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

Updated Sports Illustrated

Browse Source
This commit is contained in:
Kovid Goyal 2011-03-16 13:08:05 -06:00
parent be945ddda0
commit d05f8b79a7
1 changed files with 38 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

88
resources/recipes/sportsillustrated.recipe
View File

@ -1,6 +1,7 @@
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
#from calibre.ebooks.BeautifulSoup import BeautifulSoup #from calibre.ebooks.BeautifulSoup import BeautifulSoup
from urllib import quote from urllib import quote
import re
class SportsIllustratedRecipe(BasicNewsRecipe) : class SportsIllustratedRecipe(BasicNewsRecipe) :
__author__ = 'kwetal' __author__ = 'kwetal'
@ -15,65 +16,52 @@ class SportsIllustratedRecipe(BasicNewsRecipe) :
remove_javascript = True remove_javascript = True
use_embedded_content = False use_embedded_content = False
INDEX = 'http://sportsillustrated.cnn.com/' INDEX = 'http://sportsillustrated.cnn.com/vault/cover/home/index.htm'
def parse_index(self): def parse_index(self):
answer = [] answer = []
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
# Find the link to the current issue on the front page. SI Cover
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) #Loop through all of the "latest" covers until we find one that actually has articles
self.log('\tLooking for current issue in: ' + currentIssue) for item in soup.findAll('div', attrs={'id': re.compile("ecomthumb_latest_*")}):
# Now let us see if they updated their frontpage regex = re.compile('ecomthumb_latest_(\d*)')
nav = index.find('div', attrs = {'class': 'siv_trav_top'}) result = regex.search(str(item))
if nav: current_issue_number = str(result.group(1))
img = nav.find('img', attrs = {'src': 'http://i.cdn.turner.com/sivault/.element/img/1.0/btn_next_v2.jpg'}) current_issue_link = 'http://sportsillustrated.cnn.com/vault/cover/toc/' + current_issue_number + '/index.htm'
if img: self.log('Checking this link for a TOC: ', current_issue_link)
parent = img.parent
if parent.name == 'a':
# They didn't update their frontpage; Load the next issue from here
href = self.INDEX + parent['href']
index = self.index_to_soup(href)
self.log('\tLooking for current issue in: ' + href)
index = self.index_to_soup(current_issue_link)
if index:
if index.find('div', 'siv_noArticleMessage'): if index.find('div', 'siv_noArticleMessage'):
nav = index.find('div', attrs = {'class': 'siv_trav_top'}) self.log('No TOC for this one. Skipping...')
if nav: else:
# Their frontpage points to an issue without any articles; Use the previous issue self.log('Found a TOC... Using this link')
img = nav.find('img', attrs = {'src': 'http://i.cdn.turner.com/sivault/.element/img/1.0/btn_previous_v2.jpg'}) break
if img:
parent = img.parent
if parent.name == 'a':
href = self.INDEX + parent['href']
index = self.index_to_soup(href)
self.log('\tLooking for current issue in: ' + href)
# Find all articles.
list = index.find('div', attrs = {'class' : 'siv_artList'})
if list:
self.log ('found siv_artList')
articles = []
# Get all the artcles ready for calibre.
counter = 0
for headline in list.findAll('div', attrs = {'class' : 'headline'}):
counter = counter + 1
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)
if counter > 5:
break
# Find all articles. # See if we can find a meaningfull title
list = index.find('div', attrs = {'class' : 'siv_artList'}) feedTitle = 'Current Issue'
if list: hasTitle = index.find('div', attrs = {'class' : 'siv_imageText_head'})
articles = [] if hasTitle :
# Get all the artcles ready for calibre. feedTitle = self.tag_to_string(hasTitle.h1)
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) answer.append([feedTitle, articles])
# 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 return answer
@ -82,6 +70,7 @@ class SportsIllustratedRecipe(BasicNewsRecipe) :
# This is the url and the parameters that work to get the print version. # 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 = 'http://si.printthis.clickability.com/pt/printThis?clickMap=printThis'
printUrl += '&fb=Y&partnerID=2356&url=' + quote(url) printUrl += '&fb=Y&partnerID=2356&url=' + quote(url)
self.log('PrintURL: ' , printUrl)
return printUrl return printUrl
@ -116,4 +105,3 @@ class SportsIllustratedRecipe(BasicNewsRecipe) :
return homeMadeSoup return homeMadeSoup
''' '''