Merge pull request #5 from msufa/update-soup

Update beautifulsoup4 and remove workarounds

setup.py

@@ -1,7 +1,7 @@
 from setuptools import setup
 
 install_requires = (
-    'beautifulsoup4==4.5.1',
+    'beautifulsoup4==4.6.3',
 )
 
 tests_require = (

test/test_injector.py

@@ -20,14 +20,3 @@ def test_injection(tmpdir):
             found = soup.find_all("script")
             assert found
             assert tracking_tag in found[0].text
-
-
-def test_removing_stray_tags():
-    with open(os.path.join(os.path.dirname(__file__), "data/test.html"), "r") as infile:
-        soup = BeautifulSoup(infile, "html.parser")
-        embed_tag = soup.new_tag("embed")
-        soup.body.append(embed_tag)
-
-        output = soup.prettify()
-        assert "</embed>" in output
-        assert "</embed>" not in injector._remove_stray_tags(output)

tridinjector/injector.py

@@ -26,16 +26,7 @@ def _inject_tracking_id(tracking_id, soup):
 
 def _write_output(soup, output_filename):
     with open(output_filename, 'w') as outfile:
-        outfile.write(_remove_stray_tags(soup.prettify()).encode('utf-8'))
-
-
-def _remove_stray_tags(output):
-    """
-    BeautifulSoup's parser is sometimes to eager to close tags, which produces output like
-    <embed></embed>, which some HTML validators fail to accept. This function removes
-    the stray tags if found.
-    """
-    return output.replace("</embed>", "")
+        outfile.write(soup.prettify().encode('utf-8'))
 
 
 def main():