View Single Post
Old 02-11-2018, 04:03 PM   #9
Omniscient1
Member
Omniscient1 began at the beginning.
 
Posts: 12
Karma: 10
Join Date: Sep 2017
Device: Kindle Paper White
I haven't looked at the submitted recipe (I will do tomorrow) but here is mine.

It autoswitches for Sunday's edition (The Observer)
Code:
#!/usr/bin/env  python2
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'

'''
www.guardian.co.uk
'''
from calibre.web.feeds.news import BasicNewsRecipe
from datetime import date


class Guardian(BasicNewsRecipe):

    title = u'The Guardian'
    if date.today().weekday() == 6:
        title = u'The Observer'
        base_url = "http://www.guardian.co.uk/theobserver"
        cover_url = 'https://i.guim.co.uk/img/media/ec57a66a548b748cd586a8b63927aad0b167b80a/0_0_642_798/master/642.jpg?w=300&q=55&auto=format&usm=12&fit=max&'
        masthead_url = 'http://static.guim.co.uk/sys-images/Guardian/Pix/site_furniture/2010/10/19/1287478087992/The-Observer-001.gif'
    else:
        base_url = "http://www.guardian.co.uk/theguardian"
#        cover_pic = 'Guardian digital edition'
#        masthead_url = 'http://static.guim.co.uk/static/f76b43f9dcfd761f0ecf7099a127b603b2922118/common/images/logos/the-guardian/titlepiece.gif'
        cover_url = 'https://i.guim.co.uk/img/media/0dcdddf037927063ea4f420e8d5baecece39d5a4/0_0_1128_1403/master/1128.png?w=700&q=55&auto=format&usm=12&fit=max&'
 #       masthead_url = 'https://assets.guim.co.uk/images/eada8aa27c12fe2d5afa3a89d3fbae0d/fallback-logo.png'
        masthead_url = 'http://www.logo-designer.co/wp-content/uploads/2018/01/2018-The-Guardian-logo-design.png'
    __author__ = 'Kovid Goyal'
    language = 'en_GB'

    oldest_article = 1
    max_articles_per_feed = 300
    remove_javascript = True
    encoding = 'utf-8'
    remove_empty_feeds = True
    no_stylesheets = True
    remove_attributes = ['style']
    ignore_duplicate_articles = {'title', 'url'}

    timefmt = ' [%a, %d %b %Y]'

    keep_only_tags = [
        dict(attrs={'class': lambda x: x and 'content__main-column' in x.split()}),
    ]
    remove_tags = [
        dict(attrs={'class': lambda x: x and '--twitter' in x}),
        dict(attrs={'class': lambda x: x and 'submeta' in x.split()}),
        dict(attrs={'data-component': ['share', 'social']}),
        dict(attrs={'data-link-name': 'block share'}),
        dict(attrs={'class': lambda x: x and 'inline-expand-image' in x}),
        dict(attrs={'class': lambda x: x and 'modern-visible' in x.split()}),
        dict(name=['link', 'meta', 'style']),
    ]
    remove_tags_after = [
        dict(attrs={'class': lambda x: x and 'content__article-body' in x.split()}),
    ]

    def preprocess_raw_html(self, raw, url):
        import html5lib
        from lxml import html
        return html.tostring(html5lib.parse(raw, namespaceHTMLElements=False, treebuilder='lxml'), encoding=unicode)

    def preprocess_html(self, soup):
        for img in soup.findAll('img', srcset=True):
            img['src'] = img['srcset'].partition(' ')[0]
            img['srcset'] = ''
        return soup

    def parse_section(self, url, title_prefix=''):
        feeds = []
        soup = self.index_to_soup(url)
        for section in soup.findAll('section'):
            title = title_prefix + self.tag_to_string(section.find(
                attrs={'class': 'fc-container__header__title'})).strip().capitalize()
            self.log('\nFound section:', title)
            feeds.append((title, []))
            for li in section.findAll('li'):
                for a in li.findAll('a', attrs={'data-link-name': 'article'}, href=True):
                    title = self.tag_to_string(a).strip()
                    url = a['href']
                    self.log(' ', title, url)
                    feeds[-1][1].append({'title': title, 'url': url})
                    break
        return feeds

    def parse_index(self):
        feeds = self.parse_section(self.base_url)
        if date.today().weekday() == 5:
            feeds += self.parse_section (
            'https://www.theguardian.com/theguardian/family', 'Family - ')
            feeds += self.parse_section (
            'https://www.theguardian.com/theguardian/guardianreview', 'Guardian Review - ')
            feeds += self.parse_section (
            'https://www.theguardian.com/theguardian/weekend', 'Weekend Magazine - ')
            feeds += self.parse_section (
            'https://www.theguardian.com/theguardian/theguide', 'The Guide - ')
        else:
          if date.today().weekday() == 6:
              feeds += self.parse_section (
               'https://www.theguardian.com/theobserver/new-review', 'New Review ')
              feeds += self.parse_section (
               'https://www.theguardian.com/theobserver/news/comment', 'Comment ')
              feeds += self.parse_section (
               'https://www.theguardian.com/theobserver/magazine', 'Observer Magazine ')
          else:
              feeds += self.parse_section (
               'https://www.theguardian.com/tone/obituaries/all', 'Obituaries - ' )
              feeds += self.parse_section (
               'https://www.theguardian.com/uk/commentisfree', 'Editorial - ' )
              feeds += self.parse_section (
               'https://www.theguardian.com/theguardian/g2', 'G2 - ' ) 

        feeds += self.parse_section(
        'https://www.theguardian.com/uk/sport', 'Sport - ')
        return feeds

Last edited by PeterT; 02-11-2018 at 04:50 PM. Reason: added [code] / [/code] wrapper
Omniscient1 is offline   Reply With Quote