New recipes for index.hu and pcworld.hu by Ezmegaz

src/calibre/trac/plugins/download.py

@@ -20,7 +20,7 @@ DEPENDENCIES = [
             ('BeautifulSoup', '3.0.5', 'beautifulsoup', 'python-beautifulsoup', 'python-BeautifulSoup'),
             ('dnspython', '1.6.0', 'dnspython', 'dnspython', 'dnspython', 'dnspython'),
             ('poppler', '0.10.5', 'poppler', 'poppler', 'poppler', 'poppler'),
-            ('pdftk', '1.12', 'pdftk', 'pdftk', 'pdftk', 'pdftk'),
+            ('podofo', '0.7', 'podofo', 'podofo', 'podofo', 'podofo'),
             ]
 
 

src/calibre/trac/plugins/templates/linux.html

@@ -49,7 +49,7 @@
         </p>
         <p>
             ${app} is available in the software repositories of the following 
-            linux distributions:
+            supported linux distributions:
             <table id="install_info">
                 <col width="150" /><col width="*" />
                 <tr>

src/calibre/web/feeds/recipes/__init__.py

@@ -42,7 +42,7 @@ recipe_modules = ['recipe_' + r for r in (
            'moneynews', 'der_standard', 'diepresse', 'nzz_ger', 'hna',
            'seattle_times', 'scott_hanselman', 'coding_horror', 'twitchfilms',
            'stackoverflow', 'telepolis_artikel', 'zaobao', 'usnews',
-           'straitstimes',
+           'straitstimes', 'index_hu', 'pcworld_hu',
           )]
 
 import re, imp, inspect, time, os

src/calibre/web/feeds/recipes/recipe_blic.py

@@ -16,12 +16,14 @@ class Blic(BasicNewsRecipe):
     description           = 'Blic.co.yu online verzija najtiraznije novine u Srbiji donosi najnovije vesti iz Srbije i sveta, komentare, politicke analize, poslovne i ekonomske vesti, vesti iz regiona, intervjue, informacije iz kulture, reportaze, pokriva sve sportske dogadjaje, detaljan tv program, nagradne igre, zabavu, fenomenalni Blic strip, dnevni horoskop, arhivu svih dogadjaja'    
     publisher             = 'RINGIER d.o.o.'
     category              = 'news, politics, Serbia'
+    delay                 = 1
     oldest_article        = 2
     max_articles_per_feed = 100
     remove_javascript     = True
     no_stylesheets        = True
     use_embedded_content  = False
     language              = _('Serbian')
+    lang                  = 'sr-Latn-RS'
     extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif} '
     
     html2lrf_options = [
@@ -45,26 +47,14 @@ class Blic(BasicNewsRecipe):
         start_url, question, rest_url = url.partition('?')
         return u'http://www.blic.rs/_print.php?' + rest_url
 
-    def cleanup_image_tags(self,soup):
-        for item in soup.findAll('img'):
-            for attrib in ['height','width','border','align']:
-                if item.has_key(attrib):
-                   del item[attrib]
-            oldParent = item.parent
-            myIndex = oldParent.contents.index(item)
-            item.extract()
-            divtag = Tag(soup,'div')
-            brtag  = Tag(soup,'br')
-            oldParent.insert(myIndex,divtag)
-            divtag.append(item)
-            divtag.append(brtag)
-        return soup
-      
-    
     def preprocess_html(self, soup):
-        mtag = '<meta http-equiv="Content-Language" content="sr-Latn-RS"/>'
+        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        soup.head.insert(0,mtag)    
+        soup.head.insert(0,mlang)
         for item in soup.findAll(style=True):
             del item['style']
-        return self.cleanup_image_tags(soup)
+        return self.adeify_images(soup)
+
+    def get_article_url(self, article):
+        raw = article.get('link',  None)         
+        return raw.replace('.co.yu','.rs')
         

src/calibre/web/feeds/recipes/recipe_index_hu.py

@@ -0,0 +1,20 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Index(BasicNewsRecipe):
+
+    title = u'INDEX.HU'
+    oldest_article = 3
+    max_articles_per_feed = 50
+    language = _('Hungarian')
+    __author__ = 'Ezmegaz'
+
+    feeds = [(u'ALL', u'http://index.hu/24ora/rss/'),
+    (u'BELF\xd6LD', u'http://index.hu/belfold/rss/default/'),
+    (u'K\xdcLF\xd6LD', u'http://index.hu/kulfold/rss/default/'),
+    (u'BULV\xc1R', u'http://index.hu/bulvar/rss/default/'),
+    (u'GAZDAS\xc1G', u'http://index.hu/gazdasag/rss/default/'),
+    (u'TECH', u'http://index.hu/tech/rss/main/'),
+    (u'KULT\xdaRA', u'http://index.hu/kultur/rss/main/'),
+    (u'TUDOM\xc1NY', u'http://index.hu/tudomany/rss/main/'),
+    (u'V\xc9LEM\xc9NY', u'http://index.hu/velemeny/rss/default/')]
+

