Code to parse the html found here http://www.capitol.state.tx.us/BillLookup/History.aspx?LegSess=83R&Bill=HB5 and produce a json version

texas_leg_html_parse

# coding=UTF-8

import sys
import re
import json
from dateutil import parser
from bs4 import BeautifulSoup

if len(sys.argv) != 2:
    print "usage: parse_bill_html.py <bill_html>"
    exit(-1)

bill = {}

leg_map_83rd = {
    #senators
    "Birdwell": "Birdwell, Brian",
    "Campbell": "Campbell, Donna",
    "Carona": "Carona, John",
    "Davis": "Davis, Wendy",
    "Deuell": "Deuell, Bob",
    "Dewhurst": "Dewhurst, David",
    "Duncan": "Duncan, Robert",
    "Ellis": "Ellis, Rodney",
    "Eltife": "Eltife, Kevin",
    "Estes": "Estes, Craig",
    "Fraser": "Fraser, Troy",
    "Garcia": "Garcia, Sylvia",
    "Hancock": "Hancock, Kelly",
    "Hegar": "Hegar, Glenn",
    "Hinojosa": "Hinojosa, Juan",
    "Huffman": "Huffman, Joan",
    "Lucio": "Lucio, Eddie Jr.",
    "Nelson": "Nelson, Jane",
    "Nichols": "Nichols, Robert",
    "Patrick": "Patrick, Dan",
    "Paxton": "Paxton, Ken",
    u"Rodríguez": "Rodríguez, José",
    "Schwertner": "Schwertner, Charles",
    "Seliger": "Seliger, Kel",
    "Taylor": "Taylor, Larry",
    "Uresti": "Uresti, Carlos",
    "Van de Putte": "Van de Putte, Leticia",
    "Watson": "Watson, Kirk",
    "West": "West, Royce",
    "Whitmire": "Whitmire, John",
    "Williams": "Williams, Tommy",
    "Zaffirini": "Zaffirini, Judith",

    #house
    "Allen": "Allen, Alma",
    "Alonzo": "Alonzo, Roberto",
    "Alvarado": "Alvarado, Carol",
    "Anchia": "Anchia, Rafael",
    "Anderson": "Anderson, Charles",
    "Ashby": "Ashby, Trent",
    "Aycock": "Aycock, Jimmie Don",
    "Bell": "Bell, Cecil",
    "Bohac": "Bohac, Dwayne",
    "Bonnen, Dennis": "Bonnen, Dennis",
    "Bonnen, Greg": "Bonnen, Greg",
    "Branch": "Branch, Dan",
    "Burkett": "Burkett, Cindy",
    "Burnam": "Burnam, Lon",
    "Button": "Button, Angie",
    "Callegari": "Callegari, Bill",
    "Canales": "Canales, Terry",
    "Capriglione": "Capriglione, Giovanni",
    "Carter": "Carter, Stefani",
    "Clardy": "Clardy, Travis",
    "Coleman": "Coleman, Garnet",
    "Collier": "Collier, Nicole",
    "Cook": "Cook, Byron",
    "Cortez": "Cortez, Philip",
    "Craddick": "Craddick, Tom",
    "Creighton": "Creighton, Brandon",
    "Crownover": "Crownover, Myra",
    "Dale": "Dale, Tony",
    "Darby": "Darby, Drew",
    "Davis, John": "Davis, John",
    "Davis, Sarah": "Davis, Sarah",
    "Davis, Yvonne": "Davis, Yvonne",
    "Deshotel": "Deshotel, Joe",
    "Dukes": "Dukew, Dawnna",
    "Dutton": "Dutton, Harold V. Jr.",
    "Eiland": "Eiland, Craig",
    "Elkins": "Elkins, Gary",
    "Fallon": "Fallon, Pat",
    "Farias": "Farias, Joe",
    "Farney": "Farney, Marsha",
    "Farrar": "Farrar, Jessica",
    "Fletcher": "Fletcher, Allen",
    "Flynn": "Flynn, Dan",
    "Frank": "Frank, James",
    "Frullo": "Frullo, John",
    "Geren": "Geren, Charlie",
    "Giddings": "Giddings, Helen",
    "Goldman": "Goldman, Craig",
    "Gonzales, Larry": "Gonzales, Larry",
    "Gonzalez, Naomi": "Gonzalez, Naomi",
    u"González, Mary": u"González, Mary",
    "Gooden": "Gooden, Lance",
    "Guerra": 'Guerra, Robert. D.',
    "Guillen": "Guillen, Ryan",
    "Gutierrez": "Gutierrez, Roland",
    "Harless": "Harless, Patricia",
    "Harper-Brown": "Harper-Brown, Linda",
    "Hernandez Luna": "Hernandez Luna, Ana",
    "Herrero": "Herrero, Abel",
    "Hilderbran": "Hilderbran, Harvey",
    "Howard": "Howard, Donna",
    "Huberty": "Huberty, Dan",
    "Hughes": "Hughes, Bryan",
    "Hunter": "Hunter, Todd",
    "Isaac": "Issac, Jason",
    "Israel": "Usrael, Celia",
    "Johnson": "Johnson, Eric",
    "Kacal": "Kacal, Kyle",
    "Keffer": "Keffer, Jim",
    "King, Ken": "King, Ken",
    "King, Phil": "King, Phil",
    "King, Susan": "King, Susan",
    "King, Tracy O.": "King, Tracy O.",
    "Kleinschmidt": "Kleinschmidt, Tim",
    "Klick": "Klick, Stephanie",
    "Kolkhorst": "Kolkhorst, Lois",
    "Krause": "Krause, Matt",
    "Kuempel": "Kuempel, John",
    "Larson": "Larson, Lyle",
    "Laubenberg": "Laubenberg, Jodie",
    "Lavender": "Lavender, George",
    "Leach": "Leach, Jeff",
    "Lewis": "Lewis, Tryon",
    "Longoria": "Longoria, Oscar",
    "Lozano": "Lozano, Jose Manuel",
    "Lucio III": "Lucio, Eddie III",
    "Martinez Fischer": "Martinez Fischer, Trey",
    'Martinez, "Mando"': "Martinez, Armando",
    "McClendon": "McClendon, Ruth",
    u"Menéndez": u"Menéndez, José",
    "Miles": "Miles, Borris",
    "Miller, Doug": "Miller, Doug",
    "Miller, Rick": "Miller, Rick",
    "Moody": "Moody, Joe",
    "Morrison": "Morrison, Geanie",
    "Murphy": "Murphy, Jim",
    u"Muñoz, Jr.": u"Muñoz, Sergio Jr.",
    u"Márquez": u"Márquez, Marisa",
    "Naishtat": "Naishtat, Elliott",
    u"Nevárez": u"Nevárez, Poncho",
    "Oliveira": u"Oliveira, René",
    "Orr": "Orr, Rob",
    "Otto": "Otto, John",
    "Paddie": "Paddie, Chris",
    "Parker": "Parker, Tan",
    "Patrick, Diane": "Patrick, Diane",
    "Perez": "Perez, Mary Ann",
    "Perry": "Perry, Charles",
    "Phillips": "Phillips, Larry",
    "Pickett": "Pickett, Joseph",
    "Pitts": "Pitts, Jim",
    "Price": 'Price, Walter "Four"',
    "Raney": "Raney, John",
    "Ratliff": "Ratliff, Bennett",
    "Raymond": u"Raymond, Richard Peña",
    "Reynolds": "Reynolds, Ron",
    "Riddle": "Riddle, Debbie",
    "Ritter": "Ritter, Allan",
    "Rodriguez, Eddie": "Rodriguez, Eddie",
    "Rodriguez, Justin": "Rodriguez, Justin",
    "Rose": "Rose, Toni",
    "Sanford": "Sanford, Scott",
    "Schaefer": "Schaefer, Matt",
    "Sheets": "Sheets, Kenneth",
    "Sheffield, J. D.": "Sheffield, Jesse David",
    "Sheffield, Ralph": "Sheffield, Ralph",
    "Simmons": "Simmons, Ron",
    "Simpson": "Simpson, David",
    "Smith": "Smith, Wayne",
    "Smithee": "Smithee, John",
    "Springer": "Springer, Drew",
    "Stephenson": "Stephenson, Phil",
    "Stickland": "Stickland, Jonathan",
    "Strama": "Strama, Mark",
    "Straus": "Straus, Joe",
    "Taylor, Van": "Taylor, Van",
    "Thompson, Ed": "Thompson, Ed",
    "Thompson, Senfronia": "Thompson, Senfronia",
    "Toth": "Toth, Steve",
    "Turner, Chris": "Turner, Chris",
    "Turner, Scott": "Turner, Scott",
    "Turner, Sylvester": "Turner, Sylvester",
    "Villalba": "Villalba, Jason",
    "Villarreal": "Villarreal, Mike",
    "Vo": "Vo, Hubert",
    "Walle": "Walle, Armando",
    "White": "White, James",
    "Workman": "Workman, Paul",
    "Wu": "Wu, Gene",
    "Zedler": "Zedler, Bill",
    "Zerwas": "Zerwas, John",
}


