Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

KG updates

Browse Source
This commit is contained in:
GRiker 2010-02-11 16:31:46 -07:00
commit a53b71a02c
4 changed files with 203 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
resources/images/news/sueddeutschezeitung.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 492 B

107
resources/recipes/sueddeutschezeitung.recipe Normal file
View File

@ -0,0 +1,107 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.sueddeutsche.de/sz/
'''
import urllib
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class SueddeutcheZeitung(BasicNewsRecipe):
title = 'Sueddeutche Zeitung'
__author__ = 'Darko Miletic'
description = 'News from Germany. Access to paid content.'
publisher = 'Sueddeutche Zeitung'
category = 'news, politics, Germany'
no_stylesheets = True
oldest_article = 2
encoding = 'cp1252'
needs_subscription = True
remove_empty_feeds = True
PREFIX = 'http://www.sueddeutsche.de'
INDEX = PREFIX + strftime('/sz/%Y-%m-%d/')
LOGIN = PREFIX + '/app/lbox/index.html'
use_embedded_content = False
masthead_url = 'http://pix.sueddeutsche.de/img/g_.gif'
language = 'de_DE'
extra_css = ' body{font-family: Arial,Helvetica,sans-serif} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
, 'linearize_tables' : True
}
remove_attributes = ['height','width']
def get_browser(self):
br = BasicNewsRecipe.get_browser()
br.open(self.INDEX)
if self.username is not None and self.password is not None:
data = urllib.urlencode({ 'login_name':self.username
,'login_passwort':self.password
,'lboxaction':'doLogin'
,'passtxt':'Passwort'
,'referer':self.INDEX
,'x':'22'
,'y':'7'
})
br.open(self.LOGIN,data)
return br
remove_tags =[
dict(attrs={'class':'hidePrint'})
,dict(name=['link','object','embed','base','iframe'])
]
remove_tags_before = dict(name='h2')
remove_tags_after = dict(attrs={'class':'author'})
feeds = [
(u'Politik' , INDEX + 'politik/' )
,(u'Seite drei' , INDEX + 'seitedrei/' )
,(u'Meinungsseite', INDEX + 'meinungsseite/')
,(u'Wissen' , INDEX + 'wissen/' )
,(u'Panorama' , INDEX + 'panorama/' )
,(u'Feuilleton' , INDEX + 'feuilleton/' )
,(u'Medien' , INDEX + 'medien/' )
,(u'Wirtschaft' , INDEX + 'wirtschaft/' )
,(u'Sport' , INDEX + 'sport/' )
,(u'Bayern' , INDEX + 'bayern/' )
,(u'Muenchen' , INDEX + 'muenchen/' )
,(u'jetzt.de' , INDEX + 'jetzt.de/' )
]
def parse_index(self):
totalfeeds = []
lfeeds = self.get_feeds()
for feedobj in lfeeds:
feedtitle, feedurl = feedobj
self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
articles = []
soup = self.index_to_soup(feedurl)
tbl = soup.find(attrs={'class':'szprintd'})
for item in tbl.findAll(name='td',attrs={'class':'topthema'}):
atag = item.find(attrs={'class':'Titel'}).a
ptag = item.find('p')
stag = ptag.find('script')
if stag:
stag.extract()
url = self.PREFIX + atag['href']
title = self.tag_to_string(atag)
description = self.tag_to_string(ptag)
articles.append({
'title' :title
,'date' :strftime(self.timefmt)
,'url' :url
,'description':description
})
totalfeeds.append((feedtitle, articles))
return totalfeeds
def print_version(self, url):
return url + 'print.html'

