Update various Polish recipes

recipes/adventure_zone_pl.recipe

@@ -11,7 +11,7 @@ class Adventure_zone(BasicNewsRecipe):
     max_articles_per_feed = 100
     cover_url = 'http://www.adventure-zone.info/inne/logoaz_2012.png'
     index='http://www.adventure-zone.info/fusion/'
-    use_embedded_content=False
+    use_embedded_content = False
     preprocess_regexps     = [(re.compile(r"<td class='capmain'>Komentarze</td>", re.IGNORECASE), lambda m: ''),
     (re.compile(r'</?table.*?>'), lambda match: ''),
     (re.compile(r'</?tbody.*?>'), lambda match: '')]
@@ -21,7 +21,7 @@ class Adventure_zone(BasicNewsRecipe):
     extra_css              = '.main-bg{text-align: left;}  td.capmain{ font-size: 22px; }'
     feeds          = [(u'Nowinki', u'http://www.adventure-zone.info/fusion/feeds/news.php')]
 
-    def parse_feeds (self): 
+    '''def parse_feeds (self): 
       feeds = BasicNewsRecipe.parse_feeds(self) 
       soup=self.index_to_soup(u'http://www.adventure-zone.info/fusion/feeds/news.php')
       tag=soup.find(name='channel')
@@ -34,7 +34,7 @@ class Adventure_zone(BasicNewsRecipe):
       for feed in feeds:
         for article in feed.articles[:]:
             article.title=titles[feed.articles.index(article)]
-      return feeds
+      return feeds'''
 
 
     '''def get_cover_url(self):
@@ -42,16 +42,25 @@ class Adventure_zone(BasicNewsRecipe):
         cover=soup.find(id='box_OstatninumerAZ')
         self.cover_url='http://www.adventure-zone.info/fusion/'+ cover.center.a.img['src']
         return getattr(self, 'cover_url', self.cover_url)'''
-
+    def populate_article_metadata(self, article, soup, first):
+        result = re.search('(.+) - Adventure Zone', soup.title.string)
+        if result:
+            article.title = result.group(1)
+        else:
+            result = soup.body.find('strong')
+            if result:
+                article.title = result.string
 
     def skip_ad_pages(self, soup):
         skip_tag = soup.body.find(name='td', attrs={'class':'main-bg'})
         skip_tag = skip_tag.findAll(name='a')
-        for r in skip_tag:
+        title = soup.title.string.lower()
-           if r.strong:
+        if (('zapowied' in title) or ('recenzj' in title)  or ('solucj' in title) or ('poradnik' in title)):
-                 word=r.strong.string.lower()
+            for r in skip_tag:
-                 if word and (('zapowied' in word) or ('recenzj' in word)  or ('solucj' in word) or ('poradnik' in word)):
+                if r.strong and r.strong.string:
-                   return self.index_to_soup('http://www.adventure-zone.info/fusion/print.php?type=A&item'+r['href'][r['href'].find('article_id')+7:], raw=True)
+                   word=r.strong.string.lower()
+                   if (('zapowied' in word) or ('recenzj' in word)  or ('solucj' in word) or ('poradnik' in word)):
+                       return self.index_to_soup('http://www.adventure-zone.info/fusion/print.php?type=A&item'+r['href'][r['href'].find('article_id')+7:], raw=True)
 
     def preprocess_html(self, soup):
         footer=soup.find(attrs={'class':'news-footer middle-border'})

recipes/bash_org_pl.recipe

@@ -35,8 +35,8 @@ class Bash_org_pl(BasicNewsRecipe):
              soup=self.index_to_soup(u'http://bash.org.pl/random/')
              #date=soup.find('div', attrs={'class':'right'}).string
              url=soup.find('a', attrs={'class':'qid click'})
-             title=url.string
+             title=''
-             url='http://bash.org.pl' +url['href']
+             url='http://bash.org.pl/random/'
              articles.append({'title' : title,
 	               'url'   : url,
 	               'date'  : '',
@@ -44,6 +44,8 @@ class Bash_org_pl(BasicNewsRecipe):
 	                })
          return articles
 
