Update WirtschaftsWoche Online

recipes/wirtscafts_woche.recipe

@@ -1,93 +1,91 @@
 __license__ = 'GPL v3'
 __copyright__ = '2013, Armin Geller'
 
+##
+# Written:      May 2013 (new coding)
+# Version:      4.2
+# Last update:  2018-03-01
+##
 '''
 Fetch WirtschaftsWoche Online
 '''
-import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 
 class WirtschaftsWocheOnline(BasicNewsRecipe):
     title = u'WirtschaftsWoche Online'
-    __author__ = 'Armin Geller'  # Update AGE 2013-01-05; Modified by Hegi 2013-04-28
+    __author__ = 'Armin Geller'  # Update AGE 2013-01-05; 2018-03-01
-    description = u'Wirtschaftswoche Online - basierend auf den RRS-Feeds von Wiwo.de'
+    description = u'German Online Portal of WirtschaftsWoche'
-    tags = 'Nachrichten, Blog, Wirtschaft'
+    publisher = 'Verlagsgruppe Handelsblatt GmbH Redaktion WirtschaftsWoche Online'
-    publisher = 'Verlagsgruppe Handelsblatt GmbH / Redaktion WirtschaftsWoche Online'
     category = 'business, economy, news, Germany'
     publication_type = 'weekly magazine'
     oldest_article = 7
     max_articles_per_feed = 100
-    simultaneous_downloads = 20
 
     auto_cleanup = False
     no_stylesheets = True
     remove_javascript = True
     remove_empty_feeds = True
-
-    # don't duplicate articles from "Schlagzeilen" / "Exklusiv" to other
-    # rubrics
-    ignore_duplicate_articles = {'title', 'url'}
-
-    # if you want to reduce size for an b/w or E-ink device, uncomment this:
-    compress_news_images = True
-    # compress_news_images_auto_size = 16
-    scale_news_images = (400, 300)
-    compress_news_images_max_size = 35
-
     timefmt = ' [%a, %d %b %Y]'
-
+    language = 'de_DE'
-    conversion_options = {'smarten_punctuation': True,
-                          'authors': publisher,
-                          'publisher': publisher}
-    language = 'de'
     encoding = 'UTF-8'
-    cover_source = 'https://kaufhaus.handelsblatt.com/downloads/wirtschaftswoche-emagazin-p1952.html'
+    cover_source = 'https://www.ikiosk.de/shop/epaper/wirtschaftswoche.html'
     masthead_url = 'http://www.wiwo.de/images/wiwo_logo/5748610/1-formatOriginal.png'
 
     def get_cover_url(self):
-        soup = self.index_to_soup(self.cover_source)
+        cover_source_soup = self.index_to_soup(self.cover_source)
-        style = soup.find('img', alt='WirtschaftsWoche eMagazin', style=True)[
+        preview_image_div = cover_source_soup.find(attrs={'class': 'gallery'})
-            'style']
+        return preview_image_div.a.img['src']
-        self.cover_url = style.partition('(')[-1].rpartition(')')[0]
-        return self.cover_url
 
-    # Insert ". " after "Place" in <span class="hcf-location-mark">Place</span>
+    extra_css = '''
-    # If you use .epub format you could also do this as extra_css
+        h1, h2 {font-size: 1.6em; text-align: left}
-    # '.hcf-location-mark:after {content: ". "}'
+        .c-leadtext {font-size: 1em; font-style: italic; font-weight: normal}
-    preprocess_regexps = [
+        h4 {font-size: 1.3em;text-align: left}
-        (re.compile(r'(<span class="hcf-location-mark">[^<]*)(</span>)', re.DOTALL | re.IGNORECASE), lambda match: match.group(1) + '. ' + match.group(2))]
+        h5, h6, a {font-size: 1em;text-align: left}
-
+        .c-metadata {font-size: .75em;text-align: left; font-style: italic}
-    extra_css      =  'h1 {font-size: 1.6em; text-align: left} \
+    '''
-                       h2 {font-size: 1em; font-style: italic; font-weight: normal} \
-                       h3 {font-size: 1.3em;text-align: left} \
-                       h4, h5, h6, a {font-size: 1em;text-align: left} \
-                       .hcf-caption {font-size: 1em;text-align: left; font-style: italic} \
-                       .hcf-location-mark {font-style: italic}'
 
     keep_only_tags = [
-        dict(name='div', attrs={
+        dict(
-             'class': ['hcf-column hcf-column1 hcf-teasercontainer hcf-maincol']}),
+            name='div',
-        dict(name='div', attrs={'id': ['contentMain']})
+            attrs={
+                'class': [
+                    'o-article__element', 'o-article__content c-richText',
+                    'o-article__content-element o-article__content-element--richtext'
+                ]
+            }
+        )
     ]
 
     remove_tags = [
-        dict(name='div', attrs={
+        dict(
-             'class': ['hcf-link-block hcf-faq-open', 'hcf-article-related']})
+            name='div',
+            attrs={
+                'class': [
+                    'c-pagination u-flex',
+                    'c-standard-article-teaser',
+                    'c-pagination u-flex ajaxify',
+                    'c-socialshare u-margin-xxl ',
+                ]
+            }
+        )
     ]
 
     feeds = [
         (u'Schlagzeilen', u'http://www.wiwo.de/contentexport/feed/rss/schlagzeilen'),
         (u'Exklusiv', u'http://www.wiwo.de/contentexport/feed/rss/exklusiv'),
-        # (u'Themen', u'http://www.wiwo.de/contentexport/feed/rss/themen'), # AGE no print version
+        #              (u'Themen', u'http://www.wiwo.de/contentexport/feed/rss/themen'), # AGE no print version
         (u'Unternehmen', u'http://www.wiwo.de/contentexport/feed/rss/unternehmen'),
         (u'Finanzen', u'http://www.wiwo.de/contentexport/feed/rss/finanzen'),
         (u'Politik', u'http://www.wiwo.de/contentexport/feed/rss/politik'),
         (u'Erfolg', u'http://www.wiwo.de/contentexport/feed/rss/erfolg'),
         (u'Technologie', u'http://www.wiwo.de/contentexport/feed/rss/technologie'),
-        # (u'Green-WiWo', u'http://green.wiwo.de/feed/rss/') # AGE no print version
+        #              (u'Green-WiWo', u'http://green.wiwo.de/feed/rss/') # AGE offline
     ]
 
+    # one page n times url: https://www.wiwo.de/finanzen/geldanlage/bla-bla/21020646.html
+    # all in one page article url: https://www.wiwo.de/finanzen/geldanlage/bla-bla/21020646-all.html
+
     def print_version(self, url):
-        main, sep, id = url.rpartition('/')
+        main, sep, rest = url.rpartition('.')
-        return main + '/v_detail_tab_print/' + id
+        return main + '-all' + sep + rest