]> git.armaanb.net Git - lightcards.git/blobdiff - lightcards/parse.py
Make file not found error print more standard
[lightcards.git] / lightcards / parse.py
index 12c1073552082f147ef17539f23bba3d60a1aae7..007b6408321b550257c45192177256296c952d9f 100755 (executable)
@@ -6,33 +6,37 @@ 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 a tuple of nested lists
+    return ([clean_text(x) for x in soup.find_all("th")][:2], outp[1:])
 
-    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]))