+    def populate_article_metadata(self, article, soup, first):
+        article.title = soup.find(attrs={'class':'qid click'}).string
 
     def parse_index(self):
          feeds          = []

recipes/ekologia_pl.recipe

@@ -15,7 +15,8 @@ class EkologiaPl(BasicNewsRecipe):
     no_stylesheets = True
     remove_empty_feeds = True
     use_embedded_content = False
-    remove_tags = [dict(attrs={'class':['ekoLogo', 'powrocArt', 'butonDrukuj']})]
+    remove_attrs = ['style']
+    remove_tags = [dict(attrs={'class':['ekoLogo', 'powrocArt', 'butonDrukuj', 'widget-social-buttons']})]
 
     feeds          = [(u'Wiadomo\u015bci', u'http://www.ekologia.pl/rss/20,53,0'), (u'\u015arodowisko', u'http://www.ekologia.pl/rss/20,56,0'), (u'Styl \u017cycia', u'http://www.ekologia.pl/rss/20,55,0')]
 

recipes/informacje_usa.recipe

@@ -1,5 +1,4 @@
 from calibre.web.feeds.news import BasicNewsRecipe
-import re
 class Informacje_USA(BasicNewsRecipe):
     title          = u'Informacje USA'
     oldest_article = 7
@@ -8,11 +7,10 @@ class Informacje_USA(BasicNewsRecipe):
     description   = u'portal wiadomości amerykańskich'
     category       = 'news'
     language       = 'pl'
-    masthead_url= 'http://www.informacjeusa.com/wp-content/add_images/top_logo_5_2010.jpg'
+    cover_url='http://www.informacjeusa.com/wp-content/uploads/2013/01/V3BANNER420-90new.jpg'
-    cover_url='http://www.informacjeusa.com/wp-content/add_images/top_logo_5_2010.jpg'
     no_stylesheets = True
-    preprocess_regexps = [(re.compile(ur'<p>Zobacz:.*?</p>', re.DOTALL), lambda match: ''), (re.compile(ur'<p><a href=".*?Zobacz także:.*?</a></p>', re.DOTALL), lambda match: ''), (re.compile(ur'<p><p>Zobacz też:.*?</a></p>', re.DOTALL), lambda match: '')]
+    use_embedded_content = False
-    keep_only_tags=[dict(name='div', attrs={'class':'box box-single'})]
+    keep_only_tags=[dict(id='post-area')]
-    remove_tags_after= dict(attrs={'class':'tags'})
+    remove_tags_after= dict(id='content-area')
-    remove_tags= [dict(attrs={'class':['postmetadata', 'tags', 'banner']}), dict(name='a', attrs={'title':['Drukuj', u'Wyślij']})]
+    remove_tags= [dict(attrs={'class':['breadcrumb']}), dict(id=['social-box', 'social-box-vert'])]
     feeds          = [(u'Informacje', u'http://www.informacjeusa.com/feed/')]

recipes/mlody_technik_pl.recipe

@@ -1,5 +1,5 @@
 # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
-
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
 class Mlody_technik(BasicNewsRecipe):
     title          = u'Młody technik'
@@ -9,7 +9,19 @@ class Mlody_technik(BasicNewsRecipe):
     language       = 'pl'
     cover_url='http://science-everywhere.pl/wp-content/uploads/2011/10/mt12.jpg'
     no_stylesheets = True
+    preprocess_regexps = [(re.compile(r"<h4>Podobne</h4>", re.IGNORECASE), lambda m: '')]
     oldest_article = 7
     max_articles_per_feed = 100
-    #keep_only_tags=[dict(id='container')]
+    remove_empty_feeds = True
-    feeds          = [(u'Artyku\u0142y', u'http://www.mt.com.pl/feed')]
+    use_embedded_content = False
+    keep_only_tags = [dict(id='content')]
+    remove_tags = [dict(attrs={'class':'st-related-posts'})]
+    remove_tags_after = dict(attrs={'class':'entry-content clearfix'})
+    feeds          = [(u'Wszystko', u'http://www.mt.com.pl/feed'), 
+		(u'MT NEWS 24/7', u'http://www.mt.com.pl/kategoria/mt-newsy-24-7/feed'),
+		(u'Info zoom', u'http://www.mt.com.pl/kategoria/info-zoom/feed'),
+		(u'm.technik', u'http://www.mt.com.pl/kategoria/m-technik/feed'),
+		(u'Szkoła', u'http://www.mt.com.pl/kategoria/szkola-2/feed'),
+		(u'Na Warsztacie', u'http://www.mt.com.pl/kategoria/na-warsztacie/feed'),
+		(u'Z pasji do...', u'http://www.mt.com.pl/kategoria/z-pasji-do/feed'),
+		(u'MT testuje', u'http://www.mt.com.pl/kategoria/mt-testuje/feed')]

