X-Git-Url: https://git.armaanb.net/?p=lightcards.git;a=blobdiff_plain;f=lightcards%2Fparse.py;h=6fc2a759cf2ac152f636b9a376efa9ddf2d9db29;hp=6f3c25f6baf0d40b75fbdcfcf6ecbe4e850fae98;hb=468d491893758e3b9ac532757ea98791303f4a6d;hpb=da5f204dfb0e33a99bba1fa00842b253bf9947e0

diff --git a/lightcards/parse.py b/lightcards/parse.py
old mode 100755
new mode 100644
index 6f3c25f..6fc2a75
--- 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
 
@@ -10,28 +9,34 @@ 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:
+        return markdown.markdown(open(file, "r").read(), extensions=["tables"])
+    except FileNotFoundError:
+        sys.exit(f'lightcards: "{file}": No such file or directory')
 
 
 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')
+    soup = BeautifulSoup(html, "html.parser").find("table")
     outp = []
 
-    for x in soup.find_all("tr"):
-        outp.append(Card([clean_text(y) for y in x.find_all("td")]))
+    try:
+        for x in soup.find_all("tr"):
+            outp.append(Card(tuple([clean_text(y) for y in x.find_all("td")])))
+    except AttributeError:
+        sys.exit("lightcards: No table found")
+
+    ths = soup.find_all("th")
+    if len(ths) != 2:
+        sys.exit("lightcards: Headings malformed")
 
-    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 ths], outp[1:])
 
 
 def main(file):