Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Various new and updated Polish news sources

Browse Source
This commit is contained in:
Kovid Goyal 2013-03-21 10:07:08 +05:30
commit fcf3d082be
46 changed files with 584 additions and 221 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.bzrignore
View File

@ -38,6 +38,8 @@ calibre_plugins/
recipes/.git
recipes/.gitignore
recipes/README.md
recipes/icon_checker.py
recipes/readme_updater.py
recipes/katalog_egazeciarz.recipe
recipes/tv_axnscifi.recipe
recipes/tv_comedycentral.recipe
@ -60,6 +62,7 @@ recipes/tv_tvpkultura.recipe
recipes/tv_tvppolonia.recipe
recipes/tv_tvpuls.recipe
recipes/tv_viasathistory.recipe
recipes/icons/katalog_egazeciarz.png
recipes/icons/tv_axnscifi.png
recipes/icons/tv_comedycentral.png
recipes/icons/tv_discoveryscience.png

25
recipes/adventure_zone_pl.recipe
View File

@ -21,35 +21,24 @@ class Adventure_zone(BasicNewsRecipe):
extra_css = '.main-bg{text-align: left;} td.capmain{ font-size: 22px; }'
feeds = [(u'Nowinki', u'http://www.adventure-zone.info/fusion/feeds/news.php')]
'''def parse_feeds (self):
feeds = BasicNewsRecipe.parse_feeds(self)
soup=self.index_to_soup(u'http://www.adventure-zone.info/fusion/feeds/news.php')
tag=soup.find(name='channel')
titles=[]
for r in tag.findAll(name='image'):
r.extract()
art=tag.findAll(name='item')
for i in art:
titles.append(i.title.string)
for feed in feeds:
for article in feed.articles[:]:
article.title=titles[feed.articles.index(article)]
return feeds'''
'''def get_cover_url(self):
soup = self.index_to_soup('http://www.adventure-zone.info/fusion/news.php')
cover=soup.find(id='box_OstatninumerAZ')
self.cover_url='http://www.adventure-zone.info/fusion/'+ cover.center.a.img['src']
return getattr(self, 'cover_url', self.cover_url)'''
def populate_article_metadata(self, article, soup, first):
result = re.search('(.+) - Adventure Zone', soup.title.string)
if result:
article.title = result.group(1)
result = result.group(1)
else:
result = soup.body.find('strong')
if result:
article.title = result.string
result = result.string
if result:
result = result.replace('&', '&')
result = result.replace(''', '’')
article.title = result
def skip_ad_pages(self, soup):
skip_tag = soup.body.find(name='td', attrs={'class':'main-bg'})

53
recipes/benchmark_pl.recipe
View File

@ -1,5 +1,7 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.ebooks.BeautifulSoup import Comment
class BenchmarkPl(BasicNewsRecipe):
title = u'Benchmark.pl'
__author__ = 'fenuks'
@ -13,10 +15,10 @@ class BenchmarkPl(BasicNewsRecipe):
no_stylesheets = True
remove_attributes = ['style']
preprocess_regexps = [(re.compile(ur'<h3><span style="font-size: small;">&nbsp;Zobacz poprzednie <a href="http://www.benchmark.pl/news/zestawienie/grupa_id/135">Opinie dnia:</a></span>.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>'), (re.compile(ur'Więcej o .*?</ul>', re.DOTALL|re.IGNORECASE), lambda match: '')]
keep_only_tags=[dict(name='div', attrs={'class':['m_zwykly', 'gallery']}), dict(id='article')]
remove_tags_after=dict(name='div', attrs={'class':'body'})
remove_tags=[dict(name='div', attrs={'class':['kategoria', 'socialize', 'thumb', 'panelOcenaObserwowane', 'categoryNextToSocializeGallery', 'breadcrumb', 'footer', 'moreTopics']}), dict(name='table', attrs={'background':'http://www.benchmark.pl/uploads/backend_img/a/fotki_newsy/opinie_dnia/bg.png'}), dict(name='table', attrs={'width':'210', 'cellspacing':'1', 'cellpadding':'4', 'border':'0', 'align':'right'})]
INDEX= 'http://www.benchmark.pl'
keep_only_tags = [dict(name='div', attrs={'class':['m_zwykly', 'gallery']}), dict(id='article')]
remove_tags_after = dict(id='article')
remove_tags = [dict(name='div', attrs={'class':['comments', 'body', 'kategoria', 'socialize', 'thumb', 'panelOcenaObserwowane', 'categoryNextToSocializeGallery', 'breadcrumb', 'footer', 'moreTopics']}), dict(name='table', attrs = {'background':'http://www.benchmark.pl/uploads/backend_img/a/fotki_newsy/opinie_dnia/bg.png'}), dict(name='table', attrs={'width':'210', 'cellspacing':'1', 'cellpadding':'4', 'border':'0', 'align':'right'})]
INDEX = 'http://www.benchmark.pl'
feeds = [(u'Aktualności', u'http://www.benchmark.pl/rss/aktualnosci-pliki.xml'),
(u'Testy i recenzje', u'http://www.benchmark.pl/rss/testy-recenzje-minirecenzje.xml')]
@ -27,7 +29,12 @@ class BenchmarkPl(BasicNewsRecipe):
soup2 = self.index_to_soup(nexturl['href'])
nexturl = soup2.find(attrs={'class':'next'})
pagetext = soup2.find(name='div', attrs={'class':'body'})
appendtag.find('div', attrs={'class':'k_ster'}).extract()
tag = appendtag.find('div', attrs={'class':'k_ster'})
if tag:
tag.extract()
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
if appendtag.find('div', attrs={'class':'k_ster'}):
@ -37,40 +44,44 @@ class BenchmarkPl(BasicNewsRecipe):
def image_article(self, soup, appendtag):
nexturl=soup.find('div', attrs={'class':'preview'})
if nexturl is not None:
nexturl=nexturl.find('a', attrs={'class':'move_next'})
image=appendtag.find('div', attrs={'class':'preview'}).div['style'][16:]
image=self.INDEX + image[:image.find("')")]
nexturl = soup.find('div', attrs={'class':'preview'})
if nexturl:
nexturl = nexturl.find('a', attrs={'class':'move_next'})
image = appendtag.find('div', attrs={'class':'preview'}).div['style'][16:]
image = self.INDEX + image[:image.find("')")]
appendtag.find(attrs={'class':'preview'}).name='img'
appendtag.find(attrs={'class':'preview'})['src']=image
appendtag.find('a', attrs={'class':'move_next'}).extract()
while nexturl is not None:
nexturl= self.INDEX + nexturl['href']
while nexturl:
nexturl = self.INDEX + nexturl['href']
soup2 = self.index_to_soup(nexturl)
nexturl=soup2.find('a', attrs={'class':'move_next'})
image=soup2.find('div', attrs={'class':'preview'}).div['style'][16:]
image=self.INDEX + image[:image.find("')")]
nexturl = soup2.find('a', attrs={'class':'move_next'})
image = soup2.find('div', attrs={'class':'preview'}).div['style'][16:]
image = self.INDEX + image[:image.find("')")]
soup2.find(attrs={'class':'preview'}).name='img'
soup2.find(attrs={'class':'preview'})['src']=image
pagetext=soup2.find('div', attrs={'class':'gallery'})
pagetext = soup2.find('div', attrs={'class':'gallery'})
pagetext.find('div', attrs={'class':'title'}).extract()
pagetext.find('div', attrs={'class':'thumb'}).extract()
pagetext.find('div', attrs={'class':'panelOcenaObserwowane'}).extract()
if nexturl is not None:
if nexturl:
pagetext.find('a', attrs={'class':'move_next'}).extract()
pagetext.find('a', attrs={'class':'move_back'}).extract()
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
def preprocess_html(self, soup):
if soup.find('div', attrs={'class':'preview'}) is not None:
if soup.find('div', attrs={'class':'preview'}):
self.image_article(soup, soup.body)
else:
self.append_page(soup, soup.body)
for a in soup('a'):
if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']:
a['href']=self.INDEX + a['href']
if a.has_key('href') and not a['href'].startswith('http'):
a['href'] = self.INDEX + a['href']
for r in soup.findAll(attrs={'class':['comments', 'body']}):
r.extract()
return soup

