Quantcast
Channel: MobileRead Forums - Calibre
Viewing all articles
Browse latest Browse all 31494

Problem: Recipe for Foreign Affairs not fetching premium articles

$
0
0
Hi,

The built-in recipe for Foreign Affairs does not fetch premium articles. I have an online subscription with Foreign Affairs. I'm pasting the recipe code below so maybe you can help me tweak it so I can fetch premium articles:

Code:

from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.ptempfile import PersistentTemporaryFile

class ForeignAffairsRecipe(BasicNewsRecipe):
    ''' there are three modifications:
    1) fetch issue cover
    2) toggle ignore premium articles
    3) extract proper section names, ie. "Comments", "Essay"

    by Chen Wei weichen302@gmx.com, 2012-02-05'''

    __license__  = 'GPL v3'
    __author__ = 'kwetal'
    language = 'en'
    version = 1.01

    title = u'Foreign Affairs (Subcription or (free) Registration)'
    publisher = u'Council on Foreign Relations'
    category = u'USA, Foreign Affairs'
    description = u'The leading forum for serious discussion of American foreign policy and international affairs.'

    no_stylesheets = True
    remove_javascript = True

    INDEX = 'http://www.foreignaffairs.com'
    FRONTPAGE = 'http://www.foreignaffairs.com/magazine'
    INCLUDE_PREMIUM = False


    remove_tags = []
    remove_tags.append(dict(name = 'base'))
    #remove_tags.append(dict(name = '', attrs = {'': ''}))

    remove_tags_before = dict(name = 'h1', attrs = {'class': 'print-title'})

    remove_tags_after = dict(name = 'div', attrs = {'class': 'print-footer'})

    extra_css = '''
                body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
                div.print-footer {font-size: x-small; color: #696969;}
                '''

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

    temp_files = []
    articles_are_obfuscated = True

    def get_cover_url(self):
        soup = self.index_to_soup(self.FRONTPAGE)
        div = soup.find('div', attrs={'class':'inthemag-issuebuy-cover'})
        img_url =  div.find('img')['src']
        return self.INDEX + img_url

    def get_obfuscated_article(self, url):
        br = self.get_browser()
        br.open(url)

        response = br.follow_link(url_regex = r'/print/[0-9]+', nr = 0)
        html = response.read()

        self.temp_files.append(PersistentTemporaryFile('_fa.html'))
        self.temp_files[-1].write(html)
        self.temp_files[-1].close()

        return self.temp_files[-1].name


    def parse_index(self):
        answer = []
        soup = self.index_to_soup(self.FRONTPAGE)
        sec_start = soup.findAll('div', attrs={'class':'panel-separator'})
        for sec in sec_start:
            content = sec.nextSibling
            if content:
                section = self.tag_to_string(content.find('h2'))
                articles = []

                tags = []
                for div in content.findAll('div', attrs = {'class': re.compile(r'view-row\s+views-row-[0-9]+\s+views-row-[odd|even].*')}):
                    tags.append(div)
                for li in content.findAll('li'):
                    tags.append(li)

                for div in tags:
                    title = url = description = author = None

                    if self.INCLUDE_PREMIUM:
                        found_premium = False
                    else:
                        found_premium = div.findAll('span', attrs={'class':
                                                              'premium-icon'})
                    if not found_premium:
                        tag = div.find('div', attrs={'class': 'views-field-title'})

                        if tag:
                            a = tag.find('a')
                            if a:
                                title = self.tag_to_string(a)
                                url = self.INDEX + a['href']
                            author = self.tag_to_string(div.find('div', attrs = {'class': 'views-field-field-article-display-authors-value'}))
                            tag_summary = div.find('span', attrs = {'class': 'views-field-field-article-summary-value'})
                            description = self.tag_to_string(tag_summary)
                            articles.append({'title':title, 'date':None, 'url':url,
                                    'description':description, 'author':author})
                if articles:
                    answer.append((section, articles))
        return answer

    def preprocess_html(self, soup):
        for img in soup.findAll('img', attrs = {'src': True}):
            if not img['src'].startswith('http://'):
                img['src'] = self.INDEX + img['src']

        return soup

    needs_subscription = True

    def get_browser(self):
        br = BasicNewsRecipe.get_browser()
        if self.username is not None and self.password is not None:
            br.open('https://www.foreignaffairs.com/user?destination=home')
            br.select_form(nr = 1)
            br['name']  = self.username
            br['pass'] = self.password
            br.submit()
        return br


Viewing all articles
Browse latest Browse all 31494

Trending Articles