Initial commit

"san_francisco_ca","37.775","-122.4183""new_york_ny","40.7142","-74.0064""boulder_co","40.015","-105.27""pittsburgh_pa","40.4406","-79.9961""redmond_wa","47.6742","-122.1203""dallas_tx","32.7833","-96.8""seattle_wa","47.6064","-122.3308""washington_dc","38.69","-77.03""tempe_az","33.4147","-111.9086"

 No newline at end of file

from rdflib.Graph import ConjunctiveGraph

from rdflib import Namespace, BNode, Literal, RDF, URIRef

import csv

import pysesame

JOBS = Namespace("http://www.medev.ac.uk/interoperability/rss/1.0/modules/jobs/rss1.0jobsmodule#")

DC = Namespace("http://purl.org/dc/elements/1.1/")

JB = Namespace("http://semprog.com/schemas/jobboard#")

COMPANY = Namespace("http://purl.org/rss/1.0/modules/company/")

RDFS=Namespace('http://www.w3.org/2000/01/rdf-schema#')

jg=ConjunctiveGraph()

jg.bind('jobs',JOBS)

jg.bind('dc',DC)

jg.bind('jobboard',JB)

jg.bind('company',COMPANY)

jg.bind('rdfs',RDFS)

# Incremental counter for vacancy IDs

vid=0

for title,salary,location,company,crunchbase,ticker in csv.reader(file('joblist.csv')):

    # Create the vacancy

    vid+=1

    vacancy=JB[str(vid)]

    jg.add((vacancy,RDF.type,JOBS['Vacancy']))

    jg.add((vacancy,DC['title'],Literal(title)))

    location_id=location.lower().replace(' ','_').replace(',','')

    jg.add((vacancy,JB['location'],JB[location_id]))

    jg.add((JB[location_id],DC['title'],Literal(location)))

    # Salary range

    salaryrange=BNode()

    jg.add((vacancy,JOBS['salaryrange'],salaryrange))

    jg.add((salaryrange,JOBS['minimumsalary'],Literal(float(salary))))

    # Create the company

    cnode=JB[company.lower().replace(' ','_')]

    jg.add((vacancy,JOBS['vacancywith'],cnode))

    jg.add((cnode,RDF.type,JOBS['Organization']))

    # Ticker symbol

    if ticker!="":

        jg.add((cnode,COMPANY['symbol'],Literal(ticker)))

    jg.add((cnode,COMPANY['name'],Literal(company)))

    # Crunchbase (see also)

    if crunchbase!="":

        jg.add((cnode,RDFS['seeAlso'],

                Literal('http://api.crunchbase.com/v/1/company/%s.js' % crunchbase)))

# Print the serialized graph

data=jg.serialize(format='xml')

print data

#c=pysesame.connection('http://freerisk.org:8280/openrdf-sesame/')

#c.use_repository('joblistings')

#print c.postdata(data)

from rdflib.Graph import ConjunctiveGraph

from rdflib import Namespace, BNode, Literal, RDF, URIRef

from pysesame import connection

import urllib

from simplejson import loads

# Connecion to Sesame

con=connection('http://freerisk.org:8280/openrdf-sesame/')

con.use_repository('joblistings')

con.addnamespace('rdfs','http://www.w3.org/2000/01/rdf-schema#')

JB = Namespace("http://semprog.com/schemas/jobboard#")

DC = Namespace("http://purl.org/dc/elements/1.1/")

FOAF = Namespace("http://xmlns.com/foaf/0.1/")

cg=ConjunctiveGraph()

cg.bind('dc',DC)

cg.bind('jobboard',JB)

cg.bind('foaf',FOAF)

# Find seeAlso URLs containing Crunchbase

res=con.query('select ?id ?url where {?id rdfs:seeAlso ?url . FILTER regex(?url, "crunchbase")}')

# Loop over the results

for row in res:

    company=URIRef(row['id']['value'])

    url=row['url']['value']

    data=urllib.urlopen(url).read()

    record=loads(data)

    # Add company locations

    for loc in record['offices']:

        if loc['city'] and loc['state_code']:

            cityid='%s_%s' % (loc['city'].lower().replace(' ','_'),loc['state_code'].lower())

            cg.add((company,JB['location'],JB[cityid]))

    # Add URL

    cg.add((company,FOAF['homepage'],Literal(record['homepage_url'])))

    # Add funding rounds

    for fr in record['funding_rounds']:

        round=BNode()

        cg.add((company,JB['funding_round'],round))

        cg.add((round,JB['amount'],Literal(fr['raised_amount'])))

        cg.add((round,DC['date'], Literal(str(fr['funded_year']))))

data=cg.serialize(format='xml')

print data

#c=pysesame.connection('http://freerisk.org:8280/openrdf-sesame/')

#c.use_repository('joblistings')

#print c.postdata(data)