html_doc = open(sys.argv[1]).read()

soup = BeautifulSoup(html_doc)

#Get last action date

if soup.find(id="cellLastAction"):
    last_action_date = soup.find(id="cellLastAction").text.split(" ", 1)[0]
else:
    last_action_date = "2013"

authors = []
if soup.find(id="cellAuthors"):
    authors = [x.strip() for x in soup.find(id="cellAuthors").text.split("|")]

co_authors = []
if soup.find(id="cellCoauthors"):
    co_authors = [x.strip() for x in soup.find(id="cellCoauthors").text.split("|")]

sponsors = []
if soup.find(id="cellSponsors"):
    sponsors = [x.strip() for x in soup.find(id="cellSponsors").text.split("|")]

co_sponsors = []
if soup.find(id="cellCosponsors"):
    co_sponsors = [x.strip() for x in soup.find(id="cellCosponsors").text.split("|")]

subject_list = []
if soup.find(id="cellSubjects"):
    subjects = soup.find(id="cellSubjects").contents

    for i in subjects:
        if i.string:
            subject_list.append(i.string)



if last_action_date.strip() != "":
    #Try to parse dates into yyyy-mm-dd format only if date is non-blank
    try:
        d = parser.parse(last_action_date)
        last_action_date = d.strftime("%Y-%m-%d")
    except:
        pass

bill["date"] = last_action_date
bill["filename"] = sys.argv[1]

bill["authors"] = []
for author in authors:
    bill["authors"].append(leg_map_83rd[author])

bill["co_authors"] = []
for co_author in co_authors:
    bill["co_authors"].append(leg_map_83rd[co_author])

bill["sponsors"] = []
for sponsor in sponsors:
    bill["sponsors"].append(leg_map_83rd[sponsor])

bill["co_sponsors"] = []
for co_sponsor in co_sponsors:
    if co_sponsor.strip() != "":
        bill["co_sponsors"].append(leg_map_83rd[co_sponsor])

bill["subjects"] = []
for subject in subject_list:
    subject = re.sub("\(.*\)", "", subject)
    subject = subject.replace("--", " - ")
    subject = subject.strip()
    if subject.isupper():
        subject = subject.title()
    bill["subjects"].append(subject)

print json.dumps(bill, sort_keys=True, indent=4, separators=(',', ': '))