Issue a warning if characters were replaced with REPLACEMENT CHARACTER during Unicode conversion.

1 files changed, 5 insertions, 0 deletions

diff --git a/bs4/dammit.py b/bs4/dammit.py
index 76ac9ce..a35c213 100644
--- a/bs4/dammit.py
+++ b/bs4/dammit.py
@@ -9,6 +9,7 @@ encoding; that's the tree builder's job.
 import codecs
 from htmlentitydefs import codepoint2name
 import re
+import warnings
 
 # Autodetects character encodings. Very useful.
 # Download from http://chardet.feedparser.org/
@@ -212,6 +213,10 @@ class UnicodeDammit:
                 if proposed_encoding != "ascii":
                     u = self._convert_from(proposed_encoding, "replace")
                 if u is not None:
+                    warnings.warn(
+                        UnicodeWarning(
+                            "Some characters could not be decoded, and were "
+                            "replaced with REPLACEMENT CHARACTER."))
                     self.contains_replacement_characters = True
                     break