It's now possible to pickle a BeautifulSoup object no matter which

  tree builder was used to create it. However, the only tree builder
  that survives the pickling process is the HTMLParserTreeBuilder
  ('html.parser'). If you unpickle a BeautifulSoup object created with
  some other tree builder, soup.builder will be None. [bug=1231545]

1 files changed, 19 insertions, 0 deletions

diff --git a/bs4/testing.py b/bs4/testing.py
index 7232513..9e5e295 100644
--- a/bs4/testing.py
+++ b/bs4/testing.py
@@ -1,5 +1,6 @@
 """Helper classes for tests."""
 
+import pickle
 import copy
 import functools
 import unittest
@@ -64,6 +65,15 @@ class HTMLTreeBuilderSmokeTest(object):
     markup in these tests, there's not much room for interpretation.
     """
 
+    def test_pickle_and_unpickle_identity(self):
+        # Pickling a tree, then unpickling it, yields a tree identical
+        # to the original.
+        tree = self.soup("<a><b>foo</a>")
+        dumped = pickle.dumps(tree, 2)
+        loaded = pickle.loads(dumped)
+        self.assertEqual(loaded.__class__, BeautifulSoup)
+        self.assertEqual(loaded.decode(), tree.decode())
+
     def assertDoctypeHandled(self, doctype_fragment):
         """Assert that a given doctype string is handled correctly."""
         doctype_str, soup = self._document_with_doctype(doctype_fragment)
@@ -532,6 +542,15 @@ Hello, world!
 
 class XMLTreeBuilderSmokeTest(object):
 
+    def test_pickle_and_unpickle_identity(self):
+        # Pickling a tree, then unpickling it, yields a tree identical
+        # to the original.
+        tree = self.soup("<a><b>foo</a>")
+        dumped = pickle.dumps(tree, 2)
+        loaded = pickle.loads(dumped)
+        self.assertEqual(loaded.__class__, BeautifulSoup)
+        self.assertEqual(loaded.decode(), tree.decode())
+
     def test_docstring_generated(self):
         soup = self.soup("<root/>")
         self.assertEqual(