Extracting data from HTML table

undef $/;
$text = <DATA>;

@tabs = $text =~ m!<table.*?>(.*?)</table>!gms;
for (@tabs) {
    @th = m!<th>(.*?)</th>!gms;
    @td = m!<td>(.*?)</td>!gms;
}
for $i (0..$#th) {
    printf "%-16st: %sn", $th[$i], $td[$i];
}

__DATA__
<table class="details" border="0" cellpadding="5" cellspacing="2" width="95%">
<tr valign="top">
<th>Tests</th>
<th>Failures</th>
<th>Success Rate</th>
<th>Average Time</th>
<th>Min Time</th>
<th>Max Time</th>
</tr>
<tr valign="top" class="Failure">
<td>103</td>
<td>24</td>
<td>76.70%</td>
<td>71 ms</td>
<td>0 ms</td>
<td>829 ms</td>
</tr>
</table>

output as follows:

Tests               : 103
Failures            : 24
Success Rate        : 76.70%
Average Time        : 71 ms
Min Time            : 0 ms
Max Time            : 829 ms

A Python solution that uses only the standard library (takes advantage of the fact that the HTML happens to be well-formed XML). More than one row of data can be handled.

(Tested with Python 2.6 and 2.7. The question was updated saying that the OP uses Python 2.4, so this answer may not be very useful in this case. ElementTree was added in Python 2.5)

from xml.etree.ElementTree import fromstring

HTML = """
<table class="details" border="0" cellpadding="5" cellspacing="2" width="95%">
  <tr valign="top">
    <th>Tests</th>
    <th>Failures</th>
    <th>Success Rate</th>
    <th>Average Time</th>
    <th>Min Time</th>
    <th>Max Time</th>
  </tr>
  <tr valign="top" class="Failure">
    <td>103</td>
    <td>24</td>
    <td>76.70%</td>
    <td>71 ms</td>
    <td>0 ms</td>
    <td>829 ms</td>
  </tr>
  <tr valign="top" class="whatever">
    <td>A</td>
    <td>B</td>
    <td>C</td>
    <td>D</td>
    <td>E</td>
    <td>F</td>
  </tr>
</table>"""

tree = fromstring(HTML)
rows = tree.findall("tr")
headrow = rows[0]
datarows = rows[1:]

for num, h in enumerate(headrow):
    data = ", ".join([row[num].text for row in datarows])
    print "{0:<16}: {1}".format(h.text, data)

Output:

Tests           : 103, A
Failures        : 24, B
Success Rate    : 76.70%, C
Average Time    : 71 ms, D
Min Time        : 0 ms, E
Max Time        : 829 ms, F

Assuming your html code is stored in a mycode.html file, here is a bash way:

paste -d: <(grep '<th>' mycode.html | sed -e 's,</*th>,,g') <(grep '<td>' mycode.html | sed -e 's,</*td>,,g')

note: the output is not perfectly aligned

Here is the top answer, adapted for Python3 compatibility, and improved by stripping whitespace in cells:

from bs4 import BeautifulSoup

html = """
  <table class="details" border="0" cellpadding="5" cellspacing="2" width="95%">
    <tr valign="top">
      <th>Tests</th>
      <th>Failures</th>
      <th>Success Rate</th>
      <th>Average Time</th>
      <th>Min Time</th>
      <th>Max Time</th>
   </tr>
   <tr valign="top" class="Failure">
     <td>103</td>
     <td>24</td>
     <td>76.70%</td>
     <td>71 ms</td>
     <td>0 ms</td>
     <td>829 ms</td>
  </tr>
</table>"""

soup = BeautifulSoup(s, 'html.parser')
table = soup.find("table")

# The first tr contains the field names.
headings = [th.get_text().strip() for th in table.find("tr").find_all("th")]

print(headings)

datasets = []
for row in table.find_all("tr")[1:]:
    dataset = dict(zip(headings, (td.get_text() for td in row.find_all("td"))))
    datasets.append(dataset)

print(datasets)

Below is a python regex based solution that I have tested on python 2.7. It doesn’t rely on xml module–so will work in case xml is not fully well formed.

import re
# input args: html string
# output: tables as a list, column max length
def extract_html_tables(html):
  tables=[]
  maxlen=0
  rex1=r'<table.*?/table>'
  rex2=r'<tr.*?/tr>'
  rex3=r'<(td|th).*?/(td|th)>'
  s = re.search(rex1,html,re.DOTALL)
  while s:
    t = s.group()  # the table
    s2 = re.search(rex2,t,re.DOTALL)
    table = []
    while s2:
      r = s2.group() # the row 
      s3 = re.search(rex3,r,re.DOTALL)
      row=[]
      while s3:
        d = s3.group() # the cell
        #row.append(strip_tags(d).strip() )
        row.append(d.strip() )

        r = re.sub(rex3,'',r,1,re.DOTALL)
        s3 = re.search(rex3,r,re.DOTALL)

      table.append( row )
      if maxlen<len(row):
        maxlen = len(row)

      t = re.sub(rex2,'',t,1,re.DOTALL)
      s2 = re.search(rex2,t,re.DOTALL)

    html = re.sub(rex1,'',html,1,re.DOTALL)
    tables.append(table)
    s = re.search(rex1,html,re.DOTALL)
  return tables, maxlen

html = """
  <table class="details" border="0" cellpadding="5" cellspacing="2" width="95%">
    <tr valign="top">
      <th>Tests</th>
      <th>Failures</th>
      <th>Success Rate</th>
      <th>Average Time</th>
      <th>Min Time</th>
      <th>Max Time</th>
   </tr>
   <tr valign="top" class="Failure">
     <td>103</td>
     <td>24</td>
     <td>76.70%</td>
     <td>71 ms</td>
     <td>0 ms</td>
     <td>829 ms</td>
  </tr>
</table>"""
print extract_html_tables(html)

Use pandas.read_html:

import pandas as pd
html_tables = pd.read_html('resources/test.html')
df = html_tables[0]
df.T # transpose to align
                   0
Tests            103
Failures          24
Success Rate  76.70%
Average Time   71 ms