scrape.py

from bs4 import BeautifulSoup
import lxml
import requests
import pandas as pd
from tabulate import tabulate

soup = BeautifulSoup(open('test.html'), 'lxml')

table = soup.find_all('table')[1]

n_columns = 12
n_rows = len(table.find_all('tr')) - 1
df = pd.DataFrame(columns = range(0,n_columns), index= range(0,n_rows))

row_marker = 0	
for row in table.find_all('tr'):
    column_marker = 0
    columns = row.find_all('td')
    for column in columns:
        df.iat[row_marker,column_marker] = column.get_text()
        column_marker += 1
    if len(columns) > 0:
    	df.iat[row_marker,2] = "http://apac-helpdesk-newtickets/"+column.get('id')
        row_marker += 1

del df[0]

df.to_csv('test.csv', encoding='utf-8')
d=d=df[df[4].str.contains("Web Hosting L2|Email Hosting")]

d=d.sort_values([8], ascending=[True])
print tabulate(d, headers='keys', tablefmt='psql')