Clean input better, only parse first two columns

diff --git a/contrib/3col.md b/contrib/3col.md
new file mode 100644 (file)
index 0000000..f86e072
--- /dev/null
+++ b/contrib/3col.md
@@ -0,0 +1,10 @@
+| Side 1       | Side 2      | Side 3       |
+|--------------|-------------|--------------|
+| Card 1 Front | Card 1 Back | Card 1 Third |
+| Card 2 Front | Card 2 Back | Card 2 Third |
+| Card 3 Front | Card 3 Back | Card 3 Third |
+| Card 4 Front | Card 4 Back | Card 4 Third |
+| Card 5 Front | Card 5 Back | Card 5 Third |
+| Card 6 Front | Card 6 Back | Card 6 Third |
+| Card 7 Front | Card 7 Back | Card 7 Third |
+| Card 8 Front | Card 8 Back | Card 8 Third |

diff --git a/lightcards/parse.py b/lightcards/parse.py
index 65cad627d4cd25e38dce77973fb9b25ae958a6dd..fb5ac68a2195bd9ccfdb1109c912bd1f83158b59 100755 (executable)
--- a/lightcards/parse.py
+++ b/lightcards/parse.py
@@ -20,21 +20,14 @@ def parse_html(html):
     def clean_text(inp):
         return inp.get_text().rstrip()
 
-    def clean_list(inp):
-        for z in inp:
-            if not len(z) == 2:
-                inp.remove(z)
-        return inp
-
     soup = BeautifulSoup(html, 'html.parser')
     outp = []
 
     for x in soup.find_all("tr"):
-        outp.append(Card([clean_text(y) for y in x.find_all("td")]))
+        outp.append(Card([clean_text(y) for y in x.find_all("td")[:2]]))
 
     # Return a tuple of nested lists
-    return ([clean_text(x) for x in soup.find_all("th")],
-            clean_list(outp))
+    return ([clean_text(x) for x in soup.find_all("th")][:2], outp[1:])
 
 
 def main(file):