ParseHTMLTables

Find tables inside HTML and extract the contents into objects using the following logic: - If table has 2 columns and has no header row, treat the first column as key and second as value and create a table of key/value - If table has a header row, create a table of objects where attribute names are the headers - If table does not have a header row, create table of objects where attribute names are cell1, cell2, cell3...

python · Filters And Transformers

Details

ID	`ParseHTMLTables`
Language	python
From Version	6.5.0
Docker Image	`demisto/bs4-py3:1.0.0.10120494`
Tags	transformer general

README

Find tables inside HTML and extract the contents into objects using the following logic:

If table has 2 columns and has no header row, treat the first column as key and second as value and create a table of key/value
If table has a header row, create a table of objects where attribute names are the headers
If table does not have a header row, create table of objects where attribute names are cell1, cell2, cell3…

Script Data

Name	Description
Script Type	python3
Tags	transformer, general

Inputs

Argument Name	Description
value	The HTML to extract tables from
title	The title for tables
filter_indexes	Extract only the tables with given indexes - 0 based
filter_titles	Extract only the tables with given titles

Outputs

There are no outputs for this script.

Source

ParseHTMLTables.py ParseHTMLTables_test.py ParseHTMLTables.yml

Download History Raw

import json

import demistomock as demisto
import pytest

INPUTS = [
    ("test_data/test1-in.html", "test_data/test1-out.json", None, None),
    ("test_data/test2-in.html", "test_data/test2-out.json", None, None),
    ("test_data/test3-in.html", "test_data/test3-out.json", None, None),
    ("test_data/test4-in.html", "test_data/test4-out.json", None, None),
    ("test_data/test5-in.html", "test_data/test5-out.json", None, None),
    ("test_data/test6-in.html", "test_data/test6-out.json", None, None),
    ("test_data/test7-in.html", "test_data/test7-out.json", None, None),
    ("test_data/test8-in.html", "test_data/test8-out.json", None, None),
    ("test_data/test9-in.html", "test_data/test9-out.json", None, None),
    ("test_data/test10-in.html", "test_data/test10-out.json", None, None),
    ("test_data/test11-in.html", "test_data/test11-out.json", None, None),
    ("test_data/test12-in.html", "test_data/test12-out.json", None, "first_row"),
    ("test_data/test13-in.html", "test_data/test13-out.json", None, "first_column"),
    ("test_data/test14-in.html", "test_data/test14-out.json", None, None),
    ("test_data/test15-in.html", "test_data/test15-out.json", None, None),
    ("test_data/test16-in.html", "test_data/test16-out.json", None, None),
    ("test_data/test17-in.html", "test_data/test17-out.json", None, None),
    ("test_data/test18-in.html", "test_data/test18-out.json", None, None),
]


@pytest.mark.parametrize("in_file, out_file, title, default_header_line", INPUTS)
def test_main(mocker, in_file, out_file, title, default_header_line):
    from ParseHTMLTables import main

    with open(in_file) as f:
        value = f.read()

    with open(out_file) as f:
        expected = json.loads(f.read())

    mocker.patch.object(
        demisto, "args", return_value={"value": value, "title": title, "default_header_line": default_header_line}
    )
    mocker.patch.object(demisto, "results")
    main()
    assert demisto.results.call_count == 1
    results = demisto.results.call_args[0][0]
    assert json.dumps(results) == json.dumps(expected)