Dnevnik (MK) and =Info by Darko Spasovski

2025-08-30 23:00:21 -04:00 · 2011-07-27 09:43:21 -06:00 · 2011-07-27 09:43:21 -06:00 · 6557e06577
commit 6557e06577
parent 9618a0ac4d
2 changed files with 145 additions and 0 deletions
--- a/recipes/dnevnik_mk.recipe
+++ b/recipes/dnevnik_mk.recipe
@ -0,0 +1,98 @@
+#!/usr/bin/env  python
+
+__author__    = 'Darko Spasovski'
+__license__   = 'GPL v3'
+__copyright__ = '2011, Darko Spasovski <darko.spasovski at gmail.com>'
+'''
+dnevnik.com.mk
+'''
+
+import re
+import datetime
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre import browser
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
+
+class Dnevnik(BasicNewsRecipe):
+
+    INDEX                 = 'http://www.dnevnik.com.mk'
+    __author__ = 'Darko Spasovski'
+    title                 = 'Dnevnik - mk'
+    description           = 'Daily Macedonian newspaper'
+    masthead_url          = 'http://www.dnevnik.com.mk/images/re-logo.gif'
+    language              = 'mk'
+    publication_type      = 'newspaper'
+    category              = 'news, Macedonia'
+    max_articles_per_feed = 100
+    remove_javascript     = True
+    no_stylesheets        = True
+    use_embedded_content  = False
+
+    preprocess_regexps = [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
+    [
+        ## Remove anything before the start of the article.
+        (r'<body.*?<\?xml version=\"1.0\"\?><!--Article start-->', lambda match: '<body>'),
+
+        ## Remove anything after the end of the article.
+        (r'<!--Article end.*?</body>', lambda match : '</body>'),
+        ]
+    ]
+
+    extra_css = """
+                    body{font-family: Arial,Helvetica,sans-serif}
+                    .WB_DNEVNIK_Naslov{FONT-WEIGHT: bold; FONT-SIZE: 18px; FONT-FAMILY: Arial, Verdana, Tahoma; TEXT-DECORATION: none}
+                """
+
+    conversion_options = {
+                          'comment'  : description,
+                          'tags'     : category,
+                          'language' : language,
+                          'linearize_tables' : True
+                        }
+
+    def parse_index(self):
+        datum = datetime.datetime.today().strftime('%d.%m.%Y')
+        soup = self.index_to_soup(self.INDEX + '/default.asp?section=arhiva&arhDatum=' + datum)
+        feeds = []
+        for section in soup.findAll('td', attrs={'class':'WB_DNEVNIK_ArhivaFormTitle'}):
+            sectionTitle = section.contents[0].string
+            if sectionTitle.lower().startswith('online'):
+                # Skip online articles
+                continue
+            containerTable = section.findPrevious(name='table').findNextSibling(name='table')
+            if containerTable==None:
+                print 'No container table found - page layout may have been changed.'
+                continue
+            articles = []
+            for article in containerTable.findAll('a', attrs={'class': 'WB_DNEVNIK_ArhivaFormText'}):
+                title = self.tag_to_string(article, use_alt=True).strip()
+                articles.append({'title': title, 'url':'http://www.dnevnik.com.mk/' + article['href'], 'description':'', 'date':''})
+            if articles:
+                feeds.append((sectionTitle, articles))
+        return sorted(feeds, key=lambda section: self.get_weight(section))
+
+    def get_weight(self, section):
+        """
+        Returns 'weight' of a section.
+        Used for sorting the sections based on their 'natural' order in the printed edition.
+        """
+        natural_order = { u'во фокусот': 1, u'актуелно': 2, u'економија': 3,
+                          u'отворена': 4, u'свет': 5, u'интервју': 6, u'џубокс': 7,
+                          u'репортажа': 8, u'наш туризам': 9, u'живот': 10,
+                          u'автомобилизам': 11, u'спорт': 12, u'омнибус': 13 }
+        if section[0].string.lower() in natural_order:
+            return natural_order[section[0].string.lower()]
+        else:
+            return 999  # section names not on the list go to the bottom
+
+    def get_cover_url(self):
+        datum = datetime.datetime.today().strftime('%d.%m.%Y')
+        soup = self.index_to_soup(self.INDEX + '/default.asp?section=arhiva&arhDatum=' + datum)
+        anchor = soup.find('a', attrs={'class': 'WB_DNEVNIK_MoreLink'})
+        if anchor != None:
+            raw = browser().open_novisit(self.INDEX + '/' + anchor['href']).read()
+            cover_soup = BeautifulSoup(raw)
+            url = cover_soup.find('div', attrs={'class':'WB_DNEVNIK_Datum2'}).findNext('img')['src']
+            return self.INDEX + '/' + url
+        return ''
+
--- a/recipes/plus_info.recipe
+++ b/recipes/plus_info.recipe
@ -0,0 +1,47 @@
+#!/usr/bin/env python
+
+__author__    = 'Darko Spasovski'
+__license__   = 'GPL v3'
+__copyright__ = '2011, Darko Spasovski <darko.spasovski at gmail.com>'
+
+'''
+www.plusinfo.mk
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class PlusInfo(BasicNewsRecipe):
+
+    INDEX                 = 'www.plusinfo.mk'
+    title                 = u'+info'
+    __author__ = 'Darko Spasovski'
+    description           = 'Macedonian news portal'
+    publication_type      = 'newsportal'
+    category              = 'news, Macedonia'
+    language              = 'mk'
+    masthead_url          = 'http://www.plusinfo.mk/style/images/logo.jpg'
+    remove_javascript     = True
+    no_stylesheets        = True
+    use_embedded_content  = False
+    remove_empty_feeds    = True
+    oldest_article        = 1
+    max_articles_per_feed = 100
+
+    keep_only_tags = [dict(name='div', attrs={'class': 'vest'})]
+    remove_tags = [dict(name='div', attrs={'class':['komentari_holder', 'objava']})]
+
+    feeds          = [(u'Македонија', u'http://www.plusinfo.mk/rss/makedonija'),
+                      (u'Бизнис', u'http://www.plusinfo.mk/rss/biznis'),
+                      (u'Скопје', u'http://www.plusinfo.mk/rss/skopje'),
+                      (u'Култура', u'http://www.plusinfo.mk/rss/kultura'),
+                      (u'Свет', u'http://www.plusinfo.mk/rss/svet'),
+                      (u'Сцена', u'http://www.plusinfo.mk/rss/scena'),
+                      (u'Здравје', u'http://www.plusinfo.mk/rss/zdravje'),
+                      (u'Магазин', u'http://www.plusinfo.mk/rss/magazin'),
+                      (u'Спорт', u'http://www.plusinfo.mk/rss/sport')]
+
+    # uncomment the following block if you want the print version (note: it lacks photos)
+#    def print_version(self,url):
+#        segments = url.split('/')
+#        printURL = '/'.join(segments[0:3]) + '/print/' + '/'.join(segments[5:])
+#        return printURL