scraper

import requests
import lxml.html
import cssselect

req = requests.get('http://tdcj.state.tx.us/unit_directory/')
root = lxml.html.fromstring(req.text)

tables = root.cssselect('table')
table = tables[0]

rows = table.cssselect('tr')
rows = rows[1:]

for row in rows:
    cells = row.cssselect('td')
    print cells[0].text_content()
    print cells[0].get('href')
    raw_input()