View Single Post
Old 12-28-2012, 11:20 PM   #1
rainrdx
Enthusiast
rainrdx can differentiate black from dark navy bluerainrdx can differentiate black from dark navy bluerainrdx can differentiate black from dark navy bluerainrdx can differentiate black from dark navy bluerainrdx can differentiate black from dark navy bluerainrdx can differentiate black from dark navy bluerainrdx can differentiate black from dark navy bluerainrdx can differentiate black from dark navy bluerainrdx can differentiate black from dark navy bluerainrdx can differentiate black from dark navy bluerainrdx can differentiate black from dark navy blue
 
Posts: 49
Karma: 13316
Join Date: Jul 2012
Device: iPad
Harper's Print Edition recipe update

This is an update on Darko Miletic's great work. What I worked on include updates on cover image processing, getting the current issue and some misc/minor things.

I changed the title to Harper's Magazine - Print Edition to fork mostly as I didn't get a chance to communicate with the original author.

R


Code:
__license__   = 'GPL v3'
__copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>'
'''
harpers.org - paid subscription/ printed issue articles
This recipe only get's article's published in text format
images and pdf's are ignored
If you have institutional subscription based on access IP you do not need to enter
anything in username/password fields
'''

import time
import urllib
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe

class Harpers_full(BasicNewsRecipe):
    title                 = "Harper's Magazine - Printed Edition"
    __author__            = 'Darko Miletic'
    description           = "Harper's Magazine, the oldest general-interest monthly in America, explores the issues that drive our national conversation, through long-form narrative journalism and essays, and such celebrated features as the iconic Harper's Index."
    publisher             = "Harpers's"
    category              = 'news, politics, USA'
    oldest_article        = 30
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
    delay                 = 1
    language              = 'en'
    encoding              = 'utf8'
    needs_subscription    = 'optional'
    masthead_url          = 'http://harpers.org/wp-content/themes/harpers/images/pheader.gif'
    publication_type      = 'magazine'
    INDEX                 = ''
    LOGIN                 = 'http://harpers.org/wp-content/themes/harpers/ajax_login.php'
    extra_css             = """
                                body{font-family: adobe-caslon-pro,serif}
                                .category{font-size: small}
                                .articlePost p:first-letter{display: inline; font-size: xx-large; font-weight: bold}
                            """

    conversion_options = {
                          'comment'   : description
                        , 'tags'      : category
                        , 'publisher' : publisher
                        , 'language'  : language
                        }

    keep_only_tags = [ dict(name='div', attrs={'class':['postdetailFull','articlePost']}) ]
    remove_tags = [
                     dict(name='div', attrs={'class':'fRight rightDivPad'})
                    ,dict(name=['link','meta','object','embed','iframe'])
                  ]
    remove_attributes=['xmlns']

    def get_browser(self):
        br = BasicNewsRecipe.get_browser()
        br.open('http://harpers.org/')
        if self.username is not None and self.password is not None:
            tt = time.localtime()*1000
            data = urllib.urlencode({ 'm':self.username
                                     ,'p':self.password
                                     ,'rt':'http://harpers.org/'
                                     ,'tt':tt
                                   })
            br.open(self.LOGIN, data)
        return br

    def parse_index(self):
	#find current issue

	soup = self.index_to_soup('http://harpers.org/')
	currentIssue=soup.find('div',attrs={'class':'mainNavi'}).find('li',attrs={'class':'curentIssue'})
	currentIssue_url=self.tag_to_string(currentIssue.a['href'])
	self.log(currentIssue_url)

	#go to the current issue
	soup1 = self.index_to_soup(currentIssue_url)
	date = re.split('\s\|\s',self.tag_to_string(soup1.head.title.string))[0]
	self.timefmt =  u' [%s]'%date

	#get cover
	coverurl='http://harpers.org/wp-content/themes/harpers/ajax_microfiche.php?img=harpers-'+re.split('harpers.org/',currentIssue_url)[1]+'gif/0001.gif'
	soup2 = self.index_to_soup(coverurl)
	self.cover_url = self.tag_to_string(soup2.find('img')['src'])
	self.log(self.cover_url)
        articles = []
        count = 0
        for item in soup1.findAll('div', attrs={'class':'articleData'}):
            text_links = item.findAll('h2')
            for text_link in text_links:
                if count == 0:
                   count = 1
                else:
                   url   = text_link.a['href']
                   title = text_link.a.contents[0]
                   date  = strftime(' %B %Y')
                   articles.append({
                                      'title'      :title
                                     ,'date'       :date
                                     ,'url'        :url
                                     ,'description':''
                                    })
        return [(soup1.head.title.string, articles)]

    def print_version(self, url):
        return url + '?single=1'

    def cleanup(self):
	soup = self.index_to_soup('http://harpers.org/')
	signouturl=self.tag_to_string(soup.find('li', attrs={'class':'subLogOut'}).findNext('li').a['href'])
	self.log(signouturl)
        self.browser.open(signouturl)
rainrdx is offline   Reply With Quote