text_extractor: make decoding more robust

pypdfium2-team · May 31, 2022 · ff13d2f · ff13d2f
1 parent 62f4386
commit ff13d2f
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/src/pypdfium2/_helpers/text_extractor.py b/src/pypdfium2/_helpers/text_extractor.py
@@ -52,7 +52,7 @@ def get_text(self, left=0, bottom=0, right=0, top=0):
 
         c_array = (ctypes.c_ushort * (n_chars+1))()
         pdfium.FPDFText_GetBoundedText(*args, ctypes.cast(c_array, ctypes.POINTER(ctypes.c_ushort)), n_chars)
-        text = bytes(c_array).decode("utf-16-le")[:-1]
+        text = bytes(c_array).decode("utf-16-le", errors="ignore")[:-1]
 
         return text