Merge pull request #8030 from cpcloud/read-html-py3-encoding-7927

BUG: fix py3 read_html bytes input

Author: cpcloud

doc/source/v0.15.0.txt

@@ -533,7 +533,11 @@ Bug Fixes
 
 
 
+- Bug in installation where ``html_encoding/*.html`` wasn't installed and
+  therefore some tests were not running correctly (:issue:`7927`).
 
+- Bug in ``read_html`` where ``bytes`` objects were not tested for in
+  ``_read`` (:issue:`7927`).
 
 
 

pandas/io/html.py

@@ -15,8 +15,8 @@
 
 from pandas.io.common import _is_url, urlopen, parse_url
 from pandas.io.parsers import TextParser
-from pandas.compat import (lrange, lmap, u, string_types, iteritems, text_type,
-                           raise_with_traceback)
+from pandas.compat import (lrange, lmap, u, string_types, iteritems,
+                           raise_with_traceback, binary_type)
 from pandas.core import common as com
 from pandas import Series
 
@@ -51,6 +51,9 @@
 _RE_WHITESPACE = re.compile(r'[\r\n]+|\s{2,}')
 
 
+char_types = string_types + (binary_type,)
+
+
 def _remove_whitespace(s, regex=_RE_WHITESPACE):
     """Replace extra whitespace inside of a string with a single space.
 
@@ -114,13 +117,13 @@ def _read(obj):
             text = url.read()
     elif hasattr(obj, 'read'):
         text = obj.read()
-    elif isinstance(obj, string_types):
+    elif isinstance(obj, char_types):
         text = obj
         try:
             if os.path.isfile(text):
                 with open(text, 'rb') as f:
                     return f.read()
-        except TypeError:
+        except (TypeError, ValueError):
             pass
     else:
         raise TypeError("Cannot read object of type %r" % type(obj).__name__)

pandas/io/tests/test_html.py

@@ -622,6 +622,7 @@ def read_string(self, f, encoding):
             return self.read_html(fobj.read(), encoding=encoding, index_col=0)
 
     def test_encode(self):
+        assert self.files, 'no files read from the data folder'
         for f in self.files:
             _, encoding = _lang_enc(f)
             from_string = self.read_string(f, encoding).pop()

setup.py

@@ -583,6 +583,7 @@ def pxd(name):
                                   'tests/data/*.xlsm',
                                   'tests/data/*.table',
                                   'tests/data/*.html',
+                                  'tests/data/html_encoding/*.html',
                                   'tests/test_json/data/*.json'],
                     'pandas.tools': ['tests/*.csv'],
                     'pandas.tests': ['data/*.pickle',