recipes/pc_lab.recipe

@@ -1,5 +1,4 @@
 #!/usr/bin/env  python
-
 from calibre.web.feeds.recipes import BasicNewsRecipe
 
 class PCLab(BasicNewsRecipe):
@@ -8,12 +7,13 @@ class PCLab(BasicNewsRecipe):
     __author__            = 'ravcio - rlelusz[at]gmail.com'
     description           = u"Articles from PC Lab website"
     language              = 'pl'
-    oldest_article        = 30.0
+    oldest_article        = 30
     max_articles_per_feed = 100
     recursions            = 0
     encoding              = 'iso-8859-2'
     no_stylesheets        = True
     remove_javascript     = True
+    remove_empty_feeds = True
     use_embedded_content  = False
 
     keep_only_tags = [
@@ -21,50 +21,54 @@ class PCLab(BasicNewsRecipe):
                      ]
 
     remove_tags = [
-            dict(name='div', attrs={'class':['chapters']})
+            dict(name='div', attrs={'class':['toc first', 'toc', 'tags', 'recommendedarticles', 'name', 'zumi', 'chapters']})
-            ,dict(name='div', attrs={'id':['script_bxad_slot_display_list_bxad_slot']})
                   ]
 
-    remove_tags_after = [
-            dict(name='div', attrs={'class':['navigation']})
-                ]
-
     #links to RSS feeds
-    feeds = [ ('PCLab', u'http://pclab.pl/xml/artykuly.xml') ]
+    feeds = [
+             (u'Aktualności', 'http://pclab.pl/xml/aktualnosci.xml'),
+             (u'Artykuły', u'http://pclab.pl/xml/artykuly.xml'),
+             (u'Poradniki', 'http://pclab.pl/xml/poradniki.xml')
+             ]
 
     #load second and subsequent page content
     # in: soup - full page with 'next' button
     # out: appendtag - tag to which new page is to be added
     def append_page(self, soup, appendtag):
         # find the 'Next' button
-        pager = soup.find('div', attrs={'class':'next'})
+        pager = soup.find('div', attrs={'class':'navigation'})
-
         if pager:
+            a = pager.find('a')
+            if 'news' in a['href']:
+                pager = None
+            else:
+                pager = pager.find('div', attrs={'class':'next'})
+
+        while pager:
             #search for 'a' element with link to next page (exit if not found)
             a = pager.find('a')
-            if a:
+            nexturl = a['href']
-                nexturl = a['href']
+            soup2 = self.index_to_soup('http://pclab.pl' + nexturl)
+            pager = soup2.find('div', attrs={'class':'next'})
+            pagetext = soup2.find('div', attrs={'class':'substance'})
+            pagetext = pagetext.find('div', attrs={'class':'data'})
 
-                soup2 = self.index_to_soup('http://pclab.pl/' + nexturl)
+            pos = len(appendtag.contents)
-
+            appendtag.insert(pos, pagetext)
-                pagetext_substance = soup2.find('div', attrs={'class':'substance'})
+            pos = len(appendtag.contents)
-                pagetext = pagetext_substance.find('div', attrs={'class':'data'})
-                pagetext.extract()
-
-                pos = len(appendtag.contents)
-                appendtag.insert(pos, pagetext)
-                pos = len(appendtag.contents)
-
-                self.append_page(soup2, appendtag)
 
