add an extra test for inner tags that should generate separate matches

streamlink · Jul 31, 2018 · e449aa3 · e449aa3
1 parent 3768e61
commit e449aa3
Show file tree

Hide file tree

Showing 2 changed files with 71 additions and 1 deletion.
diff --git a/src/streamlink/utils/__init__.py b/src/streamlink/utils/__init__.py
@@ -143,6 +143,65 @@ def rtmpparse(url):
     return tcurl, playpath
 
 
+def memoize(obj):
+    cache = obj.cache = {}
+
+    @functools.wraps(obj)
+    def memoizer(*args, **kwargs):
+        key = str(args) + str(kwargs)
+        if key not in cache:
+            cache[key] = obj(*args, **kwargs)
+        return cache[key]
+    return memoizer
+
+
+def search_dict(data, key):
+    """
+    Search for a key in a nested dict, or list of nested dicts, and return the values.
+
+    :param data: dict/list to search
+    :param key: key to find
+    :return: matches for key
+    """
+    if isinstance(data, dict):
+        for dkey, value in data.items():
+            if dkey == key:
+                yield value
+            for result in search_dict(value, key):
+                yield result
+    elif isinstance(data, list):
+        for value in data:
+            for result in search_dict(value, key):
+                yield result
+
+
+def load_module(name, path=None):
+    if is_py3:
+        import importlib.machinery
+        import importlib.util
+        import sys
+
+        loader_details = [(importlib.machinery.SourceFileLoader, importlib.machinery.SOURCE_SUFFIXES)]
+        finder = importlib.machinery.FileFinder(path, *loader_details)
+        spec = finder.find_spec(name)
+        if not spec or not spec.loader:
+            raise ImportError("no module named {0}".format(name))
+        if sys.version_info[1] > 4:
+            mod = importlib.util.module_from_spec(spec)
+            spec.loader.exec_module(mod)
+            return mod
+        else:
+            return spec.loader.load_module(name)
+
+    else:
+        import imp
+        fd, filename, desc = imp.find_module(name, path and [path])
+        try:
+            return imp.load_module(name, fd, filename, desc)
+        finally:
+            if fd:
+                fd.close()
+
 #####################################
 # Deprecated functions, do not use. #
 #####################################
@@ -246,4 +305,4 @@ def escape_librtmp(value):  # pragma: no cover
            "verifyjson", "absolute_url", "parse_qsd", "parse_json", "res_json",
            "parse_xml", "res_xml", "rtmpparse", "prepend_www", "NamedPipe",
            "escape_librtmp", "LazyFormatter", "get_filesystem_encoding",
-           "maybe_decode", "maybe_encode"]
+           "maybe_decode", "maybe_encode"]
diff --git a/tests/test_plugin_utils.py b/tests/test_plugin_utils.py
@@ -11,6 +11,8 @@
 
 class TestPluginUtil(unittest.TestCase):
     test_html = """
+<!doctype html>
+<html lang="en" class="no-js">
 <title>Title</title>
 <meta property="og:type" content= "website" />
 <meta property="og:url" content="http://test.se/"/>
@@ -19,8 +21,11 @@ class TestPluginUtil(unittest.TestCase):
 <link rel="stylesheet" type="text/css" href="https://test.se/test.css">
 <script>Tester.ready(function () {
 alert("Hello, world!"); });</script>
+<p>
 <a 
 href="http://test.se/foo">bar</a>
+</p>
+</html>
         """
 
     def test_itertags_single_text(self):
@@ -70,5 +75,11 @@ def test_no_end_tag(self):
                                                "type": "text/css",
                                                "href": "https://test.se/test.css"})
 
+    def test_tag_inner_tag(self):
+        links = list(itertags(self.test_html, "p"))
+        self.assertTrue(len(links), 1)
+        self.assertEqual(links[0].tag, "p")
+        self.assertEqual(links[0].text.strip(), '<a \nhref="http://test.se/foo">bar</a>')
+        self.assertEqual(links[0].attributes, {})