2
recipes/biweekly.recipe
View File

@ -14,7 +14,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class biweekly(BasicNewsRecipe):
__author__ = u'Łukasz Grąbczewski'
title = 'Biweekly'
language = 'en'
language = 'en_PL'
publisher = 'National Audiovisual Institute'
publication_type = 'magazine'
description = u'link with culture [English edition of Polish magazine]: literature, theatre, film, art, music, views, talks'

30
recipes/blog_biszopa.recipe Normal file
View File

@ -0,0 +1,30 @@
__license__ = 'GPL v3'
from calibre.web.feeds.news import BasicNewsRecipe
class BlogBiszopa(BasicNewsRecipe):
title = u'Blog Biszopa'
__author__ = 'fenuks'
description = u'Zapiski z Granitowego Miasta'
category = 'history'
#publication_type = ''
language = 'pl'
#encoding = ''
#extra_css = ''
cover_url = 'http://blogbiszopa.pl/wp-content/themes/biszop/images/logo.png'
masthead_url = ''
use_embedded_content = False
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
remove_javascript = True
remove_attributes = ['style', 'font']
ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [dict(id='main-content')]
remove_tags = [dict(name='footer')]
#remove_tags_after = {}
#remove_tags_before = {}
feeds = [(u'Artyku\u0142y', u'http://blogbiszopa.pl/feed/')]

55
recipes/ciekawostki_historyczne.recipe
View File

@ -1,5 +1,6 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
class Ciekawostki_Historyczne(BasicNewsRecipe):
title = u'Ciekawostki Historyczne'
oldest_article = 7
@ -7,42 +8,30 @@ class Ciekawostki_Historyczne(BasicNewsRecipe):
description = u'Serwis popularnonaukowy - odkrycia, kontrowersje, historia, ciekawostki, badania, ciekawostki z przeszłości.'
category = 'history'
language = 'pl'
masthead_url= 'http://ciekawostkihistoryczne.pl/wp-content/themes/Wordpress_Magazine/images/logo-ciekawostki-historyczne-male.jpg'
cover_url='http://ciekawostkihistoryczne.pl/wp-content/themes/Wordpress_Magazine/images/logo-ciekawostki-historyczne-male.jpg'
masthead_url = 'http://ciekawostkihistoryczne.pl/wp-content/themes/Wordpress_Magazine/images/logo-ciekawostki-historyczne-male.jpg'
cover_url = 'http://ciekawostkihistoryczne.pl/wp-content/themes/Wordpress_Magazine/images/logo-ciekawostki-historyczne-male.jpg'
max_articles_per_feed = 100
oldest_article = 140000
preprocess_regexps = [(re.compile(ur'Ten artykuł ma kilka stron.*?</fb:like>', re.DOTALL), lambda match: ''), (re.compile(ur'<h2>Zobacz też:</h2>.*?</ol>', re.DOTALL), lambda match: '')]
no_stylesheets=True
remove_empty_feeds=True
keep_only_tags=[dict(name='div', attrs={'class':'post'})]
remove_tags=[dict(id='singlepostinfo')]
no_stylesheets = True
remove_empty_feeds = True
keep_only_tags = [dict(name='div', attrs={'class':'post'})]
recursions = 5
remove_tags = [dict(id='singlepostinfo')]
feeds = [(u'Staro\u017cytno\u015b\u0107', u'http://ciekawostkihistoryczne.pl/tag/starozytnosc/feed/'), (u'\u015aredniowiecze', u'http://ciekawostkihistoryczne.pl/tag/sredniowiecze/feed/'), (u'Nowo\u017cytno\u015b\u0107', u'http://ciekawostkihistoryczne.pl/tag/nowozytnosc/feed/'), (u'XIX wiek', u'http://ciekawostkihistoryczne.pl/tag/xix-wiek/feed/'), (u'1914-1939', u'http://ciekawostkihistoryczne.pl/tag/1914-1939/feed/'), (u'1939-1945', u'http://ciekawostkihistoryczne.pl/tag/1939-1945/feed/'), (u'Powojnie (od 1945)', u'http://ciekawostkihistoryczne.pl/tag/powojnie/feed/'), (u'Recenzje', u'http://ciekawostkihistoryczne.pl/category/recenzje/feed/')]
def append_page(self, soup, appendtag):
tag=soup.find(name='h7')
if tag:
if tag.br:
pass
elif tag.nextSibling.name=='p':
tag=tag.nextSibling
nexturl = tag.findAll('a')
for nextpage in nexturl:
tag.extract()
nextpage= nextpage['href']
soup2 = self.index_to_soup(nextpage)
pagetext = soup2.find(name='div', attrs={'class':'post'})
for r in pagetext.findAll('div', attrs={'id':'singlepostinfo'}):
r.extract()
for r in pagetext.findAll('div', attrs={'class':'wp-caption alignright'}):
r.extract()
for r in pagetext.findAll('h1'):
r.extract()
pagetext.find('h6').nextSibling.extract()
pagetext.find('h7').nextSibling.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
def is_link_wanted(self, url, tag):
return 'ciekawostkihistoryczne' in url and url[-2] in {'2', '3', '4', '5', '6'}
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
def postprocess_html(self, soup, first_fetch):
tag = soup.find('h7')
if tag:
tag.nextSibling.extract()
if not first_fetch:
for r in soup.findAll(['h1']):
r.extract()
soup.find('h6').nextSibling.extract()
return soup

16
recipes/computerworld_pl.recipe
View File

@ -1,5 +1,5 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Computerworld_pl(BasicNewsRecipe):
title = u'Computerworld.pl'
@ -12,8 +12,16 @@ class Computerworld_pl(BasicNewsRecipe):
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100
keep_only_tags = [dict(attrs={'class':['tyt_news', 'prawo', 'autor', 'tresc']})]
remove_tags_after = dict(name='div', attrs={'class':'rMobi'})
remove_tags = [dict(name='div', attrs={'class':['nnav', 'rMobi']}), dict(name='table', attrs={'class':'ramka_slx'})]
remove_attributes = ['style',]
preprocess_regexps = [(re.compile(u'Zobacz również:', re.IGNORECASE), lambda m: ''), (re.compile(ur'[*]+reklama[*]+', re.IGNORECASE), lambda m: ''),]
keep_only_tags = [dict(id=['szpaltaL', 's2011'])]
remove_tags_after = dict(name='div', attrs={'class':'tresc'})
remove_tags = [dict(attrs={'class':['nnav', 'rMobi', 'tagi', 'rec']}),]
feeds = [(u'Wiadomo\u015bci', u'http://rssout.idg.pl/cw/news_iso.xml')]
def skip_ad_pages(self, soup):
if soup.title.string.lower() == 'advertisement':
tag = soup.find(name='a')
if tag:
new_soup = self.index_to_soup(tag['href'], raw=True)
return new_soup

