From 83a836f9b5fa14c7a567185fe626073be85be21c Mon Sep 17 00:00:00 2001
From: xenofem <xenofem@xeno.science>
Date: Sun, 1 Sep 2024 13:13:14 -0400
Subject: [PATCH] pymupdf TextPage.extractBLOCKS() no longer includes images by
 default

---
 dlibrary/dlibrary.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/dlibrary/dlibrary.py b/dlibrary/dlibrary.py
index 049e583..7b97233 100755
--- a/dlibrary/dlibrary.py
+++ b/dlibrary/dlibrary.py
@@ -697,7 +697,7 @@ def block_relevant(block):
     return block_is_image(block) or not IRRELEVANT_PDF_BLOCK_REGEX.search(block_text(block))
 
 def relevant_blocks(page):
-    blocks = page.get_text('blocks')
+    blocks = page.get_text('blocks', flags=(fitz.TEXTFLAGS_BLOCKS | fitz.TEXT_PRESERVE_IMAGES))
     return [block for block in blocks if block_relevant(block)]
 
 def is_single_image(page):