improved find() and find_all() to recurse through iframes

ultrafunkamsterdam · Feb 21, 2024 · a0c269e · a0c269e
1 parent 54560b4
commit a0c269e
Show file tree

Hide file tree

Showing 4 changed files with 32 additions and 17 deletions.
diff --git a/nodriver/core/connection.py b/nodriver/core/connection.py
@@ -502,6 +502,7 @@ async def listener_loop(self):
                     event = cdp.util.parse_json_event(message)
                     # self.history.append(event)
                     event_tx = EventTransaction(event)
+                    # getattr(globals(), event.__class__.__module__)
                     if not self.connection.mapper:
                         self.connection.__count__ = itertools.count(0)
                     event_tx.id = next(self.connection.__count__)

diff --git a/nodriver/core/tab.py b/nodriver/core/tab.py
@@ -88,7 +88,7 @@ class Tab(Connection):
     find and returns all elements by css selector match.
     when no match is found, it will retry for <timeout> seconds (default: 10), so
     this is also suitable to use as wait condition.
-    
+
 
     await :py:obj:`Tab`
     ---------------------------
@@ -461,7 +461,9 @@ async def find_elements_by_text(
         doc = await self.send(cdp.dom.get_document(-1, True))
         search_id, nresult = await self.send(cdp.dom.perform_search(text, True))
         if nresult:
-            node_ids = await self.send(cdp.dom.get_search_results(search_id, 0, nresult))
+            node_ids = await self.send(
+                cdp.dom.get_search_results(search_id, 0, nresult)
+            )
         else:
             node_ids = []
 
@@ -501,17 +503,23 @@ async def find_elements_by_text(
         # let's also search through the iframes
         iframes = util.filter_recurse_all(doc, lambda node: node.node_name == "IFRAME")
         if iframes:
-            iframes_elems = [element.create(iframe, self, iframe.content_document) for iframe in iframes]
+            iframes_elems = [
+                element.create(iframe, self, iframe.content_document)
+                for iframe in iframes
+            ]
             for iframe_elem in iframes_elems:
-                iframe_text_nodes = util.filter_recurse_all(
-                    iframe_elem.content_document,
-                    lambda node: node.node_type == 3  # noqa
-                                 and text.lower() in node.node_value.lower(),
-                )
-                if iframe_text_nodes:
-                    iframe_text_elems = [element.create(text_node, self, iframe_elem.tree) for text_node in
-                                         iframe_text_nodes]
-                    results.extend(text_node.parent for text_node in iframe_text_elems)
+                if iframe_elem.content_document:
+                    iframe_text_nodes = util.filter_recurse_all(
+                        iframe_elem,
+                        lambda node: node.node_type == 3  # noqa
+                        and text.lower() in node.node_value.lower(),
+                    )
+                    if iframe_text_nodes:
+                        iframe_text_elems = [
+                            element.create(text_node, self, iframe_elem.tree)
+                            for text_node in iframe_text_nodes
+                        ]
+                        results.extend(text_node.parent for text_node in iframe_text_elems)
         await self.send(cdp.dom.disable())
         return results or []
 
@@ -574,15 +582,21 @@ async def find_element_by_text(
         # let's also search through the iframes
         iframes = util.filter_recurse_all(doc, lambda node: node.node_name == "IFRAME")
         if iframes:
-            iframes_elems = [element.create(iframe, self, iframe.content_document) for iframe in iframes]
+            iframes_elems = [
+                element.create(iframe, self, iframe.content_document)
+                for iframe in iframes
+            ]
             for iframe_elem in iframes_elems:
                 iframe_text_nodes = util.filter_recurse_all(
-                    iframe_elem.content_document,
+                    iframe_elem,
                     lambda node: node.node_type == 3  # noqa
                     and text.lower() in node.node_value.lower(),
                 )
                 if iframe_text_nodes:
-                    iframe_text_elems = [element.create(text_node, self, iframe_elem.tree) for text_node in iframe_text_nodes]
+                    iframe_text_elems = [
+                        element.create(text_node, self, iframe_elem.tree)
+                        for text_node in iframe_text_nodes
+                    ]
                     results.extend(text_node.parent for text_node in iframe_text_elems)
         try:
             if not results:

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "nodriver" # Required
-version = "0.23rc0"  # Required
+version = "0.24rc1"  # Required
 description = """
     * Official successor of Undetected Chromedriver
     * Can be made to work for for all chromium based browsers.

diff --git a/version b/version
@@ -1 +1 @@
-0.23rc0
+0.24rc1