8
recipes/conowego_pl.recipe
View File

@ -1,5 +1,6 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Comment
class CoNowegoPl(BasicNewsRecipe):
title = u'conowego.pl'
__author__ = 'fenuks'
@ -34,7 +35,10 @@ class CoNowegoPl(BasicNewsRecipe):
pagetext = soup2.find(attrs={'class':'ni_content'})
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
for r in appendtag.findAll(attrs={'class':['pages', 'paginationWrap']}):
r.extract()

1
recipes/drytooling_pl.recipe
View File

@ -8,6 +8,7 @@ class BasicUserRecipe1337668045(BasicNewsRecipe):
cover_url = 'http://drytooling.com.pl/images/drytooling-kindle.png'
description = u'Drytooling.com.pl jest serwisem wspinaczki zimowej, alpinizmu i himalaizmu. Jeśli uwielbiasz zimę, nie możesz doczekać się aż wyciągniesz szpej z szafki i uderzysz w Tatry, Alpy, czy może Himalaje, to znajdziesz tutaj naprawdę dużo interesujących Cię treści! Zapraszamy!'
__author__ = u'Damian Granowski'
language = 'pl'
oldest_article = 100
max_articles_per_feed = 20
auto_cleanup = True

20
recipes/dzieje_pl.recipe
View File

@ -1,4 +1,5 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class Dzieje(BasicNewsRecipe):
title = u'dzieje.pl'
@ -11,8 +12,8 @@ class Dzieje(BasicNewsRecipe):
index = 'http://dzieje.pl'
oldest_article = 8
max_articles_per_feed = 100
remove_javascript=True
no_stylesheets= True
remove_javascript = True
no_stylesheets = True
keep_only_tags = [dict(name='h1', attrs={'class':'title'}), dict(id='content-area')]
remove_tags = [dict(attrs={'class':'field field-type-computed field-field-tagi'}), dict(id='dogory')]
#feeds = [(u'Dzieje', u'http://dzieje.pl/rss.xml')]
@ -28,16 +29,19 @@ class Dzieje(BasicNewsRecipe):
pagetext = soup2.find(id='content-area').find(attrs={'class':'content'})
for r in pagetext.findAll(attrs={'class':['fieldgroup group-groupkul', 'fieldgroup group-zdjeciekult', 'fieldgroup group-zdjecieciekaw', 'fieldgroup group-zdjecieksiazka', 'fieldgroup group-zdjeciedu', 'field field-type-filefield field-field-zdjecieglownawyd']}):
r.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
# appendtag.insert(pos, pagetext)
tag = soup2.find('li', attrs={'class':'pager-next'})
for r in appendtag.findAll(attrs={'class':['item-list', 'field field-type-computed field-field-tagi', ]}):
r.extract()
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def find_articles(self, url):
articles = []
soup=self.index_to_soup(url)
tag=soup.find(id='content-area').div.div
soup = self.index_to_soup(url)
tag = soup.find(id='content-area').div.div
for i in tag.findAll('div', recursive=False):
temp = i.find(attrs={'class':'views-field-title'}).span.a
title = temp.string
@ -64,7 +68,7 @@ class Dzieje(BasicNewsRecipe):
def preprocess_html(self, soup):
for a in soup('a'):
if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']:
a['href']=self.index + a['href']
if a.has_key('href') and not a['href'].startswith('http'):
a['href'] = self.index + a['href']
self.append_page(soup, soup.body)
return soup

29
recipes/dziennik_pl.recipe
View File

@ -2,6 +2,8 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.ebooks.BeautifulSoup import Comment
class Dziennik_pl(BasicNewsRecipe):
title = u'Dziennik.pl'
__author__ = 'fenuks'
@ -9,17 +11,17 @@ class Dziennik_pl(BasicNewsRecipe):
category = 'newspaper'
language = 'pl'
masthead_url= 'http://5.s.dziennik.pl/images/logos.png'
cover_url= 'http://5.s.dziennik.pl/images/logos.png'
cover_url = 'http://5.s.dziennik.pl/images/logos.png'
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100
remove_javascript=True
remove_empty_feeds=True
remove_javascript = True
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
extra_css= 'ul {list-style: none; padding: 0; margin: 0;} li {float: left;margin: 0 0.15em;}'
extra_css = 'ul {list-style: none; padding: 0; margin: 0;} li {float: left;margin: 0 0.15em;}'
preprocess_regexps = [(re.compile("Komentarze:"), lambda m: ''), (re.compile('<p><strong><a href=".*?">&gt;&gt;&gt; CZYTAJ TAKŻE: ".*?"</a></strong></p>'), lambda m: '')]
keep_only_tags=[dict(id='article')]
remove_tags=[dict(name='div', attrs={'class':['art_box_dodatki', 'new_facebook_icons2', 'leftArt', 'article_print', 'quiz-widget', 'belka-spol', 'belka-spol belka-spol-bottom', 'art_data_tags', 'cl_right', 'boxRounded gal_inside']}), dict(name='a', attrs={'class':['komentarz', 'article_icon_addcommnent']})]
keep_only_tags = [dict(id='article')]
remove_tags = [dict(name='div', attrs={'class':['art_box_dodatki', 'new_facebook_icons2', 'leftArt', 'article_print', 'quiz-widget', 'belka-spol', 'belka-spol belka-spol-bottom', 'art_data_tags', 'cl_right', 'boxRounded gal_inside']}), dict(name='a', attrs={'class':['komentarz', 'article_icon_addcommnent']})]
feeds = [(u'Wszystko', u'http://rss.dziennik.pl/Dziennik-PL/'),
(u'Wiadomości', u'http://rss.dziennik.pl/Dziennik-Wiadomosci'),
(u'Gospodarka', u'http://rss.dziennik.pl/Dziennik-Gospodarka'),
@ -34,26 +36,29 @@ class Dziennik_pl(BasicNewsRecipe):
(u'Nieruchomości', u'http://rss.dziennik.pl/Dziennik-Nieruchomosci')]
def skip_ad_pages(self, soup):
tag=soup.find(name='a', attrs={'title':'CZYTAJ DALEJ'})
tag = soup.find(name='a', attrs={'title':'CZYTAJ DALEJ'})
if tag:
new_soup=self.index_to_soup(tag['href'], raw=True)
new_soup = self.index_to_soup(tag['href'], raw=True)
return new_soup
def append_page(self, soup, appendtag):
tag=soup.find('a', attrs={'class':'page_next'})
tag = soup.find('a', attrs={'class':'page_next'})
if tag:
appendtag.find('div', attrs={'class':'article_paginator'}).extract()
while tag:
soup2= self.index_to_soup(tag['href'])
tag=soup2.find('a', attrs={'class':'page_next'})
soup2 = self.index_to_soup(tag['href'])
tag = soup2.find('a', attrs={'class':'page_next'})
if not tag:
for r in appendtag.findAll('div', attrs={'class':'art_src'}):
r.extract()
pagetext = soup2.find(name='div', attrs={'class':'article_body'})
for dictionary in self.remove_tags:
v=pagetext.findAll(name=dictionary['name'], attrs=dictionary['attrs'])
v = pagetext.findAll(name=dictionary['name'], attrs=dictionary['attrs'])
for delete in v:
delete.extract()
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
if appendtag.find('div', attrs={'class':'article_paginator'}):

6
recipes/dziennik_wschodni.recipe
View File

@ -1,5 +1,7 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class DziennikWschodni(BasicNewsRecipe):
title = u'Dziennik Wschodni'
__author__ = 'fenuks'
@ -72,6 +74,10 @@ class DziennikWschodni(BasicNewsRecipe):
if pagetext:
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)

