Use optipng to optimise document thumbnails

src/documents/consumer.py

@@ -149,7 +149,7 @@ class Consumer:
         parsed_document = parser_class(doc)
 
         try:
-            thumbnail = parsed_document.get_thumbnail()
+            thumbnail = parsed_document.get_optimised_thumbnail()
             date = parsed_document.get_date()
             document = self._store(
                 parsed_document.get_text(),

src/documents/parsers.py

@@ -2,6 +2,7 @@ import logging
 import os
 import re
 import shutil
+import subprocess
 import tempfile
 
 import dateparser
@@ -36,6 +37,7 @@ class DocumentParser:
 
     SCRATCH = settings.SCRATCH_DIR
     DATE_ORDER = settings.DATE_ORDER
+    OPTIPNG = settings.OPTIPNG_BINARY
 
     def __init__(self, path):
         self.document_path = path
@@ -49,6 +51,19 @@ class DocumentParser:
         """
         raise NotImplementedError()
 
+    def optimise_thumbnail(self, in_path):
+
+        out_path = os.path.join(self.tempdir, "optipng.png")
+
+        args = (self.OPTIPNG, "-o5", in_path, "-out", out_path)
+        if not subprocess.Popen(args).wait() == 0:
+            raise ParseError("Optipng failed at {}".format(args))
+
+        return out_path
+
+    def get_optimised_thumbnail(self):
+        return self.optimise_thumbnail(self.get_thumbnail())
+
     def get_text(self):
         """
         Returns the text from the document and only the text.