Various Czech news source by FunThomas. Fixes #8562 (New Czech recipes)

resources/recipes/abc.recipe

@@ -0,0 +1,43 @@
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ABCRecipe(BasicNewsRecipe):
+  title          = u'ABC Linuxu'
+  oldest_article = 5
+  max_articles_per_feed = 3#5
+  __author__ = 'Funthomas'
+  language = 'cs'
+
+  feeds = [
+    #(u'Blogy', u'http://www.abclinuxu.cz/auto/blogDigest.rss'),
+    (u'Články', u'http://www.abclinuxu.cz/auto/abc.rss'),
+    (u'Zprávičky','http://www.abclinuxu.cz/auto/zpravicky.rss')
+  ]
+
+  remove_javascript = True
+  no_stylesheets    = True
+  remove_attributes = ['width','height']
+
+  remove_tags_before = dict(name='h1')
+  remove_tags = [
+    dict(attrs={'class':['meta-vypis','page_tools','cl_perex']}),
+    dict(attrs={'class':['cl_nadpis-link','komix-nav']})
+  ]
+
+  remove_tags_after = [
+    dict(name='div',attrs={'class':['cl_perex','komix-nav']}),
+    dict(attrs={'class':['meta-vypis','page_tools']}),
+    dict(name='',attrs={'':''}),
+  ]
+
+
+  preprocess_regexps = [
+    (re.compile(r'</div>.*<p class="perex">', re.DOTALL),lambda match: '</div><p class="perex">')
+  ]
+  def print_version(self, url):
+    return url + '?varianta=print&noDiz'
+
+  extra_css = '''
+            h1 {font-size:130%; font-weight:bold}
+            h3 {font-size:111%; font-weight:bold}
+        '''

resources/recipes/idnes.recipe

@@ -0,0 +1,54 @@
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class iHeuteRecipe(BasicNewsRecipe):
+    __author__  = 'FunThomas'
+    title = u'iDnes.cz'
+    publisher = u'MAFRA a.s.'
+    description = 'iDNES.cz Zprávy, Technet, Komiksy a další'
+    oldest_article = 3
+    max_articles_per_feed = 2
+
+    feeds = [
+            (u'Zprávy', u'http://servis.idnes.cz/rss.asp?c=zpravodaj'),
+            (u'Sport', u'http://servis.idnes.cz/rss.asp?c=sport'),
+            (u'Technet', u'http://servis.idnes.cz/rss.asp?c=technet'),
+            (u'Mobil', u'http://servis.idnes.cz/rss.asp?c=mobil'),
+            (u'Ekonomika', u'http://servis.idnes.cz/rss.asp?c=ekonomikah'),
+            #(u'Kultura', u'http://servis.idnes.cz/rss.asp?c=kultura'),
+            (u'Cestování', u'http://servis.idnes.cz/rss.asp?c=iglobe'),
+            #(u'Kavárna', u'http://servis.idnes.cz/rss.asp?r=kavarna'),
+            (u'Komixy', u'http://servis.idnes.cz/rss.asp?c=komiksy')
+            ]
+
+
+    encoding = 'cp1250'
+    language = 'cs'
+    cover_url = 'http://g.idnes.cz/u/loga-n4/idnes.gif'
+    remove_javascript = True
+    no_stylesheets = True
+
+    remove_attributes = ['width','height']
+    remove_tags = [dict(name='div',   attrs={'id':['zooming']}),
+                   dict(name='div',   attrs={'class':['related','mapa-wrapper']}),
+                   dict(name='table', attrs={'id':['opener-img','portal']}),
+                   dict(name='table', attrs={'class':['video-16ku9']})]
+    remove_tags_after  = [dict(name='div',attrs={'id':['related','related2']})]
+
+    keep_only_tags = [dict(name='div', attrs={'class':['art-full adwords-text','dil-day']})
+                      ,dict(name='table',attrs={'class':['kemel-box']})]
+
+    def print_version(self, url):
+        print_url = url
+        split_url = url.split("?")
+        if (split_url[0].rfind('dilbert.asp')  != -1):      #dilbert komix
+            print_url = print_url.replace('.htm','.gif&tisk=1')
+            print_url = print_url.replace('.asp','.aspx')
+        elif (split_url[0].rfind('kemel.asp')  == -1):      #not Kemel komix
+            print_url = 'http://zpravy.idnes.cz/tiskni.asp?' +  split_url[1]
+        #kemel                  kemel print page doesn't work
+        return print_url
+
+    extra_css = '''
+                  h1 {font-size:125%; font-weight:bold}
+                  h3 {font-size:110%; font-weight:bold}
+                '''

resources/recipes/root.recipe

@@ -0,0 +1,39 @@
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1289939440(BasicNewsRecipe):
+  __author__  = 'FunThomas'
+  title       = u'Root.cz'
+  description = u'Zprávičky a články z Root.cz'
+  publisher   = u'Internet Info, s.r.o'
+  oldest_article = 2               #max stari clanku ve dnech
+  max_articles_per_feed = 50       #max pocet clanku na feed
+
+  feeds = [
+    (u'Články', u'http://www.root.cz/rss/clanky/'),
+    (u'Zprávičky', u'http://www.root.cz/rss/zpravicky/')
+  ]
+
+  publication_type = u'magazine'
+  language = u'cs'
+  no_stylesheets = True
+  remove_javascript = True
+  cover_url = u'http://i.iinfo.cz/urs/logo-root-bila-oranzova-cerna-111089527143118.gif'
+
+  remove_attributes = ['width','height','href'] #,'href'
+  keep_only_tags = [
+    dict(name='h1'),
+    dict(name='a',attrs={'class':'author'}),
+    dict(name='p', attrs={'class':'intro'}),
+    dict(name='div',attrs={'class':'urs'})
+  ]
+
+  preprocess_regexps = [
+    (re.compile(u'<p class="perex[^"]*">[^<]*<img[^>]*>', re.DOTALL),lambda match: '<p class="intro">'),
+    (re.compile(u'<h3><a name="tucnak">Tričko tučňák.*</body>', re.DOTALL),lambda match: '<!--deleted-->')
+  ]
+
+  extra_css = '''
+                h1 {font-size:130%; font-weight:bold}
+                h3 {font-size:111%; font-weight:bold}
+              '''