5
recipes/echo_dnia.recipe
View File

@ -1,5 +1,6 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class EchoDnia(BasicNewsRecipe):
title = u'Echo Dnia'
@ -68,6 +69,10 @@ class EchoDnia(BasicNewsRecipe):
if pagetext:
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)

210
recipes/esenja.recipe
View File

@ -3,85 +3,153 @@
__license__ = 'GPL v3'
__copyright__ = '2010, matek09, matek09@gmail.com'
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Comment
class Esensja(BasicNewsRecipe):
title = u'Esensja'
__author__ = 'matek09'
description = 'Monthly magazine'
encoding = 'utf-8'
no_stylesheets = True
language = 'pl'
remove_javascript = True
HREF = '0'
title = u'Esensja'
__author__ = 'matek09 & fenuks'
description = 'Magazyn kultury popularnej'
encoding = 'utf-8'
no_stylesheets = True
language = 'pl'
remove_javascript = True
masthead_url = 'http://esensja.pl/img/wrss.gif'
oldest_article = 1
URL = 'http://esensja.pl'
HREF = '0'
remove_attributes = ['style', 'bgcolor', 'alt', 'color']
keep_only_tags = [dict(attrs={'class':'sekcja'}), ]
#keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'article'})
#remove_tags_before = dict(dict(name = 'div', attrs = {'class' : 't-title'}))
remove_tags_after = dict(id='tekst')
#keep_only_tags =[]
#keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'article'})
remove_tags_before = dict(dict(name = 'div', attrs = {'class' : 't-title'}))
remove_tags_after = dict(dict(name = 'img', attrs = {'src' : '../../../2000/01/img/tab_bot.gif'}))
remove_tags = [dict(name = 'img', attrs = {'src' : ['../../../2000/01/img/tab_top.gif', '../../../2000/01/img/tab_bot.gif']}),
dict(name = 'div', attrs = {'class' : 't-title2 nextpage'}),
#dict(attrs={'rel':'lightbox[galeria]'})
dict(attrs={'class':['tekst_koniec', 'ref', 'wykop']}),
dict(attrs={'itemprop':['copyrightHolder', 'publisher']}),
dict(id='komentarze')
]
remove_tags =[]
remove_tags.append(dict(name = 'img', attrs = {'src' : '../../../2000/01/img/tab_top.gif'}))
remove_tags.append(dict(name = 'img', attrs = {'src' : '../../../2000/01/img/tab_bot.gif'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 't-title2 nextpage'}))
extra_css = '''
.t-title {font-size: x-large; font-weight: bold; text-align: left}
.t-author {font-size: x-small; text-align: left}
.t-title2 {font-size: x-small; font-style: italic; text-align: left}
.text {font-size: small; text-align: left}
.annot-ref {font-style: italic; text-align: left}
'''
extra_css = '''
.t-title {font-size: x-large; font-weight: bold; text-align: left}
.t-author {font-size: x-small; text-align: left}
.t-title2 {font-size: x-small; font-style: italic; text-align: left}
.text {font-size: small; text-align: left}
.annot-ref {font-style: italic; text-align: left}
'''
preprocess_regexps = [(re.compile(r'alt="[^"]*"'), lambda match: ''),
(re.compile(ur'(title|alt)="[^"]*?"', re.DOTALL), lambda match: ''),
]
preprocess_regexps = [(re.compile(r'alt="[^"]*"'),
lambda match: '')]
def parse_index(self):
soup = self.index_to_soup('http://www.esensja.pl/magazyn/')
a = soup.find('a', attrs={'href' : re.compile('.*/index.html')})
year = a['href'].split('/')[0]
month = a['href'].split('/')[1]
self.HREF = 'http://www.esensja.pl/magazyn/' + year + '/' + month + '/iso/'
soup = self.index_to_soup(self.HREF + '01.html')
self.cover_url = 'http://www.esensja.pl/magazyn/' + year + '/' + month + '/img/ilustr/cover_b.jpg'
feeds = []
chapter = ''
subchapter = ''
articles = []
intro = soup.find('div', attrs={'class' : 'n-title'})
'''
introduction = {'title' : self.tag_to_string(intro.a),
'url' : self.HREF + intro.a['href'],
'date' : '',
'description' : ''}
chapter = 'Wprowadzenie'
articles.append(introduction)
'''
for tag in intro.findAllNext(attrs={'class': ['chapter', 'subchapter', 'n-title']}):
if tag.name in 'td':
if len(articles) > 0:
section = chapter
if len(subchapter) > 0:
section += ' - ' + subchapter
feeds.append((section, articles))
articles = []
if tag['class'] == 'chapter':
chapter = self.tag_to_string(tag).capitalize()
subchapter = ''
else:
subchapter = self.tag_to_string(tag)
subchapter = self.tag_to_string(tag)
continue
finalurl = tag.a['href']
if not finalurl.startswith('http'):
finalurl = self.HREF + finalurl
articles.append({'title' : self.tag_to_string(tag.a), 'url' : finalurl, 'date' : '', 'description' : ''})
a = self.index_to_soup(finalurl)
i = 1
while True:
div = a.find('div', attrs={'class' : 't-title2 nextpage'})
if div is not None:
link = div.a['href']
if not link.startswith('http'):
link = self.HREF + link
a = self.index_to_soup(link)
articles.append({'title' : self.tag_to_string(tag.a) + ' c. d. ' + str(i), 'url' : link, 'date' : '', 'description' : ''})
i = i + 1
else:
break
def parse_index(self):
soup = self.index_to_soup('http://www.esensja.pl/magazyn/')
a = soup.find('a', attrs={'href' : re.compile('.*/index.html')})
year = a['href'].split('/')[0]
month = a['href'].split('/')[1]
self.HREF = 'http://www.esensja.pl/magazyn/' + year + '/' + month + '/iso/'
soup = self.index_to_soup(self.HREF + '01.html')
self.cover_url = 'http://www.esensja.pl/magazyn/' + year + '/' + month + '/img/ilustr/cover_b.jpg'
feeds = []
intro = soup.find('div', attrs={'class' : 'n-title'})
introduction = {'title' : self.tag_to_string(intro.a),
'url' : self.HREF + intro.a['href'],
'date' : '',
'description' : ''}
chapter = 'Wprowadzenie'
subchapter = ''
articles = []
articles.append(introduction)
for tag in intro.findAllNext(attrs={'class': ['chapter', 'subchapter', 'n-title']}):
if tag.name in 'td':
if len(articles) > 0:
section = chapter
if len(subchapter) > 0:
section += ' - ' + subchapter
feeds.append((section, articles))
articles = []
if tag['class'] == 'chapter':
chapter = self.tag_to_string(tag).capitalize()
subchapter = ''
else:
subchapter = self.tag_to_string(tag)
subchapter = self.tag_to_string(tag)
continue
articles.append({'title' : self.tag_to_string(tag.a), 'url' : self.HREF + tag.a['href'], 'date' : '', 'description' : ''})
return feeds
a = self.index_to_soup(self.HREF + tag.a['href'])
i = 1
while True:
div = a.find('div', attrs={'class' : 't-title2 nextpage'})
if div is not None:
a = self.index_to_soup(self.HREF + div.a['href'])
articles.append({'title' : self.tag_to_string(tag.a) + ' c. d. ' + str(i), 'url' : self.HREF + div.a['href'], 'date' : '', 'description' : ''})
i = i + 1
else:
break
def append_page(self, soup, appendtag):
r = appendtag.find(attrs={'class':'wiecej_xxx'})
if r:
nr = r.findAll(attrs={'class':'tn-link'})[-1]
try:
nr = int(nr.a.string)
except:
return
baseurl = soup.find(attrs={'property':'og:url'})['content'] + '&strona={0}'
for number in range(2, nr+1):
soup2 = self.index_to_soup(baseurl.format(number))
pagetext = soup2.find(attrs={'class':'tresc'})
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class':['wiecej_xxx', 'tekst_koniec']}):
r.extract()
for r in appendtag.findAll('script'):
r.extract()
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
for tag in soup.findAll(attrs={'class':'img_box_right'}):
temp = tag.find('img')
src = ''
if temp:
src = temp.get('src', '')
for r in tag.findAll('a', recursive=False):
r.extract()
info = tag.find(attrs={'class':'img_info'})
text = str(tag)
if not src:
src = re.search('src="[^"]*?"', text)
if src:
src = src.group(0)
src = src[5:].replace('//', '/')
if src:
tag.contents = []
tag.insert(0, BeautifulSoup('<img src="{0}{1}" />'.format(self.URL, src)))
if info:
tag.insert(len(tag.contents), info)
return soup
return feeds

