Changeset 15595 for main/waeup.kofa/trunk/src/waeup/kofa

Timestamp:

19 Sep 2019, 23:38:52 (5 years ago)

Author:

uli

Message:

Add a function to extract key/value pairs from

HTML forms.

Location:

main/waeup.kofa/trunk/src/waeup/kofa/utils

Files:

• helpers.py (modified) (2 diffs)
• tests/sample_response.html (added)

main/waeup.kofa/trunk/src/waeup/kofa/utils/helpers.py

@@ -30 +30 @@
 from cStringIO import StringIO
 from docutils.core import publish_string
+from HTMLParser import HTMLParser
 from zope.component import getUtility
 from zope.component.interfaces import IFactory
@@ -864 +865 @@
                 contents=ReST2HTML(text))
     return elements
+
+
+
+class FormVarParser(HTMLParser):
+    """An HTML form parser that extracts keys and values.
+
+       Fed with an HTML document, we parse all starttags and check for each,
+       whether it provides a `name` and a `value` attribute. If so, the
+       values of the respective attributes are stored in instance var
+       `form_vars` as a dict entry.
+    """
+
+    def __init__(self):
+        HTMLParser.__init__(self)  # old-style class - no super()
+        self.form_vars = {}
+
+    def handle_starttag(self, tag, attrs):
+        tag_attrs = {}
+        for key, val in attrs:
+            tag_attrs[key] = val
+        if 'name' in tag_attrs and 'value' in tag_attrs:
+            self.form_vars[tag_attrs['name']] = tag_attrs['value']
+
+
+def extract_formvars(html_code):
+    """Extract keys and values from an HTML form as dict.
+
+       No text, no values::
+
+         >>> extract_formvars("")
+         {}
+
+       Simple input tags normally provide name and value::
+
+         >>> extract_formvars("<input type='text' name='foo' value='bar'>")
+         {'foo': 'bar'}
+
+       The sample doc we stored in tests is a bit more difficult::
+
+         >>> html_path = os.path.join(os.path.dirname(__file__),
+         ...                          'tests', 'sample_response.html')
+         >>> html_code = open(html_path, 'r').read()
+         >>> import pprint
+         >>> pprint.pprint(extract_formvars(html_code))
+         {'AMOUNT': '100',
+         ...
+          'TRANS_NUM': '01ESA20190916134824YA3YJ8'}
+
+    """
+    result = {}
+    parser = FormVarParser()
+    parser.feed(html_code)
+    return parser.form_vars