X-Git-Url: https://git.armaanb.net/?a=blobdiff_plain;f=lightcards%2Fparse.py;h=8e0d320f6202f5e0bde347b540bcca36d02cc93e;hb=3ec382bac0913a7268e8059eaf337a54cf1b0f5c;hp=12c1073552082f147ef17539f23bba3d60a1aae7;hpb=ecd6aa920a6287905e86e3c98cbe6bacc6e8677c;p=lightcards.git

diff --git a/lightcards/parse.py b/lightcards/parse.py
old mode 100755
new mode 100644
index 12c1073..8e0d320
--- 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
 
@@ -6,33 +5,54 @@ 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"""
+    outp = ""
+    for i in file:
+        try:
+            outp += markdown.markdown(
+                open(i, "r").read(), extensions=["tables"]
+            )
+        except FileNotFoundError:
+            raise Exception(
+                f'lightcards: "{i}": No such file or directory'
+            ) from None
+
+    return outp
 
 
 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_all("table")
     outp = []
 
-    for x in soup.find_all("tr"):
-        outp.append([clean_text(y) for y in x.find_all("td")])
+    for table in soup:
+        try:
+            for x in table.find_all("tr"):
+                y = x.find_all("td")
+                if y:
+                    outp.append(Card(tuple([clean_text(z) for z in y])))
+        except AttributeError:
+            raise Exception("lightcards: No table found") from None
+
+        ths = table.find_all("th")
+        if len(ths) != 2:
+            raise Exception("lightcards: Headings malformed")
+
+    # Return a tuple of nested lists
+    return ([clean_text(x) for x in ths], outp)
 
-    return ([clean_text(x) for x in soup.find_all("th")],
-            clean_list(outp))
 
 def main(file):
     return parse_html(md2html(file))
 
+
 if __name__ == "__main__":
     print(main(sys.argv[1]))