109
recipes/esensja_(rss).recipe Normal file
View File

@ -0,0 +1,109 @@
__license__ = 'GPL v3'
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Comment
class EsensjaRSS(BasicNewsRecipe):
title = u'Esensja (RSS)'
__author__ = 'fenuks'
description = u'Magazyn kultury popularnej'
category = 'reading, fantasy, reviews, boardgames, culture'
#publication_type = ''
language = 'pl'
encoding = 'utf-8'
INDEX = 'http://www.esensja.pl'
extra_css = '''.t-title {font-size: x-large; font-weight: bold; text-align: left}
.t-author {font-size: x-small; text-align: left}
.t-title2 {font-size: x-small; font-style: italic; text-align: left}
.text {font-size: small; text-align: left}
.annot-ref {font-style: italic; text-align: left}
'''
cover_url = ''
masthead_url = 'http://esensja.pl/img/wrss.gif'
use_embedded_content = False
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
remove_javascript = True
ignore_duplicate_articles = {'title', 'url'}
preprocess_regexps = [(re.compile(r'alt="[^"]*"'), lambda match: ''),
(re.compile(ur'(title|alt)="[^"]*?"', re.DOTALL), lambda match: ''),
]
remove_attributes = ['style', 'bgcolor', 'alt', 'color']
keep_only_tags = [dict(attrs={'class':'sekcja'}), ]
remove_tags_after = dict(id='tekst')
remove_tags = [dict(name = 'img', attrs = {'src' : ['../../../2000/01/img/tab_top.gif', '../../../2000/01/img/tab_bot.gif']}),
dict(name = 'div', attrs = {'class' : 't-title2 nextpage'}),
#dict(attrs={'rel':'lightbox[galeria]'})
dict(attrs={'class':['tekst_koniec', 'ref', 'wykop']}),
dict(attrs={'itemprop':['copyrightHolder', 'publisher']}),
dict(id='komentarze')
]
feeds = [(u'Książka', u'http://esensja.pl/rss/ksiazka.rss'),
(u'Film', u'http://esensja.pl/rss/film.rss'),
(u'Komiks', u'http://esensja.pl/rss/komiks.rss'),
(u'Gry', u'http://esensja.pl/rss/gry.rss'),
(u'Muzyka', u'http://esensja.pl/rss/muzyka.rss'),
(u'Twórczość', u'http://esensja.pl/rss/tworczosc.rss'),
(u'Varia', u'http://esensja.pl/rss/varia.rss'),
(u'Zgryźliwi Tetrycy', u'http://esensja.pl/rss/tetrycy.rss'),
(u'Nowe książki', u'http://esensja.pl/rss/xnowosci.rss'),
(u'Ostatnio dodane książki', u'http://esensja.pl/rss/xdodane.rss'),
]
def get_cover_url(self):
soup = self.index_to_soup(self.INDEX)
cover = soup.find(id='panel_1')
self.cover_url = self.INDEX + cover.find('a')['href'].replace('index.html', '') + 'img/ilustr/cover_b.jpg'
return getattr(self, 'cover_url', self.cover_url)
def append_page(self, soup, appendtag):
r = appendtag.find(attrs={'class':'wiecej_xxx'})
if r:
nr = r.findAll(attrs={'class':'tn-link'})[-1]
try:
nr = int(nr.a.string)
except:
return
baseurl = soup.find(attrs={'property':'og:url'})['content'] + '&strona={0}'
for number in range(2, nr+1):
soup2 = self.index_to_soup(baseurl.format(number))
pagetext = soup2.find(attrs={'class':'tresc'})
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class':['wiecej_xxx', 'tekst_koniec']}):
r.extract()
for r in appendtag.findAll('script'):
r.extract()
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
for tag in soup.findAll(attrs={'class':'img_box_right'}):
temp = tag.find('img')
src = ''
if temp:
src = temp.get('src', '')
for r in tag.findAll('a', recursive=False):
r.extract()
info = tag.find(attrs={'class':'img_info'})
text = str(tag)
if not src:
src = re.search('src="[^"]*?"', text)
if src:
src = src.group(0)
src = src[5:].replace('//', '/')
if src:
tag.contents = []
tag.insert(0, BeautifulSoup('<img src="{0}{1}" />'.format(self.INDEX, src)))
if info:
tag.insert(len(tag.contents), info)
return soup

18
recipes/film_web.recipe
View File

@ -1,6 +1,7 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class FilmWebPl(BasicNewsRecipe):
title = u'FilmWeb'
__author__ = 'fenuks'
@ -9,12 +10,14 @@ class FilmWebPl(BasicNewsRecipe):
category = 'movies'
language = 'pl'
index = 'http://www.filmweb.pl'
#extra_css = '.MarkupPhotoHTML-7 {float:left; margin-right: 10px;}'
oldest_article = 8
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
preprocess_regexps = [(re.compile(u'\(kliknij\,\ aby powiększyć\)', re.IGNORECASE), lambda m: ''), ]#(re.compile(ur' | ', re.IGNORECASE), lambda m: '')]
remove_javascript = True
preprocess_regexps = [(re.compile(u'\(kliknij\,\ aby powiększyć\)', re.IGNORECASE), lambda m: ''), (re.compile(ur'(<br ?/?>\s*?<br ?/?>\s*?)+', re.IGNORECASE), lambda m: '<br />')]#(re.compile(ur' | ', re.IGNORECASE), lambda m: '')]
extra_css = '.hdrBig {font-size:22px;} ul {list-style-type:none; padding: 0; margin: 0;}'
remove_tags = [dict(name='div', attrs={'class':['recommendOthers']}), dict(name='ul', attrs={'class':'fontSizeSet'}), dict(attrs={'class':'userSurname anno'})]
remove_attributes = ['style',]
@ -41,7 +44,12 @@ class FilmWebPl(BasicNewsRecipe):
skip_tag = soup.find('a', attrs={'class':'welcomeScreenButton'})
if skip_tag is not None:
return self.index_to_soup(skip_tag['href'], raw=True)
def postprocess_html(self, soup, first_fetch):
for r in soup.findAll(attrs={'class':'singlephoto'}):
r['style'] = 'float:left; margin-right: 10px;'
return soup
def preprocess_html(self, soup):
for a in soup('a'):
if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']:
@ -56,4 +64,8 @@ class FilmWebPl(BasicNewsRecipe):
tag.name = 'div'
for t in tag.findAll('li'):
t.name = 'div'
for r in soup.findAll(id=re.compile('photo-\d+')):
r.extract()
for r in soup.findAll(style=re.compile('float: ?left')):
r['class'] = 'singlephoto'
return soup

