Implement #1769 (Remove first image in file during Conversion)

src/calibre/ebooks/epub/__init__.py

@@ -141,6 +141,10 @@ help on using this feature.
               action='store_true',
               help=_('Use the cover detected from the source file in preference '
                      'to the specified cover.'))
+    structure('remove_first_image', ['--remove-first-image'], default=False,
+              help=_('Remove the first image from the input ebook. Useful if '
+                     'the first image in the source file is a cover and you '
+                     'are specifying an external cover.'))
     structure('dont_split_on_page_breaks', ['--dont-split-on-page-breaks'], default=False,
               help=_('Turn off splitting at page breaks. Normally, input files '
                      'are automatically split at every page break into '

src/calibre/ebooks/epub/from_html.py

@@ -206,6 +206,13 @@ class HTMLProcessor(Processor, Rationalizer):
         #    self.convert_image(img)
         Processor.save(self)
         
+    def remove_first_image(self):
+        images = self.root.xpath('//img')
+        if images:
+            images[0].getparent().remove(images[0])
+            return True
+        return False
+        
     
             
 
@@ -227,10 +234,13 @@ def parse_content(filelist, opts, tdir):
     resource_map, stylesheets = {}, {}
     toc = TOC(base_path=tdir, type='root')
     stylesheet_map = {}
+    first_image_removed = False
     for htmlfile in filelist:
         logging.getLogger('html2epub').debug('Processing %s...'%htmlfile)
         hp = HTMLProcessor(htmlfile, opts, os.path.join(tdir, 'content'), 
                            resource_map, filelist, stylesheets)
+        if not first_image_removed and opts.remove_first_image:
+            first_image_removed = hp.remove_first_image()
         hp.populate_toc(toc)
         hp.save()
         stylesheet_map[os.path.basename(hp.save_path())] = \