Update Danas

Fixes #1742163 [Updated recipe for Danas](https://bugs.launchpad.net/calibre/+bug/1742163) [Updated recipe for Danas](https://bugs.launchpad.net/calibre/+bug/1742163)

recipes/danas.recipe

@@ -1,131 +1,102 @@
+# -*- mode: python -*-
+# -*- coding: utf-8 -*-
+
 __license__ = 'GPL v3'
-__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2018, Darko Miletic <darko.miletic at gmail.com>'
 '''
 danas.rs
 '''
 
-import re
 from calibre.web.feeds.news import BasicNewsRecipe
+from datetime import date, timedelta
 
 
 class Danas(BasicNewsRecipe):
     title = 'Danas'
     __author__ = 'Darko Miletic'
     description = 'Dnevne novine sa vestima iz sveta, politike, ekonomije, kulture, sporta, Beograda, Novog Sada i cele Srbije.'
-    publisher = 'Danas d.o.o.'
+    publisher = 'DAN GRAF d.o.o.'
-    category = 'news, politics, Serbia'
+    category = 'danas Dnevne novine politika drustvo ekonomija svet sport beograd vojvodina periskop terazije Beograd Srbija Novi Sad Nis Kragujevac Vojvodina politics Serbia'  # noqa
     oldest_article = 2
     max_articles_per_feed = 100
     no_stylesheets = False
     use_embedded_content = False
     encoding = 'utf-8'
-    masthead_url = 'http://www.danas.rs/images/basic/danas.gif'
+    masthead_url = 'http://www.danas.rs/images/basic/logo.png'
     language = 'sr'
     remove_javascript = True
     publication_type = 'newspaper'
     remove_empty_feeds = True
-    extra_css             = """ @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
+    auto_cleanup = True
-                                @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
+    auto_cleanup_keep = '//h1[@class="title"] | //div[@class="subTitle"] | //div[@class="author"] | //div[@class="published"]'
-                                .article,.articledescription,body,.lokacija,.feed{font-family: Tahoma,Arial,Helvetica,sans1,sans-serif}
+    resolve_internal_links = True
-                                .nadNaslov,h1,.preamble{font-family: Georgia,"Times New Roman",Times,serif1,serif}
+    INDEX = "http://www.danas.rs"
-                                .antrfileText{border-left: 2px solid #999999;
+    extra_css = """
-                                              margin-left: 0.8em;
+                                .author{font-size: small}
-                                              padding-left: 1.2em;
+                                .published {font-size: small}
-                                              margin-bottom: 0;
-                                              margin-top: 0}
-                                h2,.datum,.lokacija,.autor{font-size: small}
-                                .autor{text-transform: uppercase}
-                                .antrfileNaslov{border-left: 2px solid #999999;
-                                                margin-left: 0.8em;
-                                                padding-left: 1.2em;
-                                                font-weight:bold;
-                                                margin-bottom: 0;
-                                                margin-top: 0}
                                 img{margin-bottom: 0.8em}
-                                .naslovTemeDana{font-size: small}
                             """
 
     conversion_options = {
-        'comment': description, 'tags': category, 'publisher': publisher, 'language': language
+        'comment': description,
+        'tags': category,
+        'publisher': publisher,
+        'language': language
     }
 
