X-Git-Url: https://git.armaanb.net/?p=lightcards.git;a=blobdiff_plain;f=lightcards%2Fparse.py;h=6fc2a759cf2ac152f636b9a376efa9ddf2d9db29;hp=12c1073552082f147ef17539f23bba3d60a1aae7;hb=468d491893758e3b9ac532757ea98791303f4a6d;hpb=ecd6aa920a6287905e86e3c98cbe6bacc6e8677c diff --git a/lightcards/parse.py b/lightcards/parse.py old mode 100755 new mode 100644 index 12c1073..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 @@ -6,33 +5,43 @@ 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: + 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([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 a tuple of nested lists + return ([clean_text(x) for x in ths], 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]))