5
recipes/gazeta_lubuska.recipe
View File

@ -1,5 +1,6 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class GazetaLubuska(BasicNewsRecipe):
title = u'Gazeta Lubuska'
@ -58,6 +59,10 @@ class GazetaLubuska(BasicNewsRecipe):
if pagetext:
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)

5
recipes/gazeta_pomorska.recipe
View File

@ -1,5 +1,6 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class GazetaPomorska(BasicNewsRecipe):
title = u'Gazeta Pomorska'
@ -85,6 +86,10 @@ class GazetaPomorska(BasicNewsRecipe):
if pagetext:
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)

5
recipes/gazeta_wspolczesna.recipe
View File

@ -1,5 +1,6 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class GazetaWspolczesna(BasicNewsRecipe):
title = u'Gazeta Wsp\xf3\u0142czesna'
@ -57,6 +58,10 @@ class GazetaWspolczesna(BasicNewsRecipe):
if pagetext:
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)

13
recipes/gazeta_wyborcza.recipe
View File

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class Gazeta_Wyborcza(BasicNewsRecipe):
title = u'Gazeta.pl'
@ -16,6 +16,7 @@ class Gazeta_Wyborcza(BasicNewsRecipe):
max_articles_per_feed = 100
remove_javascript = True
no_stylesheets = True
ignore_duplicate_articles = {'title', 'url'}
remove_tags_before = dict(id='k0')
remove_tags_after = dict(id='banP4')
remove_tags = [dict(name='div', attrs={'class':'rel_box'}), dict(attrs={'class':['date', 'zdjP', 'zdjM', 'pollCont', 'rel_video', 'brand', 'txt_upl']}), dict(name='div', attrs={'id':'footer'})]
@ -48,6 +49,9 @@ class Gazeta_Wyborcza(BasicNewsRecipe):
url = self.INDEX + link['href']
soup2 = self.index_to_soup(url)
pagetext = soup2.find(id='artykul')
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
tag = soup2.find('div', attrs={'id': 'Str'})
@ -65,6 +69,9 @@ class Gazeta_Wyborcza(BasicNewsRecipe):
nexturl = pagetext.find(id='gal_btn_next')
if nexturl:
nexturl = nexturl.a['href']
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
rem = appendtag.find(id='gal_navi')
@ -105,3 +112,7 @@ class Gazeta_Wyborcza(BasicNewsRecipe):
soup = self.index_to_soup('http://wyborcza.pl/' + cover.contents[3].a['href'])
self.cover_url = 'http://wyborcza.pl' + soup.img['src']
return getattr(self, 'cover_url', self.cover_url)
'''def image_url_processor(self, baseurl, url):
print "@@@@@@@@", url
return url.replace('http://wyborcza.pl/ ', '')'''

55
recipes/gcn.recipe
View File

@ -1,5 +1,6 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class GCN(BasicNewsRecipe):
title = u'Gazeta Codziennej Nowiny'
@ -16,36 +17,36 @@ class GCN(BasicNewsRecipe):
remove_empty_feeds = True
no_stylesheets = True
ignore_duplicate_articles = {'title', 'url'}
preprocess_regexps = [(re.compile(ur'Czytaj:.*?</a>', re.DOTALL), lambda match: ''), (re.compile(ur'Przeczytaj także:.*?</a>', re.DOTALL|re.IGNORECASE), lambda match: ''),
remove_attributes = ['style']
preprocess_regexps = [(re.compile(ur'Czytaj:.*?</a>', re.DOTALL), lambda match: ''), (re.compile(ur'Przeczytaj także:.*?</a>', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(ur'Przeczytaj również:.*?</a>', re.DOTALL|re.IGNORECASE), lambda match: ''), (re.compile(ur'Zobacz też:.*?</a>', re.DOTALL|re.IGNORECASE), lambda match: '')]
keep_only_tags = [dict(id=['article', 'cover', 'photostory'])]
remove_tags = [dict(id=['articleTags', 'articleMeta', 'boxReadIt', 'articleGalleries', 'articleConnections',
'ForumArticleComments', 'articleRecommend', 'jedynkiLinks', 'articleGalleryConnections',
'photostoryConnections', 'articleEpaper', 'articlePoll', 'articleAlarm', 'articleByline']),
'ForumArticleComments', 'articleRecommend', 'jedynkiLinks', 'articleGalleryConnections',
'photostoryConnections', 'articleEpaper', 'articlePoll', 'articleAlarm', 'articleByline']),
dict(attrs={'class':'articleFunctions'})]
feeds = [(u'Wszystkie', u'http://www.nowiny24.pl/rss.xml'),
(u'Podkarpacie', u'http://www.nowiny24.pl/podkarpacie.xml'),
(u'Bieszczady', u'http://www.nowiny24.pl/bieszczady.xml'),
(u'Rzeszów', u'http://www.nowiny24.pl/rzeszow.xml'),
(u'Przemyśl', u'http://www.nowiny24.pl/przemysl.xml'),
(u'Leżajsk', u'http://www.nowiny24.pl/lezajsk.xml'),
(u'Łańcut', u'http://www.nowiny24.pl/lancut.xml'),
(u'Dębica', u'http://www.nowiny24.pl/debica.xml'),
(u'Jarosław', u'http://www.nowiny24.pl/jaroslaw.xml'),
(u'Krosno', u'http://www.nowiny24.pl/krosno.xml'),
(u'Mielec', u'http://www.nowiny24.pl/mielec.xml'),
(u'Nisko', u'http://www.nowiny24.pl/nisko.xml'),
(u'Sanok', u'http://www.nowiny24.pl/sanok.xml'),
(u'Stalowa Wola', u'http://www.nowiny24.pl/stalowawola.xml'),
(u'Tarnobrzeg', u'http://www.nowiny24.pl/tarnobrzeg.xml'),
(u'Sport', u'http://www.nowiny24.pl/sport.xml'),
(u'Dom', u'http://www.nowiny24.pl/dom.xml'),
(u'Auto', u'http://www.nowiny24.pl/auto.xml'),
(u'Praca', u'http://www.nowiny24.pl/praca.xml'),
(u'Zdrowie', u'http://www.nowiny24.pl/zdrowie.xml'),
feeds = [(u'Wszystkie', u'http://www.nowiny24.pl/rss.xml'),
(u'Podkarpacie', u'http://www.nowiny24.pl/podkarpacie.xml'),
(u'Bieszczady', u'http://www.nowiny24.pl/bieszczady.xml'),
(u'Rzeszów', u'http://www.nowiny24.pl/rzeszow.xml'),
(u'Przemyśl', u'http://www.nowiny24.pl/przemysl.xml'),
(u'Leżajsk', u'http://www.nowiny24.pl/lezajsk.xml'),
(u'Łańcut', u'http://www.nowiny24.pl/lancut.xml'),
(u'Dębica', u'http://www.nowiny24.pl/debica.xml'),
(u'Jarosław', u'http://www.nowiny24.pl/jaroslaw.xml'),
(u'Krosno', u'http://www.nowiny24.pl/krosno.xml'),
(u'Mielec', u'http://www.nowiny24.pl/mielec.xml'),
(u'Nisko', u'http://www.nowiny24.pl/nisko.xml'),
(u'Sanok', u'http://www.nowiny24.pl/sanok.xml'),
(u'Stalowa Wola', u'http://www.nowiny24.pl/stalowawola.xml'),
(u'Tarnobrzeg', u'http://www.nowiny24.pl/tarnobrzeg.xml'),
(u'Sport', u'http://www.nowiny24.pl/sport.xml'),
(u'Dom', u'http://www.nowiny24.pl/dom.xml'),
(u'Auto', u'http://www.nowiny24.pl/auto.xml'),
(u'Praca', u'http://www.nowiny24.pl/praca.xml'),
(u'Zdrowie', u'http://www.nowiny24.pl/zdrowie.xml'),
(u'Wywiady', u'http://www.nowiny24.pl/wywiady.xml')]
def get_cover_url(self):
@ -78,6 +79,10 @@ class GCN(BasicNewsRecipe):
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
return soup

