Merge from trunk

Changelog.yaml

@@ -44,7 +44,7 @@
 
     - title: "MOBI Output: Fix a memory leak and a crash in the palmdoc compression routine"
 
-    - title: "Metadata download: Fix a regressiont at resulted in a failed download for some books"
+    - title: "Metadata download: Fix a regression that resulted in a failed download for some books"
 
   new recipes:
     - title: "Foreign Policy and Alo!"

resources/recipes/big_oven.recipe

@@ -0,0 +1,64 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class BigOven(BasicNewsRecipe):
+    title               = 'BigOven'
+    __author__          = 'Starson17'
+    description         = 'Recipes for the Foodie in us all. Registration is free. A fake username and password just gives smaller photos.'
+    language            = 'en'
+    category            = 'news, food, recipes, gourmet'
+    publisher           = 'Starson17'
+    use_embedded_content= False
+    no_stylesheets      = True
+    oldest_article      = 24
+    remove_javascript   = True
+    remove_empty_feeds    = True
+    cover_url           = 'http://www.software.com/images/products/BigOven%20Logo_177_216.JPG'
+    max_articles_per_feed = 30
+    needs_subscription = True
+
+    conversion_options = {'linearize_tables'  : True
+                        , 'comment'           : description
+                        , 'tags'              : category
+                        , 'publisher'         : publisher
+                        , 'language'          : language
+                        }
+
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        if self.username is not None and self.password is not None:
+            br.open('http://www.bigoven.com/')
+            br.select_form(name='form1')
+            br['TopMenu_bo1$email']  = self.username
+            br['TopMenu_bo1$password'] = self.password
+            br.submit()
+        return br
+
+    remove_attributes = ['style', 'font']
+
+    keep_only_tags     = [dict(name='h1')
+                          ,dict(name='div', attrs={'class':'img'})
+                          ,dict(name='div', attrs={'id':'intro'})
+                          ]
+
+    remove_tags = [dict(name='div', attrs={'style':["overflow: visible;"]})
+                   ,dict(name='div', attrs={'class':['ctas']})
+                   #,dict(name='a', attrs={'class':['edit']})
+                   ,dict(name='p', attrs={'class':['byline']})
+                   ]
+
+    feeds = [(u'4 & 5 Star Rated Recipes', u'http://feeds.feedburner.com/Bigovencom-RecipeRaves?format=xml')]
+
+    def preprocess_html(self, soup):
+        for tag in soup.findAll(name='a', attrs={'class':['edit']}):
+          tag.parent.extract()
+        for tag in soup.findAll(name='a', attrs={'class':['deflink']}):
+          tag.replaceWith(tag.string)
+        return soup
+
+    extra_css = '''
+                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:medium;}
+                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+		            '''
+

resources/recipes/editor_and_publisher.recipe

@@ -1,14 +1,29 @@
-import re
+#!/usr/bin/env python
+__license__ = 'GPL v3'
+__copyright__ = '2010 elsuave'
+
 from calibre.web.feeds.news import BasicNewsRecipe
 class EandP(BasicNewsRecipe):
     title              = u'Editor and Publisher'
-    __author__         = u'Xanthan Gum'
+    __author__         = u'elsuave (modified from Xanthan Gum)'
     description        = 'News about newspapers and journalism.'
+    publisher             = 'Editor and Publisher'
+    category              = 'news, journalism, industry'
     language = 'en'
-    no_stylesheets     = True
+    max_articles_per_feed = 25
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf8'
+    cover_url             = 'http://www.editorandpublisher.com/images/EP_main_logo.gif'
+    remove_javascript     = True
 
-    oldest_article = 7
+    html2lrf_options = [
-    max_articles_per_feed = 100
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
 
     # Font formatting code borrowed from kwetal
 
@@ -18,17 +33,21 @@ class EandP(BasicNewsRecipe):
                  h2{font-size: large;}
                 '''
 
-    # Delete everything before the article
+    # Keep only div:itemmgap
 
-    remove_tags_before = dict(name='font', attrs={'class':'titlebar_black'})
+    keep_only_tags = [
+                          dict(name='div', attrs={'class':'itemmgap'})
+                          ]
 
-    # Delete everything after the article
+    # Remove commenting/social media lins
 
-    preprocess_regexps = [(re.compile(r'<!--endclickprintinclude-->.*</body>', re.DOTALL|re.IGNORECASE),
+    remove_tags_after = [dict(name='div', attrs={'class':'clear'})]
-                           lambda match: '</body>'),]
+
+
+    feeds = [(u'Breaking News', u'http://www.editorandpublisher.com/GenerateRssFeed.aspx'),
+             (u'Business News', u'http://www.editorandpublisher.com/GenerateRssFeed.aspx?CategoryId=2'),
+             (u'Ad/Circ News', u'http://www.editorandpublisher.com/GenerateRssFeed.aspx?CategoryId=3'),
+             (u'Newsroom', u'http://www.editorandpublisher.com/GenerateRssFeed.aspx?CategoryId=4'),
+             (u'Technology News', u'http://www.editorandpublisher.com/GenerateRssFeed.aspx?CategoryId=5'),
+             (u'Syndicates News', u'http://www.editorandpublisher.com/GenerateRssFeed.aspx?CategoryId=7')]
 
