├── README.md
└── html2csv.py


/README.md:
--------------------------------------------------------------------------------
 1 | html2csv.py
 2 | ===================================
 3 | 
 4 | This handy script reads an HTML file and prints each of the HTML tables
 5 | therein to separate CSV files.
 6 | 
 7 | Examples
 8 | --------
 9 | 
10 |     ./html2csv.py webpage.html
11 |     
12 |     cat webpage.html | ./html2csv.py
13 | 
14 | Credits
15 | -------
16 | 
17 | Fernando Ferreira provided changes that updated the script to Python3.


--------------------------------------------------------------------------------
/html2csv.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env python3
 2 | # -*- coding: utf-8 -*-
 3 | #Richard's html2csv converter
 4 | #rijard.barnes@gmail.com
 5 | #
 6 | 
 7 | from bs4 import BeautifulSoup
 8 | import argparse
 9 | import csv
10 | import fileinput
11 | import sys
12 | 
13 | parser = argparse.ArgumentParser(description='Reads in an HTML and attempts to convert all tables into CSV files.')
14 | parser.add_argument('--delimiter', '-d', action='store', default=',',help="Character with which to separate CSV columns")
15 | parser.add_argument('--quotechar', '-q', action='store', default='"',help="Character within which to nest CSV text")
16 | parser.add_argument('filename', nargs="?", help="HTML file from which to extract tables")
17 | args = parser.parse_args()
18 | 
19 | data = list(fileinput.input(files=(args.filename, ) if args.filename is not None else ('-', )))
20 | data = "\n".join(data)
21 | 
22 | soup = BeautifulSoup(data, "html.parser")
23 | 
24 | #Preemptively removing unnecessary tags
25 | [s.extract() for s in soup('script')]
26 | 
27 | for index,table in enumerate(soup.findAll("table")):
28 |   fout = csv.writer(sys.stdout, delimiter=args.delimiter, quotechar=args.quotechar, quoting=csv.QUOTE_MINIMAL)
29 |   for row in table.findAll('tr'):
30 |     cols = row.findAll(['td','th'])
31 |     if cols:
32 |       cols = [str(x.text).strip() for x in cols]
33 |       fout.writerow(cols)
34 | 
35 |   print("\n\n###")


--------------------------------------------------------------------------------