src/calibre/web/feeds/recipes/recipe_nin.py

@@ -8,12 +8,13 @@ nin.co.rs
 
 import re, urllib
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 
 class Nin(BasicNewsRecipe):    
     title                  = 'NIN online'
     __author__             = 'Darko Miletic'
     description            = 'Nedeljne informativne novine'
-    publisher              = 'NIN'
+    publisher              = 'NIN D.O.O.'
     category               = 'news, politics, Serbia'    
     no_stylesheets         = True
     oldest_article         = 15
@@ -28,9 +29,9 @@ class Nin(BasicNewsRecipe):
     remove_javascript      = True
     use_embedded_content   = False
     language               = _('Serbian')
-    lang                   = 'sr-RS'
+    lang                   = 'sr-Latn-RS'
     direction              = 'ltr'
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: justify; font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif} .artTitle{font-size: x-large; font-weight: bold} .columnhead{font-size: small; font-weight: bold}'
     
     html2lrf_options = [
                           '--comment'  , description
@@ -70,9 +71,10 @@ class Nin(BasicNewsRecipe):
     def preprocess_html(self, soup):
         soup.html['lang'] = self.lang
         soup.html['dir' ] = self.direction
-        mtag = '<meta http-equiv="Content-Language" content="' + self.lang + '"/>'
+        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        mtag += '\n<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '"/>'
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=UTF-8")])
-        soup.head.insert(0,mtag)    
+        soup.head.insert(0,mlang)
+        soup.head.insert(1,mcharset)
         for item in soup.findAll(style=True):
             del item['style']        
         return soup

src/calibre/web/feeds/recipes/recipe_pcworld_hu.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import with_statement
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
+__docformat__ = 'restructuredtext en'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Index(BasicNewsRecipe):
+
+
+    title = u'PCWORLD.HU'
+    oldest_article = 3
+    max_articles_per_feed = 50
+    language = _('Hungarian')
+    __author__ = 'Ezmegaz'
+
+
+    feeds = [(u'H\xedrek', u'http://pcworld.hu/rss/rss.xml'), (u'Hardver h\xedrek', u'http://www.pcworld.hu/rss/rss_hardverhirek.xml'), (u'Szoftver h\xedrek', u'http://www.pcworld.hu/rss/rss_szoftverhirek.xml'), (u'Hardver cikkek', u'http://www.pcworld.hu/rss/rss_hardvercikkek.xml'), (u'Szoftver cikkek', u'http://www.pcworld.hu/rss/rss_szoftvercikkek.xml'), (u'Mobil h\xedrek', u'http://www.pcworld.hu/rss/rss_mobil.xml'), (u'\xdczleti h\xedrek', u'http://www.pcworld.hu/rss/rss_uzlet.xml'), (u'Let\xf6lt\xe9sek', u'http://www.pcworld.hu/rss/rss_letoltes.xml'), (u'PC World TV', u'http://tv.pcworld.hu/rss/rss_hun_pcw.xml'), (u'Tudta-e...?', u'http://pcworld.hu/rss/rss_tudtae.xml')]
+

src/calibre/web/feeds/recipes/recipe_pobjeda.py

@@ -10,6 +10,7 @@ pobjeda.co.me
 import re
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 
 class Pobjeda(BasicNewsRecipe):
     title                 = 'Pobjeda Online'
@@ -22,12 +23,13 @@ class Pobjeda(BasicNewsRecipe):
     encoding              = 'utf8'
     remove_javascript     = True
     use_embedded_content  = False
+    language              = _('Serbian')
+    lang                  = 'sr-Latn-Me'
     INDEX                 = u'http://www.pobjeda.co.me'
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{text-align: justify; font-family: serif1, serif} .article_description{font-family: serif1, serif}'
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif}'
     
     html2lrf_options = [
                           '--comment', description
-                        , '--base-font-size', '10'
                         , '--category', category
                         , '--publisher', publisher
                         ]
@@ -59,11 +61,13 @@ class Pobjeda(BasicNewsRecipe):
             ]
 
     def preprocess_html(self, soup):
-        soup.html['xml:lang'] = 'sr-Latn-ME'
+        soup.html['xml:lang'] = self.lang
-        soup.html['lang']     = 'sr-Latn-ME'
+        soup.html['lang']     = self.lang
-        mtag = '<meta http-equiv="Content-Language" content="sr-Latn-ME"/>'
+        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        soup.head.insert(0,mtag)
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=UTF-8")])
-        return soup
+        soup.head.insert(0,mlang)
+        soup.head.insert(1,mcharset)
+        return self.adeify_images(soup)
 
     def get_cover_url(self):
         cover_url = None

src/calibre/web/feeds/recipes/recipe_st_petersburg_times.py

@@ -1,39 +1,48 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+
 '''
 sptimes.ru
 '''
 