-    feeds = [(u'Breaking News', u'http://feeds.feedburner.com/EditorAndPublisher-BreakingNews'),
-             (u'Business News', u'http://feeds.feedburner.com/EditorAndPublisher-BusinessNews'),
-             (u'Newsroom', u'http://feeds.feedburner.com/EditorAndPublisher-Newsroom'),
-             (u'Technology News', u'http://feeds.feedburner.com/EditorAndPublisher-Technology'),
-             (u'Syndicates News', u'http://feeds.feedburner.com/EditorAndPublisher-Syndicates')]

resources/recipes/estadao.recipe

@@ -1,7 +1,7 @@
 #!/usr/bin/env  python
 
 __license__   = 'GPL v3'
-__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2010, elsuave'
 '''
 estadao.com.br
 '''
@@ -10,12 +10,12 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class Estadao(BasicNewsRecipe):
     title                 = 'O Estado de S. Paulo'
-    __author__            = 'Darko Miletic'
+    __author__            = 'elsuave (modified from Darko Miletic)'
     description           = 'News from Brasil in Portuguese'
     publisher             = 'O Estado de S. Paulo'
     category              = 'news, politics, Brasil'
     oldest_article        = 2
-    max_articles_per_feed = 100
+    max_articles_per_feed = 25
     no_stylesheets        = True
     use_embedded_content  = False
     encoding              = 'utf8'
@@ -30,13 +30,14 @@ class Estadao(BasicNewsRecipe):
 
     html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
 
-    keep_only_tags = [dict(name='div', attrs={'id':'c1'})]
+    keep_only_tags = [
+                          dict(name='div', attrs={'class':['bb-md-noticia','c5']})
+                     ]
 
     remove_tags = [
                      dict(name=['script','object','form','ul'])
-                    ,dict(name='div', attrs={'id':['votacao','estadaohoje']})
+                    ,dict(name='div', attrs={'class':['fnt2 Color_04 bold','right fnt2 innerTop15 dvTmFont','™_01 right outerLeft15','tituloBox','tags']})
-                    ,dict(name='p', attrs={'id':'ctrl_texto'})
+                    ,dict(name='div', attrs={'id':['bb-md-noticia-subcom']})
-                    ,dict(name='p', attrs={'class':'texto'})
                   ]
 
     feeds = [
@@ -51,13 +52,12 @@ class Estadao(BasicNewsRecipe):
               ,(u'Vida &', u'http://www.estadao.com.br/rss/vidae.xml')
             ]
 
-    def preprocess_html(self, soup):
+
-        ifr = soup.find('iframe')
-        if ifr:
-           ifr.extract()
-        for item in soup.findAll(style=True):
-            del item['style']
-        return soup
 
     language = 'pt'
 
+    def get_article_url(self, article):
+        url = BasicNewsRecipe.get_article_url(self, article)
+        if '/Multimidia/' not in url:
+            return url
+

src/calibre/ebooks/metadata/fetch.py

@@ -351,9 +351,13 @@ def search(title=None, author=None, publisher=None, isbn=None, isbndb_key=None,
     if len(results) > 1:
         if not results[0].comments or len(results[0].comments) == 0:
             for r in results[1:]:
-                if title.lower() == r.title[:len(title)].lower() and r.comments and len(r.comments):
+                try:
-                    results[0].comments = r.comments
+                    if title and title.lower() == r.title[:len(title)].lower() \
-                    break
+                            and r.comments and len(r.comments):
+                        results[0].comments = r.comments
+                        break
+                except:
+                    pass
         # Find a pubdate
         pubdate = None
         for r in results:

src/calibre/gui2/actions.py

@@ -323,7 +323,6 @@ class AddAction(object): # {{{
                 accept = True
         if accept:
             event.accept()
-            self.cover_cache.refresh([cid])
             self.library_view.model().current_changed(current_idx, current_idx)
 
     def __add_filesystem_book(self, paths, allow_device=True):

src/calibre/gui2/cover_flow.py

@@ -115,6 +115,7 @@ class CoverFlowMixin(object):
                     self.sync_cf_to_listview)
             self.db_images = DatabaseImages(self.library_view.model())
             self.cover_flow.setImages(self.db_images)
+            self.cover_flow.itemActivated.connect(self.view_specific_book)
         else:
             self.cover_flow = QLabel('<p>'+_('Cover browser could not be loaded')
                     +'<br>'+pictureflowerror)

src/calibre/gui2/pictureflow/pictureflow.cpp

@@ -579,12 +579,10 @@ void PictureFlowPrivate::resetSlides()
 
 static QImage prepareSurface(QImage img, int w, int h)
 {
-  Qt::TransformationMode mode = Qt::SmoothTransformation;
+  img = img.scaled(w, h, Qt::IgnoreAspectRatio, Qt::SmoothTransformation);
-  img = img.scaled(w, h, Qt::IgnoreAspectRatio, mode);
 