11
recipes/gildia_pl.recipe
View File

@ -11,12 +11,13 @@ class Gildia(BasicNewsRecipe):
language = 'pl'
oldest_article = 8
max_articles_per_feed = 100
remove_empty_feeds=True
no_stylesheets=True
remove_empty_feeds = True
no_stylesheets = True
ignore_duplicate_articles = {'title', 'url'}
preprocess_regexps = [(re.compile(ur'</?sup>'), lambda match: '') ]
remove_tags=[dict(name='div', attrs={'class':'backlink'}), dict(name='div', attrs={'class':'im_img'}), dict(name='div', attrs={'class':'addthis_toolbox addthis_default_style'})]
keep_only_tags=dict(name='div', attrs={'class':'widetext'})
ignore_duplicate_articles = {'title', 'url'}
remove_tags = [dict(name='div', attrs={'class':'backlink'}), dict(name='div', attrs={'class':'im_img'}), dict(name='div', attrs={'class':'addthis_toolbox addthis_default_style'})]
keep_only_tags = dict(name='div', attrs={'class':'widetext'})
feeds = [(u'Gry', u'http://www.gry.gildia.pl/rss'), (u'Literatura', u'http://www.literatura.gildia.pl/rss'), (u'Film', u'http://www.film.gildia.pl/rss'), (u'Horror', u'http://www.horror.gildia.pl/rss'), (u'Konwenty', u'http://www.konwenty.gildia.pl/rss'), (u'Plansz\xf3wki', u'http://www.planszowki.gildia.pl/rss'), (u'Manga i anime', u'http://www.manga.gildia.pl/rss'), (u'Star Wars', u'http://www.starwars.gildia.pl/rss'), (u'Techno', u'http://www.techno.gildia.pl/rss'), (u'Historia', u'http://www.historia.gildia.pl/rss'), (u'Magia', u'http://www.magia.gildia.pl/rss'), (u'Bitewniaki', u'http://www.bitewniaki.gildia.pl/rss'), (u'RPG', u'http://www.rpg.gildia.pl/rss'), (u'LARP', u'http://www.larp.gildia.pl/rss'), (u'Muzyka', u'http://www.muzyka.gildia.pl/rss'), (u'Nauka', u'http://www.nauka.gildia.pl/rss')]
@ -34,7 +35,7 @@ class Gildia(BasicNewsRecipe):
def preprocess_html(self, soup):
for a in soup('a'):
if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']:
if a.has_key('href') and not a['href'].startswith('http'):
if '/gry/' in a['href']:
a['href']='http://www.gry.gildia.pl' + a['href']
elif u'książk' in soup.title.string.lower() or u'komiks' in soup.title.string.lower():

1
recipes/gram_pl.recipe
View File

@ -1,5 +1,6 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class Gram_pl(BasicNewsRecipe):
title = u'Gram.pl'
__author__ = 'fenuks'

13
recipes/gry_online_pl.recipe
View File

@ -1,5 +1,6 @@
import time
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class GryOnlinePl(BasicNewsRecipe):
title = u'Gry-Online.pl'
@ -40,10 +41,14 @@ class GryOnlinePl(BasicNewsRecipe):
r.extract()
for r in pagetext.findAll(attrs={'itemprop':'description'}):
r.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class':['n5p', 'add-info', 'twitter-share-button', 'lista lista3 lista-gry']}):
r.extract()
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
else:
tag = appendtag.find('div', attrs={'class':'S018stronyr'})
if tag:
@ -70,16 +75,22 @@ class GryOnlinePl(BasicNewsRecipe):
r.extract()
for r in pagetext.findAll(attrs={'itemprop':'description'}):
r.extract()
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
[comment.extract() for comment in comments]
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class':['n5p', 'add-info', 'twitter-share-button', 'lista lista3 lista-gry', 'S018strony']}):
r.extract()
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def image_url_processor(self, baseurl, url):
if url.startswith('..'):
return url[2:]
else:
return url
return url
def preprocess_html(self, soup):
self.append_page(soup, soup.body)

BIN
recipes/icons/bachormagazyn.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 898 B

BIN
recipes/icons/blog_biszopa.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 755 B

BIN
recipes/icons/esenja.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 329 B

BIN
recipes/icons/esensja_(rss).png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 329 B

BIN
recipes/icons/historia_pl.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 806 B

After

Width:  |  Height:  |  Size: 869 B

BIN
recipes/icons/ksiazka_pl.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.3 KiB

0
recipes/icons/nowy_obywatel.png Executable file → Normal file
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 480 B

After

Width:  |  Height:  |  Size: 480 B

BIN
recipes/icons/websecurity_pl.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 863 B

17
recipes/in4_pl.recipe
View File

@ -1,5 +1,7 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.ebooks.BeautifulSoup import Comment
class in4(BasicNewsRecipe):
title = u'IN4.pl'
oldest_article = 7
@ -8,14 +10,14 @@ class in4(BasicNewsRecipe):
description = u'Serwis Informacyjny - Aktualnosci, recenzje'
category = 'IT'
language = 'pl'
index='http://www.in4.pl/'
index = 'http://www.in4.pl/'
#cover_url= 'http://www.in4.pl/recenzje/337/in4pl.jpg'
no_stylesheets = True
remove_empty_feeds = True
preprocess_regexps = [(re.compile(ur'<a title="translate into.*?</a>', re.DOTALL), lambda match: '') ]
keep_only_tags=[dict(name='div', attrs={'class':'left_alone'})]
remove_tags_after=dict(name='img', attrs={'title':'komentarze'})
remove_tags=[dict(name='img', attrs={'title':'komentarze'})]
keep_only_tags = [dict(name='div', attrs={'class':'left_alone'})]
remove_tags_after = dict(name='img', attrs={'title':'komentarze'})
remove_tags = [dict(name='img', attrs={'title':'komentarze'})]
feeds = [(u'Wiadomo\u015bci', u'http://www.in4.pl/rss.php'), (u'Recenzje', u'http://www.in4.pl/rss_recenzje.php'), (u'Mini recenzje', u'http://www.in4.pl/rss_mini.php')]
def append_page(self, soup, appendtag):
@ -28,10 +30,13 @@ class in4(BasicNewsRecipe):
while nexturl:
soup2 = self.index_to_soup(nexturl)
pagetext = soup2.find(id='news')
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
nexturl=None
tag=soup2.findAll('a')
nexturl = None
tag = soup2.findAll('a')
for z in tag:
if z.string and u'następna str' in z.string:
nexturl='http://www.in4.pl/' + z['href']

