parse href

md_dead_link_check/preprocess.py

@@ -10,7 +10,8 @@
 
 RE_HEADER = r"^[#]{1,6}\s*(.*)"
 RE_LINK = r"[!]{0,1}\[[^\]!]*\]\((([^\s)]+)(?:\s*(.*?))?)\)"
-RE_HTML_A_TAG_ID = r"<a\s+id=[\"'](.*)[\"']>.*?<\/a>"
+RE_HTML_A_TAG_ID = r"<a\s+id=[\"'](.*?)[\"']>.*?<\/a>"
+RE_HTML_A_TAG_HREF = r"<a\s+href=[\"'](.*?)[\"']>.*?<\/a>"
 RE_SUB = r"[$`][^`]+?[$`]"
 
 
@@ -102,9 +103,13 @@ def process_md_file(path: Path, root_dir: Path) -> MarkdownInfo:
 
             # Detect id under a tag <a id="introduction"></a>
             matches = re.findall(RE_HTML_A_TAG_ID, line)
-            if matches:
-                for id in matches:
-                    fragments.append(id)
+            for id in matches:
+                fragments.append(id)
+
+            # Detect links under a tag <a href="introduction"></a>
+            matches = re.findall(RE_HTML_A_TAG_HREF, line)
+            for link in matches:
+                links.append(LinkInfo(link, path, line_num))
     return MarkdownInfo(path=path, fragments=fragments, links=links)
 
 

tests/test_md_files/a.md

@@ -26,7 +26,7 @@ Some text
 
 [github](https://github.com/AlexanderDokuchaev)
 [b](./b.md) [d.a](b.md) `[A+B](A)`
-[d.a](./d/a.md)
+<a href="./d/a.md">d.a</a><a href="./d/a.md">d.a</a>
 [d.a](/tests/test_md_files/d/a.md "tag")
 
 ### Header with `quotes` and $math$

tests/test_preprocess.py

@@ -73,6 +73,11 @@ def test_process_md_file():
             location=Path("tests/test_md_files/a.md"),
             line_num=29,
         ),
+        LinkInfo(
+            link="./d/a.md",
+            location=Path("tests/test_md_files/a.md"),
+            line_num=29,
+        ),
         LinkInfo(
             link="/tests/test_md_files/d/a.md",
             location=Path("tests/test_md_files/a.md"),