+        pager = soup.find('div', attrs={'class':'navigation'})
+        if pager:
+            pager.extract()
 
     def preprocess_html(self, soup):
-
         # soup.body contains no title and no navigator, they are in soup
         self.append_page(soup, soup.body)
-
+        for link in soup.findAll('a'):
+            href = link.get('href', None)
+            if href and href.startswith('/'):
+                link['href'] = 'http://pclab.pl' + href
         # finally remove some tags
-        tags = soup.findAll('div',attrs={'class':['tags', 'index', 'script_bxad_slot_display_list_bxad_slot', 'index first', 'zumi', 'navigation']})
+        #for r in soup.findAll('div', attrs={'class':['tags', 'index', 'script_bxad_slot_display_list_bxad_slot', 'index first', 'zumi', 'navigation']})
-        [tag.extract() for tag in tags]
 
         return soup

recipes/spiders_web_pl.recipe

@@ -5,11 +5,14 @@ class SpidersWeb(BasicNewsRecipe):
     oldest_article = 7
     __author__        = 'fenuks'
     description   = u''
-    cover_url      = 'http://www.spidersweb.pl/wp-content/themes/spiderweb/img/Logo.jpg'
+    cover_url      = 'http://www.spidersweb.pl/wp-content/themes/new_sw/images/spidersweb.png'
     category       = 'IT, WEB'
     language       = 'pl'
     no_stylesheers=True
+    remove_javascript = True
+    use_embedded_content = False
     max_articles_per_feed = 100
-    keep_only_tags=[dict(id='Post')]
+    keep_only_tags=[dict(id='start')]
-    remove_tags=[dict(name='div', attrs={'class':['Comments', 'Shows', 'Post-Tags']}), dict(id='Author-Column')]
+    remove_tags_after = dict(attrs={'class':'padding20'})
+    remove_tags=[dict(name='div', attrs={'class':['padding border-bottom', 'padding20', 'padding border-top']})]
     feeds          = [(u'Wpisy', u'http://www.spidersweb.pl/feed')]

recipes/wprost.recipe

@@ -10,89 +10,89 @@ from calibre.web.feeds.news import BasicNewsRecipe
 import re
 
 class Wprost(BasicNewsRecipe):
-        EDITION = 0
+    EDITION = 0
-        FIND_LAST_FULL_ISSUE = True
+    FIND_LAST_FULL_ISSUE = True
-        EXCLUDE_LOCKED = True
+    EXCLUDE_LOCKED = True
-        ICO_BLOCKED = 'http://www.wprost.pl/G/layout2/ico_blocked.png'
+    ICO_BLOCKED = 'http://www.wprost.pl/G/layout2/ico_blocked.png'
+    title = u'Wprost'
+    __author__ = 'matek09'
+    description = 'Weekly magazine'
+    encoding = 'ISO-8859-2'
+    no_stylesheets = True
+    language = 'pl'
+    remove_javascript = True
+    recursions = 0  
+    remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
+    remove_tags_after = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
+    '''
+    keep_only_tags =[]
+    keep_only_tags.append(dict(name = 'table', attrs = {'id' : 'title-table'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-header'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-content'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'def element-autor'}))
+    '''
 
-        title = u'Wprost'
+    preprocess_regexps = [(re.compile(r'style="display: none;"'), lambda match: ''),
-        __author__ = 'matek09'
-        description = 'Weekly magazine'
-        encoding = 'ISO-8859-2'
-        no_stylesheets = True
-        language = 'pl'
-        remove_javascript = True
-	recursions = 0	
-
-        remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
-        remove_tags_after = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
-
-        '''keep_only_tags =[]
-        keep_only_tags.append(dict(name = 'table', attrs = {'id' : 'title-table'}))
-        keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-header'}))
-        keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-content'}))
-        keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'def element-autor'}))'''
-
-        preprocess_regexps = [(re.compile(r'style="display: none;"'), lambda match: ''),
         (re.compile(r'display: block;'), lambda match: ''),
         (re.compile(r'\<td\>\<tr\>\<\/table\>'), lambda match: ''),
         (re.compile(r'\<table .*?\>'), lambda match: ''),
         (re.compile(r'\<tr>'), lambda match: ''),
         (re.compile(r'\<td .*?\>'), lambda match: ''),
-	(re.compile(r'\<div id="footer"\>.*?\</footer\>'), lambda match: '')]
+        (re.compile(r'\<div id="footer"\>.*?\</footer\>'), lambda match: '')]
 
-        remove_tags =[]
+    remove_tags =[]
-        remove_tags.append(dict(name = 'div', attrs = {'class' : 'def element-date'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'def element-date'}))
-        remove_tags.append(dict(name = 'div', attrs = {'class' : 'def silver'}))
+    remove_tags.append(dict(name = 'div', attrs = {'class' : 'def silver'}))
-        remove_tags.append(dict(name = 'div', attrs = {'id' : 'content-main-column-right'}))
+    remove_tags.append(dict(name = 'div', attrs = {'id' : 'content-main-column-right'}))
 
