Clean input better, only parse first two columns

[lightcards.git] / lightcards / parse.py

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):