Add missing tests of HTML rewriting

scraper/src/mindtouch2zim/errors.py

@@ -10,6 +10,12 @@ class UnsupportedTagError(Exception):
     pass
 
 
+class UnsupportedHrefSrcError(Exception):
+    """An exception raised when an href or src is not expected to be encountered"""
+
+    pass
+
+
 class NoIllustrationFoundError(Exception):
     """An exception raised when no suitable illustration has been found"""
 

scraper/src/mindtouch2zim/html_rewriting.py

@@ -15,7 +15,7 @@
 
 from mindtouch2zim.client import LibraryPage
 from mindtouch2zim.constants import logger
-from mindtouch2zim.errors import UnsupportedTagError
+from mindtouch2zim.errors import UnsupportedHrefSrcError, UnsupportedTagError
 from mindtouch2zim.utils import is_better_srcset_descriptor
 from mindtouch2zim.vimeo import get_vimeo_thumbnail_url
 
@@ -52,8 +52,8 @@ def rewrite_href_src_attributes(
         )
     if not new_attr_value:
         # we do not (yet) support other tags / attributes so we fail the scraper
-        raise ValueError(
-            f"Empty new value when rewriting {attr_value} from {attr_name} in {tag} tag"
+        raise UnsupportedHrefSrcError(
+            f"Unsupported {attr_name} encountered in {tag} tag (value: {attr_value})"
         )
     return (attr_name, new_attr_value)
 

scraper/tests/test_html_rewriting.py

@@ -6,6 +6,7 @@
 )
 
 from mindtouch2zim.client import LibraryPage
+from mindtouch2zim.errors import UnsupportedHrefSrcError, UnsupportedTagError
 from mindtouch2zim.html_rewriting import HtmlUrlsRewriter
 
 
@@ -14,7 +15,9 @@ def url_rewriter() -> HtmlUrlsRewriter:
     return HtmlUrlsRewriter(
         library_url="https://www.acme.com",
         page=LibraryPage(id="123", title="a page", path="A_Page"),
-        existing_zim_paths=set(),
+        existing_zim_paths={
+            ZimPath("www.acme.com/existing.html"),
+        },
     )
 
