Support more tags in gemparse

Gemparse now supports parsing:
 - h3
 - h4
 - ul, ol, li
 - a tags as anchors (<a name="" />)
 - a tags as anchor refs (<a href="#.." ></a>)

1 files changed, 17 insertions, 6 deletions

diff --git a/gemparse.py b/gemparse.py
index 54dd990..dd83c89 100755
--- a/gemparse.py
+++ b/gemparse.py
@@ -13,9 +13,16 @@ def handleNestedTag(tag, links, linkCnt, dest_f):
     for child in tag.contents:
         if child.name == "a":
             href = child.get("href")
-            print("{}[{}]".format(strip(child.string), linkCnt), end=" ", file=dest_f)
-            links[linkCnt] = href
-            linkCnt += 1
+            if href is not None:
+                if href.startswith("#"):
+                    print(strip(child.string), end=" ", file=dest_f)
+                else:
+                    print("{}[{}]".format(strip(child.string), linkCnt), end=" ", file=dest_f)
+                    links[linkCnt] = href
+                    linkCnt += 1
+            else:
+                # it's not a href link then its likely an anchor
+                pass
         else:
             if child.string == "\n":
                 print(strip(child.string), end="", file=dest_f)
@@ -59,14 +66,18 @@ for tag in html.article.children:
         else:
             print("\n", end="", file=dest_f)
             handleNestedTag(tag, links, linkCnt, dest_f)
-    if tag.name == "ul" or tag.name == "ol":
+    elif tag.name == "ul" or tag.name == "ol":
         for child in tag.contents:
             if child.name == "li":
                 print("*", end=" ", file=dest_f)
                 handleNestedTag(child, links, linkCnt, dest_f)
-    if tag.name == "h3":
+    if tag.name == "figure":
+        if tag.blockquote is not None:
+            print(">", end=" ", file=dest_f)
+            handleNestedTag(tag.blockquote, links, linkCnt, dest_f)
+    elif tag.name == "h3":
         print("\n## {}".format(strip(tag.string)), file=dest_f)
-    if tag.name == "h4":
+    elif tag.name == "h4":
         print("\n### {}".format(strip(tag.string)), file=dest_f)
 
 print("\n## Links\n", file=dest_f)