Clean up lightcards.py

[lightcards.git] / lightcards / parse.py

diff --git a/lightcards/parse.py b/lightcards/parse.py
old mode 100755 (executable)
new mode 100644 (file)
index 457da13..9b1820a
--- a/lightcards/parse.py
+++ b/lightcards/parse.py
@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # Parse markdown table into tuple of lists
 # Armaan Bhojwani 2021
 
@@ -6,30 +5,32 @@ import sys
 from bs4 import BeautifulSoup
 import markdown
 
+from .deck import Card
+
 
 def md2html(file):
-    with open(file, "r", encoding="utf-8") as input_file:
-        return markdown.markdown(input_file.read(), extensions=['tables'])
+    """Use the markdown module to convert input to HTML"""
+    try:
+        with open(file, "r", encoding="utf-8") as input_file:
+            return markdown.markdown(input_file.read(), extensions=['tables'])
+    except FileNotFoundError:
+        print(f"lightcards: \"{file}\": No such file or directory")
+        exit(1)
 
 
 def parse_html(html):
+    """Use BeautifulSoup to parse the 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([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 ([clean_text(x) for x in soup.find_all("th")],
-            clean_list(outp))
+    # Return a tuple of nested lists
+    return ([clean_text(x) for x in soup.find_all("th")][:2], outp[1:])
 
 
 def main(file):