   // slightly larger, to accommodate for the reflection
   int hs = int(h * REFLECTION_FACTOR);
-  int hofs = 0;
 
   // offscreen buffer: black is sweet
   QImage result(hs, w, QImage::Format_RGB16);  
@@ -595,21 +593,20 @@ static QImage prepareSurface(QImage img, int w, int h)
   // (and much better and faster to work row-wise, i.e in one scanline)
   for(int x = 0; x < w; x++)
     for(int y = 0; y < h; y++)
-      result.setPixel(hofs + y, x, img.pixel(x, y));
+      result.setPixel(y, x, img.pixel(x, y));
 
   // create the reflection
-  int ht = hs - h - hofs;
+  int ht = hs - h;
-  int hte = ht;
   for(int x = 0; x < w; x++)
     for(int y = 0; y < ht; y++)
     {
       QRgb color = img.pixel(x, img.height()-y-1);
       //QRgb565 color = img.scanLine(img.height()-y-1) + x*sizeof(QRgb565); //img.pixel(x, img.height()-y-1);
       int a = qAlpha(color);
-      int r = qRed(color)   * a / 256 * (hte - y) / hte * 3/5;
+      int r = qRed(color)   * a / 256 * (ht - y) / ht * 3/5;
-      int g = qGreen(color) * a / 256 * (hte - y) / hte * 3/5;
+      int g = qGreen(color) * a / 256 * (ht - y) / ht * 3/5;
-      int b = qBlue(color)  * a / 256 * (hte - y) / hte * 3/5;
+      int b = qBlue(color)  * a / 256 * (ht - y) / ht * 3/5;
-      result.setPixel(h+hofs+y, x, qRgb(r, g, b));
+      result.setPixel(h+y, x, qRgb(r, g, b));
     }
 
   return result;
@@ -798,12 +795,20 @@ QRect PictureFlowPrivate::renderCenterSlide(const SlideInfo &slide) {
   int sw = src->height();
   int sh = src->width();
   int h = buffer.height();
-  QRect rect(buffer.width()/2 - sw/2, 0, sw, h-1);
+  int srcoff = 0;
-  int left = rect.left();
+  int left = buffer.width()/2 - sw/2;
+  if (left < 0) {
+      srcoff = -left;
+      sw += left;
+      left = 0;
+  }
+  QRect rect(left, 0, sw, h-1);
+  int xcon = MIN(h-1, sh-1);
+  int ycon = MIN(sw, buffer.width() - left);
 
-  for(int x = 0; x < MIN(h-1, sh-1); x++)
+  for(int x = 0; x < xcon; x++)
-    for(int y = 0; y < sw; y++)
+      for(int y = 0; y < ycon; y++)
-      buffer.setPixel(left + y, 1+x, src->pixel(x, y));
+          buffer.setPixel(left + y, 1+x, src->pixel(x, srcoff+y));
 
   return rect;
 }

src/calibre/web/fetch/simple.py

@@ -238,7 +238,7 @@ class RecursiveFetcher(object):
         soup = BeautifulSoup(u'<a href="'+url+'" />')
         self.log.debug('Downloading')
         res = self.process_links(soup, url, 0, into_dir='')
-        self.log.debug('%s saved to %s'%( url, res))
+        self.log.debug(url, 'saved to', res)
         return res
 
     def is_link_ok(self, url):
@@ -281,7 +281,7 @@ class RecursiveFetcher(object):
                 try:
                     data = self.fetch_url(iurl)
                 except Exception:
-                    self.log.exception('Could not fetch stylesheet %s'% iurl)
+                    self.log.exception('Could not fetch stylesheet ', iurl)
                     continue
                 stylepath = os.path.join(diskpath, 'style'+str(c)+'.css')
                 with self.stylemap_lock:
@@ -304,7 +304,7 @@ class RecursiveFetcher(object):
                         try:
                             data = self.fetch_url(iurl)
                         except Exception:
-                            self.log.exception('Could not fetch stylesheet %s'% iurl)
+                            self.log.exception('Could not fetch stylesheet ', iurl)
                             continue
                         c += 1
                         stylepath = os.path.join(diskpath, 'style'+str(c)+'.css')
@@ -337,7 +337,7 @@ class RecursiveFetcher(object):
                     # Skip empty GIF files as PIL errors on them anyway
                     continue
             except Exception:
-                self.log.exception('Could not fetch image %s'% iurl)
+                self.log.exception('Could not fetch image ', iurl)
                 continue
             c += 1
             fname = ascii_filename('img'+str(c))
@@ -423,7 +423,7 @@ class RecursiveFetcher(object):
                     newbaseurl = dsrc.newurl
                     if len(dsrc) == 0 or \
                        len(re.compile('<!--.*?-->', re.DOTALL).sub('', dsrc).strip()) == 0:
-                        raise ValueError('No content at URL %s'%iurl)
+                        raise ValueError('No content at URL %r'%iurl)
                     if callable(self.encoding):
                         dsrc = self.encoding(dsrc)
                     elif self.encoding is not None: