Merge from trunk

recipes/dna.recipe

@@ -1,6 +1,3 @@
-'''
-dnaindia.com
-'''
 import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
@@ -12,6 +9,10 @@ class DNAIndia(BasicNewsRecipe):
     language = 'en_IN'
 
     encoding    = 'cp1252'
+    use_embedded_content = False
+
+    no_stylesheets = True
+    auto_cleanup = True
 
     feeds       = [
                    ('Top News', 'http://www.dnaindia.com/syndication/rss_topnews.xml'),
@@ -22,15 +23,10 @@ class DNAIndia(BasicNewsRecipe):
                    ('World', 'http://www.dnaindia.com/syndication/rss,catid-9.xml'),
                    ('Money', 'http://www.dnaindia.com/syndication/rss,catid-4.xml'),
                    ('Sports', 'http://www.dnaindia.com/syndication/rss,catid-6.xml'),
-                   ('After Hours', 'http://www.dnaindia.com/syndication/rss,catid-7.xml'),
-                   ('Digital Life', 'http://www.dnaindia.com/syndication/rss,catid-1089741.xml'),
+                   ('After Hours', 'http://www.dnaindia.com/syndication/rss,catid-7.xml')
                    ]
-    remove_tags = [{'id':['footer', 'lhs-col']}, {'class':['bottom', 'categoryHead',
-        'article_tools']}]
-    keep_only_tags = dict(id='middle-col')
-    remove_tags_after=[dict(attrs={'id':'story'})]
-    remove_attributes=['style']
-    no_stylesheets = True
+
+    
 
     def print_version(self, url):
         match = re.search(r'newsid=(\d+)', url)

recipes/toi.recipe

@@ -9,11 +9,16 @@ class TimesOfIndia(BasicNewsRecipe):
     max_articles_per_feed = 25
 
     no_stylesheets = True
-    keep_only_tags = [{'class':['maintable12', 'prttabl']}]
+    remove_attributes = ['style']
+    keep_only_tags = [
+            {'class':re.compile(r'maintable12|prttabl')},
+            {'id':['mod-article-header',
+                'mod-a-body-after-first-para', 'mod-a-body-first-para']},
+            ]
     remove_tags = [
-            dict(style=lambda x: x and 'float' in x),
-            {'class':['prvnxtbg', 'footbdrin', 'bcclftr']},
-    ]
+            {'class':re.compile('tabsintbgshow|prvnxtbg')},
+            {'id':['fbrecommend', 'relmaindiv']}
+            ]
 
     feeds          = [
 ('Top Stories',
@@ -41,6 +46,8 @@ class TimesOfIndia(BasicNewsRecipe):
 ]
 
     def get_article_url(self, article):
+        # Times of India sometimes serves an ad page instead of the article,
+        # this code, detects and circumvents that
         url = BasicNewsRecipe.get_article_url(self, article)
         if '/0Ltimesofindia' in url:
             url = url.partition('/0L')[-1]
@@ -61,6 +68,3 @@ class TimesOfIndia(BasicNewsRecipe):
 
