Merge from trunk

resources/recipes/el_cultural.recipe

@@ -0,0 +1,86 @@
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class RevistaElCultural(BasicNewsRecipe):
+
+    title       = 'Revista El Cultural'
+    __author__  = 'Jefferson Frantz'
+    description = 'Revista de cultura'
+    timefmt = ' [%d %b, %Y]'
+    language = 'es'
+
+    no_stylesheets = True
+    remove_javascript = True
+
+    extra_css              = 'h1{ font-family: sans-serif; font-size: large; font-weight: bolder; text-align: justify } h2{ font-family: sans-serif; font-size: small; font-weight: 500; text-align: justify } h3{ font-family: sans-serif; font-size: small; font-weight: 500; text-align: justify } h4{ font-family: sans-serif; font-weight: lighter; font-size: medium; font-style: italic; text-align: justify } .rtsArticuloFirma{ font-family: sans-serif; font-size: small; text-align: justify } .column span-13 last{ font-family: sans-serif; font-size: medium; text-align: justify } .rtsImgArticulo{font-family: serif; font-size: small; color: #000000; text-align: justify}'
+
+
+    def preprocess_html(self, soup):
+            for item in soup.findAll(style=True):
+               del item['style']
+
+            return soup
+
+    keep_only_tags = [dict(name='div', attrs={'class':['column span-13 last']}),dict(name='div', attrs={'class':['rtsImgArticulo']})]
+
+    remove_tags        = [
+                             dict(name=['object','link','script','ul'])
+                            ,dict(name='div', attrs={'class':['rtsRating']})
+
+                         ]
+
+
+    #TO GET ARTICLES IN SECTION
+    def ec_parse_section(self, url, titleSection):
+            print 'Section: '+ titleSection
+            soup = self.index_to_soup(url)
+            div = soup.find(attrs={'id':'gallery'})
+            current_articles = []
+
+            for a in div.findAllNext('a', href=True):
+                    if a is None:
+                        continue
+                    title = self.tag_to_string(a)
+
+                    url = a.get('href', False)
+                    if not url or not title:
+                        continue
+
+                    if not url.startswith('/version_papel/'+titleSection+'/'):
+                        if len(current_articles) > 0 and not url.startswith('/secciones/'):
+                            break
+                        continue
+
+                    if url.startswith('/version_papel/'+titleSection+'/'):
+                         url = 'http://www.elcultural.es'+url
+
+                    self.log('\t\tFound article:', title[0:title.find("|")-1])
+                    self.log('\t\t\t', url)
+                    current_articles.append({'title': title[0:title.find("|")-1], 'url':url,
+                        'description':'', 'date':''})
+
+            return current_articles
+
+
+    # To GET SECTIONS
+    def parse_index(self):
+            feeds = []
+            for title, url in [
+                ('LETRAS',
+                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
+                ('ARTE',
+                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
+                ('CINE',
+                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
+                ('CIENCIA',
+                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
+##                ('OPINION',
+##                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
+                ('ESCENARIOS',
+                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
+             ]:
+               articles = self.ec_parse_section(url,title)
+               if articles:
+                   feeds.append((title, articles))
+
+
+            return feeds

src/calibre/ebooks/metadata/isbndb.py

@@ -45,37 +45,34 @@ def fetch_metadata(url, max=100, timeout=5.):
 class ISBNDBMetadata(Metadata):
 
     def __init__(self, book):
-        Metadata.__init__(self, None, [])
+        Metadata.__init__(self, None)
-        self.getmetadata(book)
+
+        def tostring(e):
+            if not hasattr(e, 'string'):
+                return None
+            ans = e.string
+            if ans is not None:
+                ans = unicode(ans).strip()
+            if not ans:
+                ans = None
+            return ans
 
-    def tostring(self, e):
-        if not hasattr(e, 'string'):
-            return None
-        ans = e.string
-        if ans is not None:
-            ans = unicode(ans).strip()
-        if not ans:
-            ans = None
-        return ans
-        
-    def getmetadata(self, book):
         self.isbn = unicode(book.get('isbn13', book.get('isbn')))
-        temptitle = self.tostring(book.find('titlelong'))
+        title = tostring(book.find('titlelong'))
-        if not temptitle:
+        if not title:
-            temptitle = self.tostring(book.find('title'))
+            title = tostring(book.find('title'))
-        if temptitle:            
+        self.title = title
-            self.title = unicode(temptitle).strip()
+        self.title = unicode(self.title).strip()
-        else:
+        authors = []
-            self.title = _('Unknown')
+        au = tostring(book.find('authorstext'))
-        self.authors = []
-        au = self.tostring(book.find('authorstext'))
         if au:
             au = au.strip()
             temp = au.split(',')
             for au in temp:
                 if not au: continue
-                self.authors.extend([a.strip() for a in au.split('&')])
+                authors.extend([a.strip() for a in au.split('&')])
-
+        if authors:
+            self.authors = authors
         try:
             self.author_sort = self.tostring(book.find('authors').find('person'))
             if self.authors and self.author_sort == self.authors[0]:

