scrape relator codes from Library of Congress - will only work on ScraperWiki

relator_scrape.py

import scraperwiki
import lxml.html

# Grab the page and turn it into an lxml object
html = scraperwiki.scrape("http://www.loc.gov/marc/relators/relaterm.html")
root = lxml.html.fromstring(html)

authorizedList = root.find_class("authorized") # get the title (has class authorized) 
codeList = root.find_class('relator-code') # get the code (has class relator-code) 
codeDict = dict()

# iterate through our elements - add each elem to dictionary
for i in range(len(authorizedList)):
    codeDict = {
        'type' : authorizedList[i].text_content().lower(), 
        'code' : codeList[i].text_content().replace('[','').replace(']','')
    }
    scraperwiki.sqlite.save(unique_keys=['code'], data=codeDict)