         return url
 
-
-    def preprocess_html(self, soup):
-        return soup

src/calibre/ebooks/metadata/sources/amazon.py

@@ -73,6 +73,20 @@ class Worker(Thread): # Get details {{{
             8: ['août'],
             9: ['sept'],
             12: ['déc'],
+            },
+            'es': {
+                1: ['enero'],
+                2: ['febrero'],
+                3: ['marzo'],
+                4: ['abril'],
+                5: ['mayo'],
+                6: ['junio'],
+                7: ['julio'],
+                8: ['agosto'],
+                9: ['septiembre', 'setiembre'],
+                10: ['octubre'],
+                11: ['noviembre'],
+                12: ['diciembre'],
             },
                 'jp': {
             1: [u'1月'],
@@ -101,13 +115,16 @@ class Worker(Thread): # Get details {{{
                  text()="Dettagli prodotto" or \
                  text()="Product details" or \
                  text()="Détails sur le produit" or \
+                 text()="Detalles del producto" or \
                  text()="登録情報"]/../div[@class="content"]
             '''
+        # Editor: is for Spanish
         self.publisher_xpath = '''
             descendant::*[starts-with(text(), "Publisher:") or \
                     starts-with(text(), "Verlag:") or \
                     starts-with(text(), "Editore:") or \
                     starts-with(text(), "Editeur") or \
+                    starts-with(text(), "Editor:") or \
                     starts-with(text(), "出版社:")]
             '''
         self.language_xpath =    '''
@@ -116,12 +133,14 @@ class Worker(Thread): # Get details {{{
                 or text() = "Language" \
                 or text() = "Sprache:" \
                 or text() = "Lingua:" \
+                or text() = "Idioma:" \
                 or starts-with(text(), "Langue") \
                 or starts-with(text(), "言語") \
                 ]
             '''
+
         self.ratings_pat = re.compile(
-            r'([0-9.]+) ?(out of|von|su|étoiles sur|つ星のうち) ([\d\.]+)( (stars|Sternen|stelle)){0,1}')
+            r'([0-9.]+) ?(out of|von|su|étoiles sur|つ星のうち|de un máximo de) ([\d\.]+)( (stars|Sternen|stelle|estrellas)){0,1}')
 
         lm = {
                 'eng': ('English', 'Englisch'),
@@ -143,6 +162,7 @@ class Worker(Thread): # Get details {{{
         for i, vals in self.months.iteritems():
             for x in vals:
                 ans = ans.replace(x, self.english_months[i])
+        ans = ans.replace(' de ', ' ')
         return ans
 
     def run(self):
@@ -422,6 +442,7 @@ class Amazon(Source):
             'uk' : _('UK'),
             'it' : _('Italy'),
             'jp' : _('Japan'),
+            'es' : _('Spain'),
     }
 
     options = (
@@ -789,6 +810,16 @@ if __name__ == '__main__': # tests {{{
             ),
     ] # }}}
 
+    es_tests = [ # {{{
+            (
+                {'identifiers':{'isbn': '8483460831'}},
+                [title_test('Tiempos Interesantes',
+                    exact=True), authors_test(['Terry Pratchett'])
+                 ]
+
+            ),
+    ] # }}}
+
     jp_tests = [ # {{{
             ( # isbn -> title, authors
                 {'identifiers':{'isbn': '9784101302720' }},
@@ -804,6 +835,6 @@ if __name__ == '__main__': # tests {{{
     ] # }}}
 
     test_identify_plugin(Amazon.name, com_tests)
-    #test_identify_plugin(Amazon.name, jp_tests)
+    #test_identify_plugin(Amazon.name, es_tests)
 # }}}
 

src/calibre/ebooks/pdf/writer.py

@@ -173,6 +173,10 @@ class PDFWriter(QObject): # {{{
                 printer.setOutputFormat(QPrinter.NativeFormat)
             self.view.print_(printer)
             printer.abort()
+        else:
+            # The document is so corrupt that we can't render the page.
+            self.loop.exit(0)
+            raise Exception('Document cannot be rendered.')
         self._render_book()
 
     def _delete_tmpdir(self):
@@ -207,11 +211,14 @@ class PDFWriter(QObject): # {{{
         try:
             outPDF = PdfFileWriter(title=self.metadata.title, author=self.metadata.author)
             for item in self.combine_queue:
-                with open(item, 'rb') as item_stream:
-                    inputPDF = PdfFileReader(item_stream)
-                    for page in inputPDF.pages:
-                        outPDF.addPage(page)
-                        outPDF.write(self.out_stream)
+                # The input PDF stream must remain open until the final PDF
+                # is written to disk. PyPDF references pages added to the
+                # final PDF from the input PDF on disk. It does not store
+                # the pages in memory so we can't close the input PDF.
+                inputPDF = PdfFileReader(open(item, 'rb'))
+                for page in inputPDF.pages:
+                    outPDF.addPage(page)
+            outPDF.write(self.out_stream)
         finally:
             self._delete_tmpdir()
             self.loop.exit(0)