Beautiful Soup will issue a warning if instead of markup you pass it

  a URL or the name of a file on disk (a common beginner mistake).

2 files changed, 45 insertions, 2 deletions

diff --git a/bs4/__init__.py b/bs4/__init__.py
index 7b5964a..0dded3a 100644
--- a/bs4/__init__.py
+++ b/bs4/__init__.py
@@ -17,12 +17,13 @@ http://www.crummy.com/software/BeautifulSoup/bs4/doc/
 """
 
 __author__ = "Leonard Richardson (leonardr@segfault.org)"
-__version__ = "4.2.1"
+__version__ = "4.3.0"
 __copyright__ = "Copyright (c) 2004-2013 Leonard Richardson"
 __license__ = "MIT"
 
 __all__ = ['BeautifulSoup']
 
+import os
 import re
 import warnings
 
@@ -162,6 +163,22 @@ class BeautifulSoup(Tag):
 
         if hasattr(markup, 'read'):        # It's a file-type object.
             markup = markup.read()
+        elif len(markup) <= 256:
+            # Print out warnings for a couple beginner problems
+            # involving passing non-markup to Beautiful Soup.
+            # Beautiful Soup will still parse the input as markup, 
+            # just in case that's what the user really wants.
+            if os.path.exists(markup):
+                warnings.warn(
+                    '"%s" looks like a filename, not markup. You should probably open a filehandle and pass the filehandle into Beautiful Soup.' % markup)
+            if markup[:5] == "http:" or markup[:6] == "https:":
+                # TODO: This is ugly but I couldn't get it to work in
+                # Python 3 otherwise.
+                if ((isinstance(markup, bytes) and not b' ' in markup)
+                    or (isinstance(markup, unicode) and not u' ' in markup)):
+                    warnings.warn(
+                        '"%s" looks like a URL. Beautiful Soup is not an HTTP client. You should probably use an HTTP client to get the document behind the URL, and feed that document to Beautiful Soup.' % markup)
+
         for (self.markup, self.original_encoding, self.declared_html_encoding,
          self.contains_replacement_characters) in (
             self.builder.prepare_markup(markup, from_encoding)):
diff --git a/bs4/tests/test_soup.py b/bs4/tests/test_soup.py
index 0b69318..860b17b 100644
--- a/bs4/tests/test_soup.py
+++ b/bs4/tests/test_soup.py
@@ -4,6 +4,8 @@
 import logging
 import unittest
 import sys
+import tempfile
+
 from bs4 import (
     BeautifulSoup,
     BeautifulStoneSoup,
@@ -64,7 +66,31 @@ class TestDeprecatedConstructorArguments(SoupTest):
         with warnings.catch_warnings(record=True) as w:
             soup = BeautifulStoneSoup("<markup>")
             self.assertTrue(isinstance(soup, BeautifulSoup))
-            self.assertTrue("BeautifulStoneSoup class is deprecated")
+            self.assertTrue("BeautifulStoneSoup class is deprecated" in str(w[0].message))
+
+class TestWarnings(SoupTest):
+
+    def test_disk_file_warning(self):
+        filehandle = tempfile.NamedTemporaryFile()
+        filename = filehandle.name
+        try:
+            with warnings.catch_warnings(record=True) as w:
+                soup = self.soup(filename)
+            msg = str(w[0].message)
+            self.assertTrue("looks like a filename" in msg)
+        finally:
+            filehandle.close()
+
+    def test_url_warning(self):
+        with warnings.catch_warnings(record=True) as w:
+            soup = self.soup("http://www.crummy.com/")
+        msg = str(w[0].message)
+        self.assertTrue("looks like a URL" in msg)
+
+        with warnings.catch_warnings(record=True) as w:
+            soup = self.soup("http://www.crummy.com/ is great")
+        self.assertEqual(0, len(w))
+
 
 class TestSelectiveParsing(SoupTest):