article = 7
max_articles_per_feed = 100
use_embedded_content = False
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
cover_url = 'http://www.bizneswnieruchomosciach.pl/wp-content/uploads/2010/07/logo_forsal.jpg'
no_stylesheets = True

View File

@ -8,7 +8,7 @@ class Kosmonauta(BasicNewsRecipe):
category = 'astronomy'
language = 'pl'
cover_url = 'http://bi.gazeta.pl/im/4/10393/z10393414X,Kosmonauta-net.jpg'
extra_css = '.thumbnail {float:left;margin-right:5px;}'
extra_css = '.thumb-left {float:left; margin-right:5px;} .calibre_navbar {clear: both;}'
no_stylesheets = True
INDEX = 'http://www.kosmonauta.net'
oldest_article = 7

View File

@ -10,8 +10,8 @@ class recipeMagic(BasicNewsRecipe):
title = 'National Geographic PL'
__author__ = 'Marcin Urban 2011'
__modified_by__ = 'fenuks'
description = 'legenda wśród magazynów z historią sięgającą 120 lat'
#cover_url = 'http://www.guj.pl/var/guj/storage/images/media/nasze_magazyny/national_geographic/logo/ng_logo/2606-1-pol-PL/ng_logo.jpg'
description = 'Legenda wśród magazynów z historią sięgającą 120 lat'
#cover_url = 'http://www.guj.pl/var/guj/storage/images/media/nasze_magazyny/national_geographic/logo/ng_logo/2606-1-pol-PL/ng_logo.jpg'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
@ -21,13 +21,14 @@ class recipeMagic(BasicNewsRecipe):
publisher = 'G+J Gruner+Jahr Polska'
category = 'news, PL,'
language = 'pl'
remove_empty_feeds = True
publication_type = 'newsportal'
extra_css = ''' body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
h1{text-align: center;}
h2{font-size: medium; font-weight: bold;}
.authordate {font-size: small; color: #696969;}
p.lead {font-weight: bold; text-align: center;}
.fot{font-size: x-small; color: #666666;} '''
h1{text-align: center;}
h2{font-size: medium; font-weight: bold;}
.authordate {font-size: small; color: #696969;}
p.lead {font-weight: bold; text-align: center;}
.fot{font-size: x-small; color: #666666;} '''
preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
conversion_options = {
'comments' : description
@ -37,9 +38,9 @@ class recipeMagic(BasicNewsRecipe):
,'linearize_tables': True
}
remove_tags = [
dict(name='div', attrs={'class':'add_inf'}),
dict(name='div', attrs={'class':'add_f'}),
remove_tags = [
dict(name='div', attrs={'class':'add_inf'}),
dict(name='div', attrs={'class':'add_f'}),
]
remove_attributes = ['width','height']
@ -47,14 +48,16 @@ class recipeMagic(BasicNewsRecipe):
def find_articles(self, url):
articles = []
soup=self.index_to_soup(url)
tag=soup.find(attrs={'class':'arl'})
art=tag.ul.findAll('li')
soup = self.index_to_soup(url)
tag = soup.find(attrs={'class':'arl'})
if not tag:
return articles
art = tag.ul.findAll('li')
for i in art:
title=i.a['title']
url=i.a['href']
title = i.a['title']
url = i.a['href']
#date=soup.find(id='footer').ul.li.string[41:-1]
desc=i.div.p.string
desc = i.div.p.string
articles.append({'title' : title,
'url' : url,
'date' : '',

