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

Improve The Marker

Browse Source
This commit is contained in:
Kovid Goyal 2011-04-27 13:00:49 -06:00
parent 92de7e1807
commit 631afb7eac
1 changed files with 31 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
recipes/the_marker.recipe
View File

@ -3,7 +3,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1283848012(BasicNewsRecipe): class AdvancedUserRecipe1283848012(BasicNewsRecipe):
description = 'TheMarker Financial News in Hebrew' description = 'TheMarker Financial News in Hebrew'
__author__ = 'TonyTheBookworm, Marbs' __author__ = 'Marbs'
cover_url = 'http://static.ispot.co.il/wp-content/upload/2009/09/themarker.jpg' cover_url = 'http://static.ispot.co.il/wp-content/upload/2009/09/themarker.jpg'
title = u'TheMarker' title = u'TheMarker'
language = 'he' language = 'he'
@ -11,42 +11,38 @@ class AdvancedUserRecipe1283848012(BasicNewsRecipe):
remove_javascript = True remove_javascript = True
timefmt = '[%a, %d %b, %Y]' timefmt = '[%a, %d %b, %Y]'
oldest_article = 1 oldest_article = 1
remove_tags = [dict(name='tr', attrs={'bgcolor':['#738A94']}) ] keep_only_tags =dict(name='div', attrs={'id':'content'})
max_articles_per_feed = 10 remove_attributes = ['width','float','margin-left']
no_stylesheets = True
remove_tags = [dict(name='div', attrs={'class':['social-nav article-social-nav','prsnlArticleEnvelope','cb']}) ,
dict(name='a', attrs={'href':['/misc/mobile']}) ,
dict(name='span', attrs={'class':['post-summ']}) ]
max_articles_per_feed = 100
extra_css='body{direction: rtl;} .article_description{direction: rtl; } a.article{direction: rtl; } .calibre_feed_description{direction: rtl; }' extra_css='body{direction: rtl;} .article_description{direction: rtl; } a.article{direction: rtl; } .calibre_feed_description{direction: rtl; }'
feeds = [(u'Head Lines', u'http://www.themarker.com/tmc/content/xml/rss/hpfeed.xml'), feeds = [(u'Head Lines', u'http://www.themarker.com/cmlink/1.144'),
(u'TA Market', u'http://www.themarker.com/tmc/content/xml/rss/sections/marketfeed.xml'), (u'TA Market', u'http://www.themarker.com/cmlink/1.243'),
(u'Real Estate', u'http://www.themarker.com/tmc/content/xml/rss/sections/realEstaterfeed.xml'), (u'Real Estate', u'http://www.themarker.com/cmlink/1.605656'),
(u'Wall Street & Global', u'http://www.themarker.com/tmc/content/xml/rss/sections/wallsfeed.xml'), (u'Global', u'http://www.themarker.com/cmlink/1.605658'),
(u'Law', u'http://www.themarker.com/tmc/content/xml/rss/sections/lawfeed.xml'), (u'Wall Street', u'http://www.themarker.com/cmlink/1.613713'),
(u'Media', u'http://www.themarker.com/tmc/content/xml/rss/sections/mediafeed.xml'), (u'SmartPhone', u'http://www.themarker.com/cmlink/1.605661'),
(u'Consumer', u'http://www.themarker.com/tmc/content/xml/rss/sections/consumerfeed.xml'), (u'Law', u'http://www.themarker.com/cmlink/1.605664'),
(u'Career', u'http://www.themarker.com/tmc/content/xml/rss/sections/careerfeed.xml'), (u'Media', u'http://www.themarker.com/cmlink/1.605660'),
(u'Car', u'http://www.themarker.com/tmc/content/xml/rss/sections/carfeed.xml'), (u'Consumer', u'http://www.themarker.com/cmlink/1.605662'),
(u'High Tech', u'http://www.themarker.com/tmc/content/xml/rss/sections/hightechfeed.xml'), (u'Career', u'http://www.themarker.com/cmlink/1.605665'),
(u'Investor Guide', u'http://www.themarker.com/tmc/content/xml/rss/sections/investorGuidefeed.xml')] (u'Car', u'http://www.themarker.com/cmlink/1.605663'),
(u'High Tech', u'http://www.themarker.com/cmlink/1.605659'),
(u'Small Business', u'http://www.themarker.com/cmlink/1.605666')]
def print_version(self, url): def print_version(self, url):
split1 = url.split("=") #split1 = url.split("/")
weblinks = url #print_url='http://www.themarker.com/misc/article-print-page/'+split1[-1]
txt=url
if weblinks is not None: re1='.*?' # Non-greedy match on filler
for link in weblinks: re2='(tv)' # Word 1
#---------------------------------------------------------
#here we need some help with some regexpressions
#we are trying to find it.themarker.com in a url
#-----------------------------------------------------------
re1='.*?' # Non-greedy match on filler
re2='(it\\.themarker\\.com)' # Fully Qualified Domain Name 1
rg = re.compile(re1+re2,re.IGNORECASE|re.DOTALL)
m = rg.search(url)
rg = re.compile(re1+re2,re.IGNORECASE|re.DOTALL)
if m: m = rg.search(txt)
split2 = url.split("article/") if m:
print_url = 'http://it.themarker.com/tmit/PrintArticle/' + split2[1] #print 'bad link'
return 1
else:
print_url = 'http://www.themarker.com/ibo/misc/printFriendly.jhtml?ElementId=%2Fibo%2Frepositories%2Fstories%2Fm1_2000%2F' + split1[1]+'.xml'
return print_url