59
resources/recipes/telegraph_uk.recipe
View File

@ -9,8 +9,8 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TelegraphUK(BasicNewsRecipe):
title = u'Telegraph.co.uk'
__author__ = 'Darko Miletic'
description = 'News from United Kingdom'
__author__ = 'Darko Miletic and Sujata Raman'
description = 'News from United Kingdom'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
@ -18,23 +18,26 @@ class TelegraphUK(BasicNewsRecipe):
use_embedded_content = False
extra_css = '''
h1{font-family :Arial,Helvetica,sans-serif; font-size:large; }
h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#444444}
.story{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
.byline{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
a{color:#234B7B; }
.imageExtras{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
'''
keep_only_tags = [
extra_css = '''
h1{font-family :Arial,Helvetica,sans-serif; font-size:large; }
h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#444444;}
.story{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
.byline{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
a{color:#234B7B; }
.imageExtras{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
'''
keep_only_tags = [
dict(name='div', attrs={'class':'storyHead'})
,dict(name='div', attrs={'class':'story' })
#,dict(name='div', attrs={'class':['slideshowHD gutterUnder',"twoThirds gutter","caption" ] })
]
remove_tags = [dict(name='div', attrs={'class':['related_links_inline',"imgindex","next","prev","gutterUnder"]})]
feeds = [
#,dict(name='div', attrs={'class':['slideshowHD gutterUnder',"twoThirds gutter","caption" ] })
]
remove_tags = [dict(name='div', attrs={'class':['related_links_inline',"imgindex","next","prev","gutterUnder",'ssImgHide','imageExtras','ssImg hide']})
#,dict(name='div', attrs={'class':['toolshideoneQuarter']})
,dict(name='span', attrs={'class':['num','placeComment']})
]
feeds = [
(u'UK News' , u'http://www.telegraph.co.uk/news/uknews/rss' )
,(u'World News' , u'http://www.telegraph.co.uk/news/worldnews/rss' )
,(u'Politics' , u'http://www.telegraph.co.uk/news/newstopics/politics/rss' )
@ -45,15 +48,27 @@ class TelegraphUK(BasicNewsRecipe):
,(u'Earth News' , u'http://www.telegraph.co.uk/earth/earthnews/rss' )
,(u'Comment' , u'http://www.telegraph.co.uk/comment/rss' )
,(u'How about that?', u'http://www.telegraph.co.uk/news/newstopics/howaboutthat/rss' )
]
]
def get_article_url(self, article):
url = article.get('guid', None)
if 'picture-galleries' in url or 'pictures' in url or 'picturegalleries' in url :
url = None
return url
def postprocess_html(self,soup,first):
for bylineTag in soup.findAll(name='div', attrs={'class':'byline'}):
for pTag in bylineTag.findAll(name='p'):
if getattr(pTag.contents[0],"Comments",True):
pTag.extract()
return soup

77
resources/recipes/toronto_sun.recipe
View File

@ -10,7 +10,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TorontoSun(BasicNewsRecipe):
title = 'Toronto SUN'
__author__ = 'Darko Miletic'
__author__ = 'Darko Miletic and Sujata Raman'
description = 'News from Canada'
publisher = 'Toronto Sun'
category = 'news, politics, Canada'
@ -21,25 +21,50 @@ class TorontoSun(BasicNewsRecipe):
encoding = 'cp1252'
language = 'en_CA'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags =[
dict(name='div', attrs={'class':'articleHead'})
,dict(name='div', attrs={'id':'channelContent'})
]
remove_tags = [
dict(name='div',attrs={'class':['leftBox','bottomBox clear','bottomBox','breadCrumb']})
,dict(name=['link','iframe','object'])
,dict(name='a',attrs={'rel':'swap'})
,dict(name='ul',attrs={'class':'tabs dl contentSwap'})
]
keep_only_tags = [
dict(name='div', attrs={'class':['articleHead','leftBox']})
,dict(name='div', attrs={'id':'channelContent'})
,dict(name='div', attrs={'id':'rotateBox'})
,dict(name='img')
]
remove_tags = [
dict(name='div',attrs={'class':['bottomBox clear','bottomBox','breadCrumb','articleControls thin','articleControls thin short','extraVideoList']})
,dict(name='h2',attrs={'class':'microhead'})
,dict(name='div',attrs={'id':'commentsBottom'})
,dict(name=['link','iframe','object'])
,dict(name='a',attrs={'rel':'swap'})
,dict(name='a',attrs={'href':'/news/haiti/'})
,dict(name='ul',attrs={'class':['tabs dl contentSwap','micrositeNav clearIt hList','galleryNav rotateNav']})
]
remove_tags_after = [
dict(name='div',attrs={'class':'bottomBox clear'})
,dict(name='div',attrs={'class':'rotateBox'})
,dict(name='div',attrs={'id':'contentSwap'})
]
extra_css = '''
h1{font-family :Arial,Helvetica,sans-serif; font-size:large;}
h2{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#666666;}
h3{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#000000;}
p{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
.bold{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;color:#444444;margin-left: 0px;}
.subheading{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#000000; font-weight: bold;}
.byline{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
.byline span{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small; text-transform: uppercase;}
.updated{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
.galleryCaption{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
.galleryUpdated{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
'''
remove_tags_after = dict(name='div',attrs={'class':'bottomBox clear'})
feeds = [
(u'News' , u'http://www.torontosun.com/news/rss.xml' )
@ -48,3 +73,19 @@ class TorontoSun(BasicNewsRecipe):
,(u'World' , u'http://www.torontosun.com/news/world/rss.xml' )
,(u'Money' , u'http://www.torontosun.com/money/rss.xml' )
]
def preprocess_html(self, soup):
##To fetch images from the specified source
for img in soup.findAll('img', src=True):
url= img.get('src').split('?')[-1].partition('=')[-1]
if url:
img['src'] = url.split('&')[0].partition('=')[0]
img['width'] = url.split('&')[-1].partition('=')[-1].split('x')[0]
img['height'] =url.split('&')[-1].partition('=')[-1].split('x')[1]
return soup