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 derStandard

Browse Source
This commit is contained in:
Kovid Goyal 2012-05-06 00:06:44 +05:30
parent 8a76489706
commit 2d80271416
1 changed files with 40 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
recipes/der_standard.recipe
View File

@ -7,10 +7,11 @@ __copyright__ = '2009, Gerhard Aigner <gerhard.aigner at gmail.com>'
''' http://www.derstandard.at - Austrian Newspaper ''' ''' http://www.derstandard.at - Austrian Newspaper '''
import re import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from time import strftime
class DerStandardRecipe(BasicNewsRecipe): class DerStandardRecipe(BasicNewsRecipe):
title = u'derStandard' title = u'derStandard'
__author__ = 'Gerhard Aigner and Sujata Raman and Marcel Jira' __author__ = 'Gerhard Aigner and Sujata Raman and Marcel Jira and Peter Reschenhofer'
description = u'Nachrichten aus Österreich' description = u'Nachrichten aus Österreich'
publisher ='derStandard.at' publisher ='derStandard.at'
category = 'news, politics, nachrichten, Austria' category = 'news, politics, nachrichten, Austria'
@ -88,3 +89,41 @@ class DerStandardRecipe(BasicNewsRecipe):
for t in soup.findAll(['ul', 'li']): for t in soup.findAll(['ul', 'li']):
t.name = 'div' t.name = 'div'
return soup return soup
def get_cover_url(self):
highResolution = True
date = strftime("%Y/%Y%m%d")
# it is also possible for the past
#date = '2012/20120503'
urlP1 = 'http://epaper.derstandarddigital.at/'
urlP2 = 'data_ep/STAN/' + date
urlP3 = '/V.B1/'
urlP4 = 'paper.htm'
urlHTML = urlP1 + urlP2 + urlP3 + urlP4
br = self.clone_browser(self.browser)
htmlF = br.open_novisit(urlHTML)
htmlC = htmlF.read()
# URL EXAMPLE: data_ep/STAN/2012/20120504/V.B1/pages/A3B6798F-2751-4D8D-A103-C5EF22F7ACBE.htm
# consists of part2 + part3 + 'pages/' + code
# 'pages/' has length 6, code has lenght 36
index = htmlC.find(urlP2) + len(urlP2 + urlP3) + 6
code = htmlC[index:index + 36]
# URL EXAMPLE HIGH RESOLUTION: http://epaper.derstandarddigital.at/data_ep/STAN/2012/20120504/pagejpg/A3B6798F-2751-4D8D-A103-C5EF22F7ACBE_b.png
# URL EXAMPLE LOW RESOLUTION: http://epaper.derstandarddigital.at/data_ep/STAN/2012/20120504/pagejpg/2AB52F71-11C1-4859-9114-CDCD79BEFDCB.png
urlPic = urlP1 + urlP2 + '/pagejpg/' + code
if highResolution:
urlPic = urlPic + '_b'
urlPic = urlPic + '.png'
return urlPic