-#!/usr/bin/env python
# Parse markdown table into tuple of lists
# Armaan Bhojwani 2021
def md2html(file):
"""Use the markdown module to convert input to HTML"""
- with open(file, "r", encoding="utf-8") as input_file:
- return markdown.markdown(input_file.read(), extensions=['tables'])
+ 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):
+
+def parse_html(html, lenient):
"""Use BeautifulSoup to parse the HTML"""
+
def clean_text(inp):
return inp.get_text().rstrip()
- soup = BeautifulSoup(html, 'html.parser')
- outp = []
-
- for x in soup.find_all("tr"):
- outp.append(Card([clean_text(y) for y in x.find_all("td")[:2]]))
+ soup = BeautifulSoup(html, "html.parser")
+ outp, ths = [], []
+
+ for table in soup.find_all("table"):
+ ths = table.find_all("th")
+ if len(ths) != 2:
+ if not lenient:
+ raise Exception("lightcards: Headings malformed")
+ else:
+ 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
# Return a tuple of nested lists
- return ([clean_text(x) for x in soup.find_all("th")][:2], outp[1:])
-
-
-def main(file):
- return parse_html(md2html(file))
-
-
-if __name__ == "__main__":
- print(main(sys.argv[1]))
+ return ([clean_text(x) for x in ths], outp)