-    preprocess_regexps = [
-        (re.compile(u'\u0110'), lambda match: u'\u00D0'), (re.compile(
-            u'\u2018'), lambda match: '&lsquo;')  # left single quotation mark
-        # right single quotation mark
-        # single low-9 quotation mark
-        # single high-reversed-9 quotation mark
-        # left double quotation mark
-        # right double quotation mark
-        # double low-9 quotation mark
-        # double high-reversed-9 quotation mark
-        # latin small letter o with circumflex
-        # latin small letter o with dieaeresis
-        # latin small letter a with acute
-        # latin small letter a with dieaeresis
-        , (re.compile(u'\u2019'), lambda match: '&rsquo;'), (re.compile(u'\u201a'), lambda match: '&lsquo;'), (re.compile(u'\u201b'), lambda match: '&rsquo;'), (re.compile(u'\u201c'), lambda match: '&ldquo;'), (re.compile(u'\u201d'), lambda match: '&rdquo;'), (re.compile(u'\u201e'), lambda match: '&ldquo;'), (re.compile(u'\u201f'), lambda match: '&rdquo;'), (re.compile(u'\u00f4'), lambda match: '&ldquo;'), (re.compile(u'\u00f6'), lambda match: '&rdquo;'), (re.compile(u'\u00e1'), lambda match: '&nbsp;'), (re.compile(u'\u00e4'), lambda match: '&nbsp;')  # noqa
-    ]
-
-    keep_only_tags = [dict(name='div', attrs={'id': 'left'})]
-    remove_tags = [
-        dict(name='div', attrs={'class': ['width_1_4', 'metaClanka', 'baner', 'listaVesti', 'article_nav']}), dict(
-            name='div', attrs={'id': 'comments'}), dict(name=['object', 'link', 'iframe', 'meta'])
-    ]
-    remove_attributes = ['w:st', 'st']
-
     feeds = [
-
+        (u'Politika', u'http://www.danas.rs/politika.56.html'),
-    (u'Politika', u'http://www.danas.rs/rss/rss.asp?column_id=27'),
+        (u'Drustvo', u'http://www.danas.rs/drustvo.55.html'),
-    (u'Hronika', u'http://www.danas.rs/rss/rss.asp?column_id=2'),
+        (u'Dijalog', u'http://www.danas.rs/dijalog.46.html'),
-    (u'Drustvo', u'http://www.danas.rs/rss/rss.asp?column_id=24'),
+        (u'Drustvo', u'http://www.danas.rs/drustvo.55.html'),
-    (u'Dijalog', u'http://www.danas.rs/rss/rss.asp?column_id=1'),
+        (u'Ekonomija', u'http://www.danas.rs/ekonomija.4.html'),
-    (u'Ekonomija', u'http://www.danas.rs/rss/rss.asp?column_id=6'),
+        (u'Svet', u'http://www.danas.rs/svet.1160.html'),
-    (u'Svet', u'http://www.danas.rs/rss/rss.asp?column_id=25'),
+        (u'Sport', u'http://www.danas.rs/sport.18.html'),
-    (u'Srbija', u'http://www.danas.rs/rss/rss.asp?column_id=28'),
+        (u'Kultura', u'http://www.danas.rs/kultura.11.html'),
-    (u'Kultura', u'http://www.danas.rs/rss/rss.asp?column_id=5'),
+        (u'Scena', u'http://www.danas.rs/scena.561.html'),
-    (u'Sport', u'http://www.danas.rs/rss/rss.asp?column_id=13'),
+        (u'Zivot', u'http://www.danas.rs/zivot.1140.html'),
-    (u'Scena', u'http://www.danas.rs/rss/rss.asp?column_id=42'),
+        (u'Auto', u'http://www.danas.rs/auto.1171.html'),
-    (u'Feljton', u'http://www.danas.rs/rss/rss.asp?column_id=19'),
+        (u'IT', u'http://www.danas.rs/it.29.html'),
-    (u'Periskop', u'http://www.danas.rs/rss/rss.asp?column_id=4'),
+        (u'Ljudi', u'http://www.danas.rs/ljudi.1141.html'),
-    (u'Famozno', u'http://www.danas.rs/rss/rss.asp?column_id=47'),
+        (u'Beograd', u'http://www.danas.rs/beograd.39.html'),
-    (u'Sluzbena beleska', u'http://www.danas.rs/rss/rss.asp?column_id=48'),
-    (u'Suocavanja', u'http://www.danas.rs/rss/rss.asp?column_id=49'),
-    (u'Moj Izbor', u'http://www.danas.rs/rss/rss.asp?column_id=50'),
-    (u'Direktno', u'http://www.danas.rs/rss/rss.asp?column_id=51'),
-    (u'I tome slicno', u'http://www.danas.rs/rss/rss.asp?column_id=52'),
-    (u'No longer and not yet', u'http://www.danas.rs/rss/rss.asp?column_id=53'),
-    (u'Resetovanje', u'http://www.danas.rs/rss/rss.asp?column_id=54'),
-    (u'Iza scene', u'http://www.danas.rs/rss/rss.asp?column_id=60'),
-    (u'Drustvoslovlje', u'http://www.danas.rs/rss/rss.asp?column_id=55'),
-    (u'Zvaka u pepeljari', u'http://www.danas.rs/rss/rss.asp?column_id=56'),
-    (u'Vostani Serbie', u'http://www.danas.rs/rss/rss.asp?column_id=57'),
-    (u'Med&Jad-a', u'http://www.danas.rs/rss/rss.asp?column_id=58'),
-    (u'Svetlosti pozornice', u'http://www.danas.rs/rss/rss.asp?column_id=59'),
-    (u'Dva cvancika', u'http://www.danas.rs/rss/rss.asp?column_id=65'),
-    (u'Iz kornera', u'http://www.danas.rs/rss/rss.asp?column_id=64')
     ]
 
-    def preprocess_html(self, soup):
-        for tagn in ['st1:place', 'st1:city', 'st1:country-region', 'st1:state']:
-            for item in soup.body.findAll(tagn):
-                item.name = 'span'
-        for item in soup.findAll(style=True):
-            del item['style']
-        for item in soup.findAll('a'):
-            if item.has_key('name'):  # noqa
-                item.extract()
-        for item in soup.findAll('img'):
-            if not item.has_key('alt'):  # noqa
-                item['alt'] = 'image'
-        return soup
-
-    def print_version(self, url):
-        return url + '&action=print'
-
     def get_cover_url(self):
-        cover_url = None
+        td = date.today() - timedelta(1)
-        soup = self.index_to_soup('http://www.danas.rs/')
+        cpart = str(td.year) + '/' + str(td.month) + '/' + str(td.day)
-        for citem in soup.findAll('img'):
+        return 'http://www.danas.rs/upload/images/' + cpart + '/Naslovna_velika.jpg'
-            if citem['src'].endswith('naslovna.jpg') or citem['src'].endswith('naslovna1.jpg'):
+
-                return 'http://www.danas.rs' + citem['src']
+    def parse_index(self):
-        return cover_url
+        totalfeeds = []
+        lfeeds = self.get_feeds()
+        for feedobj in lfeeds:
+            feedtitle, feedurl = feedobj
+            self.report_progress(
+                0,
+                _('Fetching feed') + ' %s...' %
+                (feedtitle if feedtitle else feedurl)
+            )
+            articles = []
+            soup = self.index_to_soup(feedurl)
+            for item in soup.findAll(
+                'div', attrs={
+                    'class': lambda x: x and 'newsBox' in x.split()
+                }
+            ):
+                atag = item.find('h2').a
+                ptag = item.find('p', attrs={'class': 'lead'})
+                artdate = item.find('div', attrs={'class': 'date'})
+                url = self.INDEX + atag['href']
+                title = self.tag_to_string(atag)
+                description = ''
+                if ptag:
+                    description = self.tag_to_string(ptag)
+                date = self.tag_to_string(artdate)
+                articles.append({
+                    'title': title,
+                    'date': date,
+                    'url': url,
+                    'description': description
+                })
+            totalfeeds.append((feedtitle, articles))
+        return totalfeeds