Merge pull request #237 from Gallaecio/query-input

Add a minimal action I/O implementation to improve SearchAction support

extruct/w3cmicrodata.py

@@ -235,6 +235,17 @@ def _extract_property_value(self, node, items_seen, base_url, itemids, force=Fal
         elif node.get("content"):
             return node.get("content")
 
+        # https://schema.org/docs/actions.html#part-4
+        elif (itemprop := node.get("itemprop")) and (
+            itemprop.endswith("-input") or itemprop.endswith("-output")
+        ):
+            result = {}
+            if "required" in node.attrib:
+                result["valueRequired"] = True
+            if name := node.get("name"):
+                result["valueName"] = name
+            return result
+
         else:
             return self._extract_textContent(node)
 

tests/samples/schema.org/SearchAction.001.html

@@ -0,0 +1,8 @@
+<div itemscope itemtype="https://schema.org/WebSite">
+  <meta itemprop="url" content="https://www.example.com/"/>
+  <form itemprop="potentialAction" itemscope itemtype="https://schema.org/SearchAction">
+    <meta itemprop="target" content="https://query.example.com/search?q={search_term_string}"/>
+    <input itemprop="query-input" type="text" name="search_term_string" required/>
+    <input type="submit"/>
+  </form>
+</div>

tests/samples/schema.org/SearchAction.001.json

@@ -0,0 +1 @@
+[{"type": "https://schema.org/WebSite", "properties": {"url": "https://www.example.com/", "potentialAction": {"type": "https://schema.org/SearchAction", "properties": {"target": "https://query.example.com/search?q={search_term_string}", "query-input": {"valueRequired": true, "valueName": "search_term_string"}}}}}]

tests/test_microdata.py

@@ -10,6 +10,17 @@ class TestMicrodata(unittest.TestCase):
 
     maxDiff = None
 
+    def _test_schemaorg(self, schema, indexes=None):
+        indexes = indexes or [1]
+        for i in indexes:
+            body = get_testdata("schema.org", f"{schema}.{i:03d}.html")
+            expected = json.loads(
+                get_testdata("schema.org", f"{schema}.{i:03d}.json").decode()
+            )
+            mde = MicrodataExtractor()
+            data = mde.extract(body)
+            self.assertEqual(data, expected)
+
     def test_schemaorg_CreativeWork(self):
         for i in [1]:
             body = get_testdata("schema.org", "CreativeWork.{:03d}.html".format(i))
@@ -63,6 +74,9 @@ def test_schemaorg_Event(self):
 
             self.assertEqual(data, expected)
 
+    def test_schemaorg_SearchAction(self):
+        self._test_schemaorg("SearchAction")
+
     def test_w3c_textContent_values(self):
         body = get_testdata("w3c", "microdata.4.2.strings.html")
         expected = json.loads(