Thanks Spedinfargo!
For some reason when I tried yours, the articles were blank.
I did my own, not-so-robust version that depends on the current issue being the 11th cover on the page. Not a great solution but works for now (and keep in mind I'm new at this)
Code:
from calibre.web.feeds.recipes import BasicNewsRecipe
#from calibre.ebooks.BeautifulSoup import BeautifulSoup
from urllib import quote
class SportsIllustratedRecipe(BasicNewsRecipe) :
__author__ = 'kwetal'
__copyright__ = 'kwetal'
__license__ = 'GPL v3'
language = 'en'
description = 'Sports Illustrated'
version = 3
title = u'Sports Illustrated v2'
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
INDEX = 'http://sportsillustrated.cnn.com/'
INDEX2 = 'http://sportsillustrated.cnn.com/vault/cover/home/index.htm'
def parse_index(self):
answer = []
soup = self.index_to_soup(self.INDEX2)
# print soup
# Find the link to the current issue on the front page. SI Cover
cover = soup.findAll('img', attrs = {'alt' : 'Read All Articles'})
currentIssue = 'http://sportsillustrated.cnn.com/' + cover[10].parent['href']
if currentIssue:
index = self.index_to_soup(currentIssue)
self.log('\tLooking for current issue in: ' + currentIssue)
nav = index.find('div', attrs = {'class': 'siv_trav_top'})
if nav:
img = nav.find('img', attrs = {'src': 'http://i.cdn.turner.com/sivault/.element/img/1.0/btn_next_v2.jpg'})
if img:
parent = img.parent
list = index.find('div', attrs = {'class' : 'siv_artList'})
if list:
articles = []
for headline in list.findAll('div', attrs = {'class' : 'headline'}):
title = self.tag_to_string(headline.a) + '\n' + self.tag_to_string(headline.findNextSibling('div', attrs = {'class' : 'info'}))
url = self.INDEX + headline.a['href']
description = self.tag_to_string(headline.findNextSibling('a').div)
article = {'title' : title, 'date' : u'', 'url' : url, 'description' : description}
articles.append(article)
# See if we can find a meaningfull title
feedTitle = 'Current Issue'
hasTitle = index.find('div', attrs = {'class' : 'siv_imageText_head'})
if hasTitle :
feedTitle = self.tag_to_string(hasTitle.h1)
answer.append([feedTitle, articles])
return answer
def print_version(self, url) :
# This is the url and the parameters that work to get the print version.
printUrl = 'http://si.printthis.clickability.com/pt/printThis?clickMap=printThis'
printUrl += '&fb=Y&partnerID=2356&url=' + quote(url)
return printUrl
# However the original javascript also uses the following parameters, but they can be left out:
# title : can be some random string
# random : some random number, but I think the number of digits is important
# expire : no idea what value to use
# All this comes from the Javascript function that redirects to the print version. It's called PT() and is defined in the file 48.js
'''def preprocess_html(self, soup):
header = soup.find('div', attrs = {'class' : 'siv_artheader'})
homeMadeSoup = BeautifulSoup('<html><head></head><body></body></html>')
body = homeMadeSoup.body
# Find the date, title and byline
temp = header.find('td', attrs = {'class' : 'title'})
if temp :
date = temp.find('div', attrs = {'class' : 'date'})
if date:
body.append(date)
if temp.h1:
body.append(temp.h1)
if temp.h2 :
body.append(temp.h2)
byline = temp.find('div', attrs = {'class' : 'byline'})
if byline:
body.append(byline)
# Find the content
for para in soup.findAll('div', attrs = {'class' : 'siv_artpara'}) :
body.append(para)
return homeMadeSoup
'''