adding new extract command to extract selector or main content as markdown, updateing version as 0.5.0

tests/test_extract.py

@@ -7,18 +7,24 @@ def test_extract_links(browser, http_tab):
     browser("tabs.active", {"tabId": http_tab["id"]})
     links = browser("extract.links")
     assert isinstance(links, list)
+    hrefs = []
     for lnk in links:
         assert "href" in lnk
         assert "text" in lnk
+        hrefs.append(lnk["href"])
+    assert len(hrefs) == len(set(hrefs))
 
 
 def test_extract_images(browser, http_tab):
     browser("tabs.active", {"tabId": http_tab["id"]})
     images = browser("extract.images")
     assert isinstance(images, list)
+    sources = []
     for img in images:
         assert "src" in img
         assert img["src"] != ""
+        sources.append(img["src"])
+    assert len(sources) == len(set(sources))
 
 
 def test_extract_text(browser, http_tab):
@@ -35,6 +41,19 @@ def test_extract_html(browser, http_tab):
     assert "<" in html
 
 
+def test_extract_markdown(browser, http_tab):
+    browser("tabs.active", {"tabId": http_tab["id"]})
+    markdown = browser("extract.markdown")
+    assert isinstance(markdown, str)
+    assert len(markdown.strip()) > 0
+
+
+def test_extract_markdown_missing_selector_errors(browser, http_tab):
+    browser("tabs.active", {"tabId": http_tab["id"]})
+    with pytest.raises(RuntimeError, match="No element"):
+        browser("extract.markdown", {"selector": ".browser-cli-definitely-missing"})
+
+
 def test_dom_exists(browser, http_tab):
     browser("tabs.active", {"tabId": http_tab["id"]})
     result = browser("dom.exists", {"selector": "body"})