In the game of web scraping, you win... or you die.

doggr.py

from urllib import request
from sys import argv, stdout, stderr
from time import sleep
from random import randrange
import re

def main(argv):
    if len(argv) == 1:
        try:
            with open(argv[0], 'r') as f:
                apis = [l.rstrip() for l in f]
        except:
            apis = argv
    else:
        apis = argv

    apis = [api if len(api) == 8 else api[2:10] for api in apis]

    output = []

    for api in apis:
        res = request.urlopen(
                'http://opi.consrv.ca.gov/opi/opi.dll/'
                'Search?UsrP_ID=100100100&WMtr_APINumber={0}'.format(api))
        welldata = res.read().decode('ascii')

        sleep(0.1)

        if 'frameset' in welldata:
            pool = process_single(welldata)
            output.append(('04' + api + '0000',) + pool)
        else:
            pools = process_multiple(welldata)
            for pool in pools:
                output.append(('04' + api + '0000',) + pool)

        sleep(0.1)

    stdout.write('\t'.join(('API', 'Pool', 'Pool Status', 'Well Type')) + '\n')
    stdout.write('\n'.join('\t'.join(rec) for rec in output))

def process_single(wellpage):
    headerframe = 'http://opi.consrv.ca.gov' + \
        re.search(r'HeaderFrame" src="([^"]+)"', wellpage).group(1)
    headerdata = request.urlopen(headerframe).read().decode('ascii')
    pool = re.search(
            r'Pool:.*?<input type="text".*?value\s*=\s*"([^"]+)"',
            headerdata).group(1)
    pool_status = re.search(
            r'Pool Status:.*?<input type="text".*?value\s*=\s*"([^"]+)"',
            headerdata).group(1)
    well_type = re.search(
            r'Well Type:.*?<input type="text".*?value\s*=\s*"([^"]+)"',
            headerdata).group(1)
    return (pool, pool_status, well_type)

def process_multiple(wellpage):
    pages = int(re.search(r'Page 1 of (\d+)', wellpage).group(1))
    if pages > 1:
        raise 'Too many pages, for now.'
    pools = [m.group(1).replace('&nbsp', '') for m in re.finditer(
        r'<tr class=record>(?:<td>.*?<\/td>){18}<td>(.*?)</td>', wellpage)]
    pool_statii = [m.group(1).replace('&nbsp', '') for m in re.finditer(
        r'<tr class=record>(?:<td>.*?<\/td>){9}<td>(.*?)</td>', wellpage)]
    well_types = [m.group(1).replace('&nbsp', '') for m in re.finditer(
        r'<tr class=record>(?:<td>.*?<\/td>){8}<td>(.*?)</td>', wellpage)]
    return zip(pools, pool_statii, well_types)


if __name__ == '__main__':
    if len(argv) <= 1:
        print('Usage: {0} [api-file|api-list...]'.format(argv[0]), file=stderr)
        quit()
    main(argv[1:])