 
@@ -97,3 +100,139 @@ def test_html_img_rewriting(
     assert rewritten.content == expected_html
     assert rewritten.title == ""
     assert url_rewriter.items_to_download == expected_items_to_download
+
+
+@pytest.mark.parametrize(
+    "source_html, expected_html, expected_items_to_download",
+    [
+        pytest.param(
+            '<iframe src="https://www.youtube.com/embed/sQaEthBmZB0?vq=hd1080" '
+            'frameborder="0" allowfullscreen="true" '
+            'style="width: 100%; height: 100%; position: absolute"></iframe>',
+            '<a href="https://www.youtube.com/embed/sQaEthBmZB0?vq=hd1080" '
+            'target="_blank">'
+            '<div class="zim-removed-video">'
+            '<img src="content/i.ytimg.com.fuzzy.replayweb.page/'
+            'vi/sQaEthBmZB0/thumbnail.jpg"></img>'
+            "</div>"
+            "</a>"
+            '<iframe style="display: none;"></iframe>',
+            {
+                ZimPath(
+                    "i.ytimg.com.fuzzy.replayweb.page/vi/sQaEthBmZB0/thumbnail.jpg"
+                ): {HttpUrl("https://i.ytimg.com/vi/sQaEthBmZB0/hqdefault.jpg")}
+            },
+            id="youtube",
+        ),
+        pytest.param(
+            '<iframe src="https://player.vimeo.com/video/153300296" '
+            'frameborder="0" allowfullscreen="true" '
+            'style="width: 100%; height: 100%; position: absolute"></iframe>',
+            '<a href="https://player.vimeo.com/video/153300296" '
+            'target="_blank">'
+            '<div class="zim-removed-video">'
+            '<img src="content/i.vimeocdn.com/video/553546340-'
+            '35aa6d23b04e9bdaf254c3cfc4da56bcfd7ff3f75a517c485536082edbf547dd-d_640">'
+            "</img>"
+            "</div>"
+            "</a>"
+            '<iframe style="display: none;"></iframe>',
+            {
+                ZimPath(
+                    "i.vimeocdn.com/video/553546340-"
+                    "35aa6d23b04e9bdaf254c3cfc4da56bcfd7ff3f75a517c485536082edbf547dd-"
+                    "d_640"
+                ): {
+                    HttpUrl(
+                        "https://i.vimeocdn.com/video/553546340-"
+                        "35aa6d23b04e9bdaf254c3cfc4da56bcfd7ff3f75a517c485536082e"
+                        "dbf547dd-d_640"
+                    )
+                }
+            },
+            id="vimeo",
+        ),
+        pytest.param(
+            '<iframe src="https://www.acme.com/embed/sQaEthBmZB0?vq=hd1080" '
+            'frameborder="0" allowfullscreen="true" '
+            'style="width: 100%; height: 100%; position: absolute"></iframe>',
+            "This content is not inside the ZIM. View content online at "
+            '<a href="https://www.acme.com/embed/sQaEthBmZB0?vq=hd1080" '
+            'target="_blank">'
+            "<div>https://www.acme.com/embed/sQaEthBmZB0?vq=hd1080</div>"
+            "</a>"
+            '<iframe style="display: none;"></iframe>',
+            {},
+            id="unhandled",
+        ),
+    ],
+)
+def test_html_iframe_rewriting(
+    url_rewriter: HtmlUrlsRewriter,
+    html_rewriter: HtmlRewriter,
+    source_html: str,
+    expected_html: str,
+    expected_items_to_download: dict[ZimPath, set[HttpUrl]],
+):
+    rewritten = html_rewriter.rewrite(source_html)
+    assert rewritten.content == expected_html
+    assert rewritten.title == ""
+    assert url_rewriter.items_to_download == expected_items_to_download
+
+
+def test_html_picture_rewriting(html_rewriter: HtmlRewriter):
+    with pytest.raises(UnsupportedTagError):
+        html_rewriter.rewrite("<picture>")
+
+
+def test_html_script_rewriting(html_rewriter: HtmlRewriter):
+    with pytest.raises(UnsupportedHrefSrcError):
+        html_rewriter.rewrite("<script src='script.js'>")
+
+
+@pytest.mark.parametrize(
+    "source_html, expected_html, expected_items_to_download",
+    [
+        pytest.param(
+            '<a href="https://www.acme.com/existing.html">Page</a>',
+            '<a href="#/existing.html">Page</a>',
+            {},
+            id="internal_absolute",
+        ),
+        pytest.param(
+            '<a href="/existing.html">Page 1</a>',
+            '<a href="#/existing.html">Page 1</a>',
+            {},
+            id="internal_root",
+        ),
+        pytest.param(
+            '<a href="../existing.html">Page 1</a>',
+            '<a href="#/existing.html">Page 1</a>',
+            {},
+            id="internal_relative",
+        ),
+        pytest.param(
+            '<a href="../outside.html">Page 1</a>',
+            '<a href="https://www.acme.com/outside.html">Page 1</a>',
+            {},
+            id="external_relative",
+        ),
+        pytest.param(
+            '<a href="https://www.foo.bar/index.html">Page 2</a>',
+            '<a href="https://www.foo.bar/index.html">Page 2</a>',
+            {},
+            id="external",
+        ),
+    ],
+)
+def test_html_href_rewriting(
+    url_rewriter: HtmlUrlsRewriter,
+    html_rewriter: HtmlRewriter,
+    source_html: str,
+    expected_html: str,
+    expected_items_to_download: dict[ZimPath, set[HttpUrl]],
+):
+    rewritten = html_rewriter.rewrite(source_html)
+    assert rewritten.content == expected_html
+    assert rewritten.title == ""
+    assert url_rewriter.items_to_download == expected_items_to_download