Harvard Business Review Update

[rainrdx]

Fixed cover image and the missing last section.

from calibre.web.feeds.news import BasicNewsRecipe
import re
from datetime import date, timedelta

class HBR(BasicNewsRecipe):

    title = 'Harvard Business Review'
    description = 'To subscribe go to http://hbr.harvardbusiness.org'
    needs_subscription = True
    __author__ = 'Kovid Goyal and Sujata Raman'
    timefmt                = ' [%B %Y]'
    language = 'en'
    no_stylesheets = True
    # recipe_disabled = ('hbr.org has started requiring the use of javascript'
    #         ' to log into their website. This is unsupported in calibre, so'
    #         ' this recipe has been disabled. If you would like to see '
    #         ' HBR supported in calibre, contact hbr.org and ask them'
    #         ' to provide a javascript free login method.')

    LOGIN_URL = 'https://hbr.org/login?request_url=/'
    LOGOUT_URL = 'https://hbr.org/logout?request_url=/'

    INDEX = 'http://hbr.org'

    keep_only_tags = [dict(name='div', id='pageContainer')]
    remove_tags = [dict(id=['mastheadContainer', 'magazineHeadline',
        'articleToolbarTopRD', 'pageRightSubColumn', 'pageRightColumn',
        'todayOnHBRListWidget', 'mostWidget', 'keepUpWithHBR',
        'mailingListTout', 'partnerCenter', 'pageFooter',
        'superNavHeadContainer', 'hbrDisqus',
        'articleToolbarTop', 'articleToolbarBottom', 'articleToolbarRD']),
        dict(name='iframe')]
    extra_css = '''
                a {font-family:Georgia,"Times New Roman",Times,serif; font-style:italic; color:#000000; }
                .article{font-family:Georgia,"Times New Roman",Times,serif; font-size: xx-small;}
                h2{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:large; }
                h4{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:small;  }
                #articleAuthors{font-family:Georgia,"Times New Roman",Times,serif; font-style:italic; color:#000000;font-size:x-small;}
                #summaryText{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:x-small;}
                '''
    use_javascript_to_login = True

    def javascript_login(self, br, username, password):
        from calibre.web.jsbrowser.browser import Timeout
        try:
            br.visit('https://hbr.org/login?request_url=/', timeout=20)
        except Timeout:
            pass
        br.click('#accordion div[tabindex="0"]', wait_for_load=False)
        f = br.select_form('#signin-form')
        f['signin-form:username'] = username
        f['signin-form:password'] = password
        br.submit(wait_for_load=False)
        br.run_for_a_time(30)

    def map_url(self, url):
        if url.endswith('/ar/1'):
            return url[:-1]+'pr'


    def hbr_parse_toc(self, soup):
        feeds = []
        current_section = None
        articles = []
        for x in soup.find(id='issueFeaturesContent').findAll(['li', 'h4']):
            if x.name == 'h4':
                if x.get('class', None) == 'basic':continue
                if current_section is not None and articles:
                    feeds.append((current_section, articles))
                current_section = self.tag_to_string(x).capitalize()
                articles = []
                self.log('\tFound section:', current_section)
            else:
                a = x.find('a', href=True)
                if a is None: continue
                title = self.tag_to_string(a)
                url = a['href']
                if '/ar/' not in url:
                    continue
                if url.startswith('/'):
                    url = 'http://hbr.org' + url
                url = self.map_url(url)
                p = x.find('p', attrs={'class':'author'})
                desc = ''
                if p is not None:
                    desc = self.tag_to_string(p)
                self.log('\t\tFound article:', title)
                self.log('\t\t\t', url)
                self.log('\t\t\t', desc)

                articles.append({'title':title, 'url':url, 'description':desc,
                    'date':''})

        if current_section is not None and articles:
                    feeds.append((current_section, articles))
	return feeds

    def parse_index(self):
        soup0 = self.index_to_soup('http://hbr.org/magazine')

	datencover = soup0.find('ul', attrs={'id':'magazineArchiveCarousel'}).findAll('li')[-1]
	
	#find date & cover
	self.cover_url=datencover.img['src']
	dates=self.tag_to_string(datencover.img['alt'])
	self.timefmt = u' [%s]'%dates
	soup = self.index_to_soup(self.INDEX + soup0.find('div', attrs = {'class':'magazine_page'}).a['href'])


        feeds = self.hbr_parse_toc(soup)
        return feeds

[rainrdx]

