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

New recipes for Sports Illustrated and Sports Illustrated Columnists by kwetal

Browse Source
This commit is contained in:
Kovid Goyal 2009-11-26 12:58:59 -07:00
parent e72e3b5e73
commit 9729c55413
2 changed files with 159 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

99
resources/recipes/sportsillustrated.recipe Normal file
View File

@ -0,0 +1,99 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
#from random import randint
from urllib import quote
class SportsIllustratedRecipe(BasicNewsRecipe) :
__author__ = 'kwetal'
__copyright__ = 'kwetal'
__license__ = 'GPL v3'
language = 'en'
description = 'Sports Illustrated'
version = 1
title = u'Sports Illustrated'
no_stylesheets = True
remove_javascript = True
#template_css = ''
use_embedded_content = False
INDEX = 'http://sportsillustrated.cnn.com/'
def parse_index(self):
answer = []
soup = self.index_to_soup(self.INDEX)
# Find the link to the current issue on the front page.
cover = soup.find('img', attrs = {'alt' : 'Read All Articles', 'style' : 'vertical-align:bottom;'})
if cover:
currentIssue = cover.parent['href']
if currentIssue:
# Open the index of current issue
index = self.index_to_soup(currentIssue)
# Find all articles.
list = index.find('div', attrs = {'class' : 'siv_artList'})
if list:
articles = []
# Get all the artcles ready for calibre.
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'})
if header:
# It's an article, prepare a container for the content
homeMadeSoup = BeautifulSoup('<html><head></head><body></body></html>')
body = homeMadeSoup.find('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
else :
# It's a TOC, just return the whole lot
return soup

60
resources/recipes/sportsillustrated_columnists.recipe Normal file
View File

@ -0,0 +1,60 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
#from random import randint
from urllib import quote
class SportsIllustratedColumnistsRecipe(BasicNewsRecipe) :
title = u'Sports Illustrated Columnists'
__author__ = u'kwetal'
__license__ = u'GPL v3'
language = 'en'
version = 2
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
feeds = []
# RSS sources found at http://sportsillustrated.cnn.com/services/rss/
feeds.append((u'Jon Heyman', u'http://rss.cnn.com/rss/si_jon_heyman.rss'))
feeds.append((u'Austin Murphy', u'http://rss.cnn.com/rss/si_austin_murphy.rss'))
feeds.append((u'Lars Anderson', u'http://rss.cnn.com/rss/si_lars_anderson.rss'))
feeds.append((u'Melissa Segura', u'http://rss.cnn.com/rss/si_melissa_segura.rss'))
feeds.append((u'Peter King', u'http://rss.cnn.com/rss/si_peter_king.rss'))
feeds.append((u'Scott Wraight', u'http://rss.cnn.com/rss/si_scott_wraight.rss'))
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) :
temp = soup.find('div', attrs = {'class' : 'cnnstoryheadline'})
if temp :
# It's an article, make a valid content container
homeMadeSoup = BeautifulSoup('<html><head></head><body></body></html>')
body = homeMadeSoup.find('body')
headline = temp.find('h1')
if headline :
body.append(headline)
for td in soup.findAll('td', attrs = {'class' : 'cnnstorycontentarea'}) :
for p in td.findAll('p') :
body.append(p)
return homeMadeSoup
else :
# It's a TOC, just return the whole lot
return soup