View File

@ -2,7 +2,7 @@ __license__ = 'GPL v3'
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Poltergeist(BasicNewsRecipe):
class Polter(BasicNewsRecipe):
title = u'Polter.pl'
__author__ = 'fenuks'
description = u'Największy polski serwis poświęcony ogólno pojętej fantastyce - grom fabularnym (RPG), książkom, filmowi, komiksowi, grom planszowym, karcianym i bitewnym.'
@ -10,21 +10,26 @@ class Poltergeist(BasicNewsRecipe):
#publication_type = ''
language = 'pl'
#encoding = ''
extra_css = '.image, .floatright {float: right; margin-left: 10px;} .floatleft {float: left; margin-right: 10px;}'
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;}'
cover_url = 'http://static.polter.pl/sub/promo/bpromo2524.jpg'
#masthead_url = ''
use_embedded_content = False
oldest_article = 7
preprocess_regexps = [(re.compile(ur'<div[^>]*?id="pol_lista"[^>]*?>.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>'), (re.compile(ur'<a[^>]*?>wersja do druku</a>', re.DOTALL|re.IGNORECASE), lambda match: '')]
preprocess_regexps = [(re.compile(ur'<div[^>]*?id="pol_lista"[^>]*?>.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>'),
(re.compile(ur'<a[^>]*?>wersja do druku</a>', re.DOTALL|re.IGNORECASE), lambda match: ''),
#(re.compile(ur'<a href="JavaScript:[^">]*">(<img ?[^>]*?/>)</a>', re.DOTALL|re.IGNORECASE), lambda match: '/1')
(re.compile(ur'(<br ?/?>[\n\s\r]*){2,}', re.DOTALL|re.IGNORECASE), lambda match: '<br />'),
(re.compile(ur'<span[^>]*>Zaloguj się aby wyłączyć tę reklamę</span>', re.DOTALL|re.IGNORECASE), lambda match: ''),
]
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
remove_javascript = True
remove_attributes = ['style', 'font']
remove_attributes = ['font', 'fieldset', 'onclick']
ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [dict(attrs={'class':'boxcontent'})]
remove_tags = [dict(attrs={'class':'fb-like'}), dict(attrs={'alt':'Wersja do druku'}), dict(id='pol_liczba'), dict(attrs={'scr':'http://static.polter.pl/tplimg/buttons/ceneo_140_40.gif'})]
remove_tags = [dict(attrs={'class':'fb-like'}), dict(attrs={'alt':'Wersja do druku'}), dict(id=['pol_liczba', 'col12AdSenseLight']), dict(attrs={'scr':'http://static.polter.pl/tplimg/buttons/ceneo_140_40.gif'}), dict(name=['g:plusone', 'fb:like'])]
remove_tags_after = dict(attrs={'class':'fb-like'})
#remove_tags_before = dict()
@ -35,9 +40,24 @@ class Poltergeist(BasicNewsRecipe):
s['class'] = 'floatleft'
for s in soup.findAll(attrs={'style':re.compile('float: ?right')}):
s['class'] = 'floatright'
for s in soup.findAll(style=True):
if 'bold;' in s['style']:
if s.get('class', ''):
s['class'] = s['class'] + ' p_title'
else:
s['class'] = 'p_title'
if 'italic;' in s['style']:
if s.get('class', ''):
s['class'] = s['class'] + ' italic'
else:
s['class'] = 'italic'
del s['style']
tag = soup.find(id='twoja_ocena')
if tag:
tag.parent.extract()
for tag in soup.findAll(id='lista_chce_ile'):
tag.parent.parent.extract()
for r in soup.findAll(name='a', href=re.compile(r'^http://www.ceneo.pl/')):
r.extract()
return soup

File diff suppressed because one or more lines are too long

View File

@ -14,7 +14,5 @@ class Tablety_pl(BasicNewsRecipe):
max_articles_per_feed = 100
preprocess_regexps = [(re.compile(ur'<p><strong>Przeczytaj także.*?</a></strong></p>', re.DOTALL), lambda match: ''), (re.compile(ur'<p><strong>Przeczytaj koniecznie.*?</a></strong></p>', re.DOTALL), lambda match: '')]
keep_only_tags = [dict(id='news_block')]
#remove_tags_before=dict(name="h1", attrs={'class':'entry-title'})
#remove_tags_after=dict(name="footer", attrs={'class':'entry-footer clearfix'})
remove_tags=[dict(attrs={'class':['comments_icon', 'wp-polls', 'entry-comments']})]
remove_tags=[dict(attrs={'class':['comments_icon', 'wp-polls', 'entry-comments', 'wp-polls-loading', 'ts-fab-wrapper', 'entry-footer']})]
feeds = [(u'Najnowsze posty', u'http://www.tablety.pl/feed/')]