X-Git-Url: https://git.armaanb.net/?a=blobdiff_plain;f=lightcards%2Fparse.py;h=6fc2a759cf2ac152f636b9a376efa9ddf2d9db29;hb=4e5a09ff518efbffe31ce064334cb1db1d42eae4;hp=457da136f4b30b503f3350dfdcf3f9dd7d58150c;hpb=52521ebab49dc4d0e2fb2a2b970873d7b832da01;p=lightcards.git diff --git a/lightcards/parse.py b/lightcards/parse.py old mode 100755 new mode 100644 index 457da13..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 @@ -6,30 +5,38 @@ 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 ([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):