Updated the remove_tags array to clean up the output

from calibre.web.feeds.news import BasicNewsRecipe
import re
from datetime import date, timedelta

class HBR(BasicNewsRecipe):

    title = 'Harvard Business Review'
    description = 'To subscribe go to http://hbr.harvardbusiness.org'
    needs_subscription = True
    __author__ = 'Kovid Goyal and Sujata Raman'
    timefmt                = ' [%B %Y]'
    language = 'en'
    no_stylesheets = True
    # recipe_disabled = ('hbr.org has started requiring the use of javascript'
    #         ' to log into their website. This is unsupported in calibre, so'
    #         ' this recipe has been disabled. If you would like to see '
    #         ' HBR supported in calibre, contact hbr.org and ask them'
    #         ' to provide a javascript free login method.')

    LOGIN_URL = 'https://hbr.org/login?request_url=/'
    LOGOUT_URL = 'https://hbr.org/logout?request_url=/'

    INDEX = 'http://hbr.org'

    keep_only_tags = [dict(name='div', id='pageContainer')]
    remove_tags = [dict(id=['mastheadContainer', 'magazineHeadline',
        'articleToolbarTopRD', 'pageRightSubColumn', 'pageRightColumn',
        'todayOnHBRListWidget', 'mostWidget', 'keepUpWithHBR',
        'mailingListTout', 'partnerCenter', 'pageFooter',
        'superNavHeadContainer', 'hbrDisqus', 'article-toolbox',
        'articleToolbarTop', 'articleToolbarBottom', 'articleToolbarRD']),
        dict(name='iframe')]
    extra_css = '''
                a {font-family:Georgia,"Times New Roman",Times,serif; font-style:italic; color:#000000; }
                .article{font-family:Georgia,"Times New Roman",Times,serif; font-size: xx-small;}
                h2{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:large; }
                h4{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:small;  }
                #articleAuthors{font-family:Georgia,"Times New Roman",Times,serif; font-style:italic; color:#000000;font-size:x-small;}
                #summaryText{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:x-small;}
                '''
    use_javascript_to_login = True

    def javascript_login(self, br, username, password):
        from calibre.web.jsbrowser.browser import Timeout
        try:
            br.visit('https://hbr.org/login?request_url=/', timeout=20)
        except Timeout:
            pass
        br.click('#accordion div[tabindex="0"]', wait_for_load=False)
        f = br.select_form('#signin-form')
        f['signin-form:username'] = username
        f['signin-form:password'] = password
        br.submit(wait_for_load=False)
        br.run_for_a_time(30)

    def map_url(self, url):
        if url.endswith('/ar/1'):
            return url[:-1]+'pr'


    def hbr_parse_toc(self, soup):
        feeds = []
        current_section = None
        articles = []
        for x in soup.find(id='issueFeaturesContent').findAll(['li', 'h4']):
            if x.name == 'h4':
                if x.get('class', None) == 'basic':continue
                if current_section is not None and articles:
                    feeds.append((current_section, articles))
                current_section = self.tag_to_string(x).capitalize()
                articles = []
                self.log('\tFound section:', current_section)
            else:
                a = x.find('a', href=True)
                if a is None: continue
                title = self.tag_to_string(a)
                url = a['href']
                if '/ar/' not in url:
                    continue
                if url.startswith('/'):
                    url = 'http://hbr.org' + url
                url = self.map_url(url)
                p = x.find('p', attrs={'class':'author'})
                desc = ''
                if p is not None:
                    desc = self.tag_to_string(p)
                self.log('\t\tFound article:', title)
                self.log('\t\t\t', url)
                self.log('\t\t\t', desc)

                articles.append({'title':title, 'url':url, 'description':desc,
                    'date':''})

        if current_section is not None and articles:
                    feeds.append((current_section, articles))
	return feeds

    def parse_index(self):
        soup0 = self.index_to_soup('http://hbr.org/magazine')

	datencover = soup0.find('ul', attrs={'id':'magazineArchiveCarousel'}).findAll('li')[-1]
	
	#find date & cover
	self.cover_url=datencover.img['src']
	dates=self.tag_to_string(datencover.img['alt'])
	self.timefmt = u' [%s]'%dates
	soup = self.index_to_soup(self.INDEX + soup0.find('div', attrs = {'class':'magazine_page'}).a['href'])


        feeds = self.hbr_parse_toc(soup)
        return feeds