knapsack-parser.py

import glob
from bs4 import BeautifulSoup
import bs4

htmls = glob.glob('./knapsack/C*')
output = open("knapsack.tsv", "w")
output.write("\t".join(["knapsackid", "name", "formula", "mw", "cas", "inchikey"]))
output.write("\n")

for i in htmls:
    knapsackid = i.split("\\")[-1]
    f = open(i)
    tags = f.read()
    soup = BeautifulSoup(tags, 'html.parser')
    title = soup.title.string.split(" - ")[-1]
    for j in soup.td.find_all('tr'):
        if type(j.th) == bs4.element.Tag:
            if j.th.string == "Formula":
                formula = j.td.string
            elif j.th.string == "Mw":
                mw = j.td.string
            elif j.th.string == "CAS RN":
                if j.td.string:
                    cas = j.td.string
            elif j.th.string == "InChIKey":
                if j.td.string:
                    inchikey = j.td.string
    output.write("\t".join([knapsackid, title, formula, mw, cas, inchikey]))
    output.write("\n")
output.close()