 
-        extra_css = '''
+    extra_css = '''.div-header {font-size: x-small; font-weight: bold}'''
-                                        .div-header {font-size: x-small; font-weight: bold}
+    #h2 {font-size: x-large; font-weight: bold}
-                                        '''
+    def is_blocked(self, a):
-#h2 {font-size: x-large; font-weight: bold}
+        if a.findNextSibling('img') is None:
-        def is_blocked(self, a):
+            return False
-                if a.findNextSibling('img') is None:
+        else:
-                        return False
+            return True
-                else:
-                        return True
 
 
+    def find_last_issue(self):
+        soup = self.index_to_soup('http://www.wprost.pl/archiwum/')
+        a = 0
+        if self.FIND_LAST_FULL_ISSUE:
+            ico_blocked = soup.findAll('img', attrs={'src' : self.ICO_BLOCKED})
+            a = ico_blocked[-1].findNext('a', attrs={'title' : re.compile(r'Spis *', re.IGNORECASE | re.DOTALL)})
+        else:
+            a = soup.find('a', attrs={'title' : re.compile(r'Spis *', re.IGNORECASE | re.DOTALL)})
+        self.EDITION = a['href'].replace('/tygodnik/?I=', '')
+        self.EDITION_SHORT = a['href'].replace('/tygodnik/?I=15', '')
+        self.cover_url = a.img['src']
 
-        def find_last_issue(self):
+    def parse_index(self):
-                soup = self.index_to_soup('http://www.wprost.pl/archiwum/')
+        self.find_last_issue()
-                a = 0
+        soup = self.index_to_soup('http://www.wprost.pl/tygodnik/?I=' + self.EDITION)
-                if self.FIND_LAST_FULL_ISSUE:
+        feeds = []
-                        ico_blocked = soup.findAll('img', attrs={'src' : self.ICO_BLOCKED})
+        headers = soup.findAll(attrs={'class':'block-header block-header-left mtop20 mbottom20'})
-                        a = ico_blocked[-1].findNext('a', attrs={'title' : re.compile(r'Spis *', re.IGNORECASE | re.DOTALL)})
+        articles_list = soup.findAll(attrs={'class':'standard-box'})
-                else:
+        for i in range(len(headers)):
-                        a = soup.find('a', attrs={'title' : re.compile(r'Spis *', re.IGNORECASE | re.DOTALL)})
+            articles = self.find_articles(articles_list[i])
-                self.EDITION = a['href'].replace('/tygodnik/?I=', '')
+            if len(articles) > 0:
-		self.EDITION_SHORT = a['href'].replace('/tygodnik/?I=15', '')
+                section = headers[i].find('a').string
-		self.cover_url = a.img['src']
+                feeds.append((section, articles))
+        return feeds
 
-        def parse_index(self):
+    def find_articles(self, main_block):
-                self.find_last_issue()
+        articles = []
-                soup = self.index_to_soup('http://www.wprost.pl/tygodnik/?I=' + self.EDITION)
+        for a in main_block.findAll('a'):
-                feeds = []
+            if a.name in "td":
-                for main_block in soup.findAll(attrs={'id': 'content-main-column-element-content'}):
+                break
-                        articles = list(self.find_articles(main_block))
+            if self.EXCLUDE_LOCKED and self.is_blocked(a):
-                        if len(articles) > 0:
+                continue
-                                section = self.tag_to_string(main_block.find('h3'))
+            articles.append({
-                                feeds.append((section, articles))
+                'title' : self.tag_to_string(a),
-                return feeds
+                'url'   : 'http://www.wprost.pl' + a['href'],
-
+                'date'  : '',
-        def find_articles(self, main_block):
+                'description' : ''
-                for a in main_block.findAll('a'):
+            })
-                        if a.name in "td":
+        return articles
-                                break
-                        if self.EXCLUDE_LOCKED & self.is_blocked(a):
-                                continue
-                        yield {
-                                'title' : self.tag_to_string(a),
-                                'url'   : 'http://www.wprost.pl' + a['href'],
-                                'date'  : '',
-                                'description' : ''
-                                }