Test for parsing of Stanford subtitle URL.

test_edx_dl.py

@@ -116,3 +116,35 @@ def mock_get_page_contents_as_json(u, h):
     expected = '0\n00:00:00,123 --> 00:00:00,456\nsubtitle content\n\n'
     actual = edx_dl.edx_get_subtitle(url, headers, mock_get_page_contents, mock_get_page_contents_as_json)
     assert expected == actual
+
+
+def test_extract_subtitle_urls():
+    text = """
+<li class="video-tracks video-download-button">
+            <a href="/courses/Engineering/QMSE02./Winter2016/xblock/i4x:;_;_Engineering;_QMSE02.;_video;_1a4c7ff41e484a15927987b745a5c779/handler/transcript/download">Download transcript</a>
+            <div class="a11y-menu-container">
+                <a class="a11y-menu-button" href="#" title=".srt" role="button" aria-disabled="false">.srt</a>
+                <ol class="a11y-menu-list" role="menu">
+                  <li class="a11y-menu-item active">
+                  
+                      <a class="a11y-menu-item-link" href="#srt" title="SubRip (.srt) file" data-value="srt" role="menuitem" aria-disabled="false">
+                        SubRip (.srt) file
+                      </a>
+                  </li>
+                  <li class="a11y-menu-item">
+                  
+                      <a class="a11y-menu-item-link" href="#txt" title="Text (.txt) file" data-value="txt" role="menuitem" aria-disabled="false">
+                        Text (.txt) file
+                      </a>
+                  </li>
+                </ol>
+            </div>
+        </li>
+    """
+
+    page_extractor = parsing.CurrentEdXPageExtractor()
+    expected = (None, 'https://base.url/courses/Engineering/QMSE02./Winter2016/xblock/i4x:;_;_Engineering;_QMSE02.;_video;_1a4c7ff41e484a15927987b745a5c779/handler/transcript/download')
+    actual = page_extractor.extract_subtitle_urls(text, "https://base.url")
+    print("actual", actual)
+    assert expected == actual
+