-from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class PetersburgTimes(BasicNewsRecipe):
-    title                 = u'The St. Petersburg Times'
+    title                 = 'The St. Petersburg Times'
     __author__            = 'Darko Miletic'
     description           = 'News from Russia'
-    oldest_article        = 7
+    publisher             = 'sptimes.ru'
+    category              = 'news, politics, Russia'
     max_articles_per_feed = 100
     no_stylesheets        = True
+    remove_javascript     = True
+    encoding              = 'cp1251'
     use_embedded_content  = False
-    language = _('English')
+    language              = _('English')
-    INDEX = 'http://www.sptimes.ru'
     
-    def parse_index(self):
+    html2lrf_options = [
-        articles = []
+                          '--comment', description
-        soup = self.index_to_soup(self.INDEX)
+                        , '--category', category
+                        , '--publisher', publisher
+                        , '--ignore-tables'
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
+     
+    remove_tags = [dict(name=['object','link','embed'])]
+
+    feeds = [(u'Headlines', u'http://sptimes.ru/headlines.php' )]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+
+    def get_article_url(self, article):
+        raw = article.get('guid',  None)         
+        return raw
+
+    def print_version(self, url):
+        start_url, question, article_id = url.rpartition('/')
+        return u'http://www.sptimes.ru/index.php?action_id=100&story_id=' + article_id
         
-        for item in soup.findAll('a', attrs={'class':'story_link_o'}):
-            if item.has_key('href'):
-                url    = self.INDEX + item['href'].replace('action_id=2','action_id=100')
-                title  = self.tag_to_string(item)
-                c_date = strftime('%A, %d %B, %Y')
-                description = ''
-                articles.append({
-                                 'title':title,
-                                 'date':c_date,
-                                 'url':url,
-                                 'description':description
-                                })
-        return [(soup.head.title.string, articles)]

src/calibre/web/feeds/recipes/recipe_vijesti.py

@@ -9,6 +9,7 @@ vijesti.me
 
 import re
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 
 class Vijesti(BasicNewsRecipe):
     title                 = 'Vijesti'
@@ -16,8 +17,8 @@ class Vijesti(BasicNewsRecipe):
     description           = 'News from Montenegro'
     publisher             = 'Daily Press Vijesti'
     category              = 'news, politics, Montenegro'    
-    oldest_article        = 1
+    oldest_article        = 2
-    max_articles_per_feed = 100
+    max_articles_per_feed = 150
     no_stylesheets        = True
     remove_javascript     = True
     encoding              = 'cp1250'
@@ -25,7 +26,8 @@ class Vijesti(BasicNewsRecipe):
     remove_javascript     = True
     use_embedded_content  = False
     language              = _('Serbian')
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{text-align: justify; font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
+    lang                  ='sr-Latn-Me'
+    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
     
     html2lrf_options = [
                           '--comment', description
@@ -44,12 +46,15 @@ class Vijesti(BasicNewsRecipe):
     feeds = [(u'Sve vijesti', u'http://www.vijesti.me/rss.php' )]
 
     def preprocess_html(self, soup):
-        soup.html['xml:lang'] = 'sr-Latn-ME'
+        soup.html['xml:lang'] = self.lang
-        soup.html['lang']     = 'sr-Latn-ME'
+        soup.html['lang']     = self.lang
-        mtag = '<meta http-equiv="Content-Language" content="sr-Latn-ME"/>'
+        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        soup.head.insert(0,mtag)
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=UTF-8")])
-        for item in soup.findAll('img'):
+        soup.head.insert(0,mlang)
-            if item.has_key('align'):
+        soup.head.insert(1,mcharset)
-               del item['align']
+        return self.adeify_images(soup)
-               item.insert(0,'<br /><br />')
+
-        return soup
+    def get_article_url(self, article):
+        raw = article.get('link',  None)         
+        return raw.replace('.cg.yu','.me')
+        

src/calibre/web/feeds/recipes/recipe_vreme.py

@@ -9,6 +9,7 @@ vreme.com
 import re
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 
 class Vreme(BasicNewsRecipe):    
     title                = 'Vreme'
@@ -27,7 +28,7 @@ class Vreme(BasicNewsRecipe):
     language             = _('Serbian')
     lang                 = 'sr-Latn-RS'
     direction            = 'ltr'    
-    extra_css            = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{text-align: justify; font-family: serif1, serif} .article_description{font-family: serif1, serif}' 
+    extra_css            = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif} .heading1{font-size: x-large; font-weight: bold} .heading2{font-size: large; font-weight: bold} .toc-heading{font-size: small}' 
     
     html2lrf_options = [
                           '--comment'  , description
@@ -89,9 +90,10 @@ class Vreme(BasicNewsRecipe):
             del item['size']
         soup.html['lang'] = self.lang
         soup.html['dir' ] = self.direction
-        mtag = '<meta http-equiv="Content-Language" content="' + self.lang + '"/>'
+        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        mtag += '\n<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '"/>'
+        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=UTF-8")])
-        soup.head.insert(0,mtag)    
+        soup.head.insert(0,mlang)
+        soup.head.insert(1,mcharset)
         return soup
                 
     def get_cover_url(self):