4
recipes/infra_pl.recipe
View File

@ -15,7 +15,7 @@ class INFRA(BasicNewsRecipe):
remove_tags_before=dict(name='h2', attrs={'class':'contentheading'})
remove_tags_after=dict(attrs={'class':'pagenav'})
remove_tags=[dict(attrs={'class':'pagenav'})]
feeds = [(u'Najnowsze wiadomo\u015bci', u'http://www.infra.org.pl/index.php?option=com_rd_rss&id=1')]
feeds = [(u'Najnowsze wiadomo\u015bci', u'http://www.infra.org.pl/rss')]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
@ -23,4 +23,4 @@ class INFRA(BasicNewsRecipe):
for a in soup('a'):
if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']:
a['href']=self.index + a['href']
return soup
return soup

2
recipes/kosmonauta_pl.recipe
View File

@ -12,6 +12,8 @@ class Kosmonauta(BasicNewsRecipe):
INDEX = 'http://www.kosmonauta.net'
oldest_article = 7
no_stylesheets = True
remove_javascript = True
remove_attributes = ['style']
max_articles_per_feed = 100
keep_only_tags = [dict(name='div', attrs={'class':'item-page'})]
remove_tags = [dict(attrs={'class':['article-tools clearfix', 'cedtag', 'nav clearfix', 'jwDisqusForm']})]

6
recipes/kurier_galicyjski.recipe
View File

@ -1,5 +1,6 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup as bs
from calibre.ebooks.BeautifulSoup import BeautifulSoup as bs, Comment
class KurierGalicyjski(BasicNewsRecipe):
title = u'Kurier Galicyjski'
__author__ = 'fenuks'
@ -42,6 +43,9 @@ class KurierGalicyjski(BasicNewsRecipe):
r.extract()
for r in appendtag.findAll(attrs={'style':'border-top-width: thin; border-top-style: dashed; border-top-color: #CCC; border-bottom-width: thin; border-bottom-style: dashed; border-bottom-color: #CCC; padding-top:5px; padding-bottom:5px; text-align:right; margin-top:10px; height:20px;'}):
r.extract()
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)

6
recipes/kurier_poranny.recipe
View File

@ -1,5 +1,6 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class KurierPoranny(BasicNewsRecipe):
title = u'Kurier Poranny'
@ -72,6 +73,11 @@ class KurierPoranny(BasicNewsRecipe):
if pagetext:
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)

6
recipes/linux_journal.recipe
View File

@ -1,4 +1,5 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class LinuxJournal(BasicNewsRecipe):
title = u'Linux Journal'
@ -25,6 +26,9 @@ class LinuxJournal(BasicNewsRecipe):
soup2 = self.index_to_soup('http://www.linuxjournal.com'+ nexturl)
pagetext = soup2.find(attrs={'class':'node-inner'}).find(attrs={'class':'content'})
next = appendtag.find('li', attrs={'class':'pager-next'})
comments = pagetext.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
tag = appendtag.find('div', attrs={'class':'links'})
@ -33,4 +37,4 @@ class LinuxJournal(BasicNewsRecipe):
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
return soup
return soup

5
recipes/nto.recipe
View File

@ -1,5 +1,6 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class NTO(BasicNewsRecipe):
title = u'Nowa Trybuna Opolska'
@ -57,6 +58,10 @@ class NTO(BasicNewsRecipe):
if pagetext:
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)

6
recipes/oclab_pl.recipe
View File

@ -1,4 +1,6 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class OCLab(BasicNewsRecipe):
title = u'OCLab.pl'
oldest_article = 7
@ -26,6 +28,10 @@ class OCLab(BasicNewsRecipe):
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class':'post-nav-bottom-list'}):
r.extract()
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
return soup

3
recipes/overclock_pl.recipe
View File

@ -1,5 +1,6 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Overclock_pl(BasicNewsRecipe):
title = u'Overclock.pl'
oldest_article = 7
@ -21,4 +22,4 @@ class Overclock_pl(BasicNewsRecipe):
if 'articles/show' in url:
return url.replace('show', 'showall')
else:
return url
return url

7
recipes/pc_foster.recipe
View File

@ -1,4 +1,8 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
#currently recipe is not working
class PC_Foster(BasicNewsRecipe):
title = u'PC Foster'
oldest_article = 7
@ -29,6 +33,9 @@ class PC_Foster(BasicNewsRecipe):
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class':'review_content double'}):
r.extract()
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)

7
recipes/pure_pc.recipe
View File

@ -1,4 +1,6 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Comment
class PurePC(BasicNewsRecipe):
title = u'PurePC'
oldest_article = 7
@ -27,7 +29,10 @@ class PurePC(BasicNewsRecipe):
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class':['PageMenuList', 'pager', 'fivestar-widget']}):
r.extract()
comments = appendtag.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
comment.extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
return soup
return soup

9
recipes/ubuntu_pomoc_org.recipe
View File

@ -1,5 +1,6 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class UbuntuPomoc(BasicNewsRecipe):
title = u'Ubuntu-pomoc.org'
__author__ = 'fenuks'
@ -15,8 +16,8 @@ class UbuntuPomoc(BasicNewsRecipe):
remove_empty_feeds = True
use_embedded_content = False
remove_attrs = ['style']
keep_only_tags = [dict(attrs={'class':'post'})]
remove_tags_after = dict(attrs={'class':'underEntry'})
remove_tags = [dict(attrs={'class':['underPostTitle', 'yarpp-related', 'underEntry', 'social', 'tags', 'commentlist', 'youtube_sc']}), dict(id=['wp_rp_first', 'commentReply'])]
keep_only_tags = [dict(name='article')]
#remove_tags_after = dict(attrs={'class':'underEntry'})
remove_tags = [dict(attrs={'class':['yarpp-related', 'youtube_sc', 'share']}), dict(name='footer')]
feeds = [(u'Ca\u0142o\u015b\u0107', u'http://feeds.feedburner.com/Ubuntu-Pomoc'),
(u'Gry', u'http://feeds.feedburner.com/GryUbuntu-pomoc')]
]

28
recipes/websecurity_pl.recipe Normal file
View File

@ -0,0 +1,28 @@
__license__ = 'GPL v3'
from calibre.web.feeds.news import BasicNewsRecipe
class WebSecurity(BasicNewsRecipe):
title = u'WebSecurity'
__author__ = 'fenuks'
description = u'WebSecurity.pl to największy w Polsce portal o bezpieczeństwie sieciowym.'
category = ''
#publication_type = ''
language = 'pl'
#encoding = ''
#extra_css = ''
cover_url = 'http://websecurity.pl/images/websecurity-logo.png'
masthead_url = ''
use_embedded_content = False
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
remove_javascript = True
remove_attributes = ['style', 'font']
ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [dict(attrs={'class':'article single'}), dict(id='content')]
remove_tags = [dict(attrs={'class':['sociable', 'no-comments']})]
remove_tags_after = dict(attrs={'class':'sociable'})
feeds = [(u'Wszystkie', u'http://websecurity.pl/feed/'), (u'Aktualno\u015bci', u'http://websecurity.pl/aktualnosci/feed/'), (u'Artyku\u0142y', u'http://websecurity.pl/artykuly/feed/'), (u'Blogosfera', u'http://websecurity.pl/blogosfera/wpisy/feed/')]

1
src/calibre/utils/localization.py
View File

@ -159,6 +159,7 @@ _extra_lang_codes = {
'en_CZ' : _('English (Czech Republic)'),
'en_PH' : _('English (Philippines)'),
'en_PK' : _('English (Pakistan)'),
'en_PL' : _('English (Poland)'),
'en_HR' : _('English (Croatia)'),
'en_HK' : _('English (Hong Kong)'),
'en_HU' : _('English (Hungary)'),