mainpage = get_page('http://projects.propublica.org/docdollars/')
majorsoup = BeautifulSoup(mainpage)
States = []
for td in majorsoup.find_all("td",class_="label",style=False)[1:-1]:
States.append(td.string)
g = Graph()
state = BNode()
clinic = BNode()
company = BNode()
transaction = BNode()
payment = BNode()
for state in States:
try:
page = get_page('http://projects.propublica.org/docdollars/states/'+state.replace(' ','-'))
soup = BeautifulSoup(page)
state_txns = soup.find_all('tr') #find all transactions
except urllib2.HTTPError:
print state+' not available'
continue
def track(tag): #get payment information
#clinic info
clinic_name = tag[0].find(class_=False).string
DDsite = tag[0].find(href=True)['href'] #Propublica's docdollars site
city = tag[1].string.strip() #city
state = soup.find("strong").string #state
g.add( (clinic, RDF.type, FOAF.Organization) )
g.add( (clinic, FOAF.name, Literal(clinic_name)) )