src/calibre/gui2/dialogs/metadata_single.py

@@ -25,7 +25,7 @@ from calibre.ebooks.metadata.covers import download_cover
 from calibre.ebooks.metadata.meta import get_metadata
 from calibre.ebooks.metadata import MetaInformation
 from calibre.utils.config import prefs, tweaks
-from calibre.utils.date import qt_to_dt, local_tz, utcfromtimestamp
+from calibre.utils.date import qt_to_dt, local_tz, utcfromtimestamp, utc_tz
 from calibre.customize.ui import run_plugins_on_import, get_isbndb_key
 from calibre.gui2.preferences.social import SocialMetadata
 from calibre.gui2.custom_column_widgets import populate_metadata_page
@@ -434,7 +434,7 @@ class MetadataSingleDialog(ResizableDialog, Ui_MetadataSingleDialog):
         self.pubdate.setDate(QDate(pubdate.year, pubdate.month,
             pubdate.day))
         timestamp = db.timestamp(self.id, index_is_id=True)
-        self.orig_timestamp = timestamp
+        self.orig_timestamp = timestamp.astimezone(utc_tz)
         self.date.setDate(QDate(timestamp.year, timestamp.month,
             timestamp.day))
 

src/calibre/manual/index.rst

@@ -17,10 +17,10 @@ To get started with more advanced usage, you should read about the :ref:`Graphic
 
 You will find the list of :ref:`Frequently Asked Questions <faq>` useful as well. 
 
-.. only:: html and online
+.. only:: online
+    
+    An e-book version of this User Manual is available in `EPUB format <calibre.epub>`_. 
     
-    An e-book version of this User Manual is available in `EPUB format <calibre.epub>`_. Because the User Manual uses advanced formatting, it is only suitable for use with the |app| e-book viewer.
-
 Sections
 ------------
 

src/calibre/utils/magick/__init__.py

@@ -109,6 +109,13 @@ class Image(_magick.Image): # {{{
         return _magick.Image.load(self, bytes(data))
 
     def open(self, path_or_file):
+        if not hasattr(path_or_file, 'read') and \
+            path_or_file.lower().endswith('.wmf'):
+            # Special handling for WMF files as ImageMagick seems
+            # to hand while reading them from a blob on linux
+            if isinstance(path_or_file, unicode):
+                path_or_file = path_or_file.encode(filesystem_encoding)
+            return _magick.Image.read(self, path_or_file)
         data = path_or_file
         if hasattr(data, 'read'):
             data = data.read()

src/calibre/utils/magick/magick.c

@@ -414,6 +414,24 @@ magick_Image_load(magick_Image *self, PyObject *args, PyObject *kwargs) {
 
 // }}}
 
+// Image.load {{{
+static PyObject *
+magick_Image_read(magick_Image *self, PyObject *args, PyObject *kwargs) {
+    const char *data;
+    MagickBooleanType res;
+    
+    if (!PyArg_ParseTuple(args, "s", &data)) return NULL;
+
+    res = MagickReadImage(self->wand, data);
+
+    if (!res)
+        return magick_set_exception(self->wand);
+
+    Py_RETURN_NONE;
+}
+
+// }}}
+
 // Image.create_canvas {{{
 static PyObject *
 magick_Image_create_canvas(magick_Image *self, PyObject *args, PyObject *kwargs)
@@ -873,6 +891,10 @@ static PyMethodDef magick_Image_methods[] = {
      "Load an image from a byte buffer (string)"
     },
 
+    {"read", (PyCFunction)magick_Image_read, METH_VARARGS,
+     "Read image from path. Path must be a bytestring in the filesystem encoding"
+    },
+
     {"export", (PyCFunction)magick_Image_export, METH_VARARGS,
      "export(format) -> bytestring\n\n Export the image as the specified format"
     },