Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update various Polish recipes

Browse Source
This commit is contained in:
Kovid Goyal 2011-11-16 07:52:12 +05:30
parent 40d0c7e3ee
commit efdad01e01
4 changed files with 27 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
recipes/di.recipe
View File

@ -46,7 +46,8 @@ class DziennikInternautowRecipe(BasicNewsRecipe):
dict(name = 'div', attrs = {'class' : 'poradniki_context'}),
dict(name = 'div', attrs = {'class' : 'uniBox'}),
dict(name = 'object', attrs = {}),
dict(name = 'h3', attrs = {})
dict(name = 'h3', attrs = {}),
dict(attrs={'class':'twitter-share-button'})
]
preprocess_regexps = [
@ -58,3 +59,8 @@ class DziennikInternautowRecipe(BasicNewsRecipe):
(r'\s*</', lambda match: '</'),
]
]
def skip_ad_pages(self, soup):
if 'Advertisement' in soup.title:
nexturl=soup.find('a')['href']
return self.index_to_soup(nexturl, raw=True)

3
recipes/frazpc.recipe
View File

@ -18,7 +18,7 @@ class FrazPC(BasicNewsRecipe):
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
cover_url='http://www.frazpc.pl/images/logo.png'
feeds = [
(u'Aktualno\u015bci', u'http://www.frazpc.pl/feed/aktualnosci'),
(u'Artyku\u0142y', u'http://www.frazpc.pl/feed/artykuly')
@ -33,6 +33,7 @@ class FrazPC(BasicNewsRecipe):
dict(name='div', attrs={'class':'comments_box'})
]
remove_tags_after=dict(name='div', attrs={'class':'content'})
preprocess_regexps = [(re.compile(r'\| <a href="#comments">Komentarze \([0-9]*\)</a>'), lambda match: '')]
remove_attributes = [ 'width', 'height' ]

63
recipes/histmag.recipe
View File

@ -7,53 +7,18 @@ from calibre.web.feeds.news import BasicNewsRecipe
import re
class Histmag(BasicNewsRecipe):
title = u'Histmag'
oldest_article = 7
max_articles_per_feed = 100
cover_url='http://histmag.org/grafika/loga/histmag-logo-2-300px.png'
__author__ = 'matek09'
description = u"Artykuly historyczne i publicystyczne"
encoding = 'utf-8'
#preprocess_regexps = [(re.compile(r'</span>'), lambda match: '</span><br><br>'),(re.compile(r'<span>'), lambda match: '<br><br><span>')]
no_stylesheets = True
language = 'pl'
remove_javascript = True
keep_only_tags=[dict(id='article')]
remove_tags=[dict(name = 'p', attrs = {'class' : 'article-tags'})]
title = u'Histmag'
__author__ = 'matek09'
description = u"Artykuly historyczne i publicystyczne"
encoding = 'utf-8'
no_stylesheets = True
language = 'pl'
remove_javascript = True
#max_articles_per_feed = 1
remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'article'}))
remove_tags_after = dict(dict(name = 'h2', attrs = {'class' : 'komentarze'}))
#keep_only_tags =[]
#keep_only_tags.append(dict(name = 'h2'))
#keep_only_tags.append(dict(name = 'p'))
remove_tags =[]
remove_tags.append(dict(name = 'p', attrs = {'class' : 'podpis'}))
remove_tags.append(dict(name = 'h2', attrs = {'class' : 'komentarze'}))
remove_tags.append(dict(name = 'img', attrs = {'src' : 'style/buttons/wesprzyjnas-1.jpg'}))
preprocess_regexps = [(re.compile(r'</span>'), lambda match: '</span><br><br>'),
(re.compile(r'<span>'), lambda match: '<br><br><span>')]
extra_css = '''
.left {font-size: x-small}
.right {font-size: x-small}
'''
def find_articles(self, soup):
articles = []
for div in soup.findAll('div', attrs={'class' : 'text'}):
articles.append({
'title' : self.tag_to_string(div.h3.a),
'url' : 'http://www.histmag.org/' + div.h3.a['href'],
'date' : self.tag_to_string(div.next('p')).split('|')[0],
'description' : self.tag_to_string(div.next('p', podpis=False)),
})
return articles
def parse_index(self):
soup = self.index_to_soup('http://histmag.org/?arc=4&dx=0')
feeds = []
feeds.append((u"Artykuly historyczne", self.find_articles(soup)))
soup = self.index_to_soup('http://histmag.org/?arc=5&dx=0')
feeds.append((u"Artykuly publicystyczne", self.find_articles(soup)))
soup = self.index_to_soup('http://histmag.org/?arc=1&dx=0')
feeds.append((u"Wydarzenia", self.find_articles(soup)))
return feeds
feeds = [(u'Wszystkie', u'http://histmag.org/rss/wszystkie.xml'), (u'Wydarzenia', u'http://histmag.org/rss/wydarzenia.xml'), (u'Recenzje', u'http://histmag.org/rss/recenzje.xml'), (u'Artykuły historyczne', u'http://histmag.org/rss/historia.xml'), (u'Publicystyka', u'http://histmag.org/rss/publicystyka.xml')]

6
recipes/osnews_pl.recipe
View File

@ -23,7 +23,7 @@ class OSNewsRecipe(BasicNewsRecipe):
oldest_article = 7
max_articles_per_feed = 100
cover_url='http://osnews.pl/wp-content/themes/osnews/img/logo.png'
extra_css = '''
.news-heading {font-size:150%}
.newsinformations li {display:inline;}
@ -44,7 +44,9 @@ class OSNewsRecipe(BasicNewsRecipe):
dict(name = 'div', attrs = {'class' : 'sociable'}),
dict(name = 'div', attrs = {'class' : 'post_prev'}),
dict(name = 'div', attrs = {'class' : 'post_next'}),
dict(name = 'div', attrs = {'class' : 'clr'})
dict(name = 'div', attrs = {'class' : 'clr'}),
dict(name = 'div', attrs = {'class' : 'tw_button'}),
dict(name = 'div', attrs = {'style' : 'width:56px;height:60px;float:left;margin-right:10px'})
]
preprocess_regexps = [(re.compile(u'</span>Komentarze: \(?[0-9]+\)? ?<span'), lambda match: '</span><span')]