Fix #239

camelot/parsers/base.py

@@ -13,7 +13,8 @@ class BaseParser(object):
         self.layout_kwargs = layout_kwargs
         self.layout, self.dimensions = get_page_layout(
             filename, **layout_kwargs)
-        self.horizontal_text = get_text_objects(self.layout, ltype="lh")
-        self.vertical_text = get_text_objects(self.layout, ltype="lv")
+        self.images = get_text_objects(self.layout, ltype='image')
+        self.horizontal_text = get_text_objects(self.layout, ltype='horizontal_text')
+        self.vertical_text = get_text_objects(self.layout, ltype='vertical_text')
         self.pdf_width, self.pdf_height = self.dimensions
         self.rootname, __ = os.path.splitext(self.filename)

camelot/parsers/lattice.py

@@ -356,8 +356,12 @@ class Lattice(BaseParser):
             logger.info('Processing {}'.format(os.path.basename(self.rootname)))
 
         if not self.horizontal_text:
-            warnings.warn("No tables found on {}".format(
-                os.path.basename(self.rootname)))
+            if self.images:
+                warnings.warn('The page is image-based, Camelot only works with'
+                              ' text-based PDF pages.'.format(os.path.basename(self.rootname)))
+            else:
+                warnings.warn('No tables found on {}'.format(
+                    os.path.basename(self.rootname)))
             return []
 
         self._generate_image()

camelot/parsers/stream.py

@@ -395,8 +395,12 @@ class Stream(BaseParser):
             logger.info('Processing {}'.format(os.path.basename(self.rootname)))
 
         if not self.horizontal_text:
-            warnings.warn("No tables found on {}".format(
-                os.path.basename(self.rootname)))
+            if self.images:
+                warnings.warn('The page is image-based, Camelot only works with'
+                              ' text-based PDF pages.'.format(os.path.basename(self.rootname)))
+            else:
+                warnings.warn('No tables found on {}'.format(
+                    os.path.basename(self.rootname)))
             return []
 
         self._generate_table_bbox()