def main():
jardines = files.readJsonFile("jardines.json")["jardines"]
info = []
for jardin in jardines:
info.append(getAdditionalInfo(jardin))
time.sleep(5)
files.save_as_json_2('jardinesInfoDetallada.json', info)
def main():
data = {}
soup = request.get_content_parsed("https://guia-capital-federal.escuelasyjardines.com.ar/guia-jardines-de-infantes-en-capital-federal-belgrano.htm")
paginas = parsePaginator(soup)
data["jardines"] = parseJardines(soup)
data["paginas"] = paginas
for pagina in paginas:
data["jardines"] = data["jardines"] + parseJardinesPerPage(pagina)
files.save_as_json_2('jardines.json', data)
def initOutputFile(candidates):
if (files.exists('sources/resultsGoGoDuck.json')):
print "File already exists"
else:
def createInitCandidate(candidate):
data = {}
data["nombre"] = candidate["nombre"]
data["apellido"] = candidate["apellido"]
data["distrito"] = candidate["distrito"]
data["processed"] = False
return data
results = map(lambda x: createInitCandidate(x), candidates)
files.save_as_json_2('sources/resultsGoGoDuck.json', results)
def main():
initOutputFile(repository.findCandidatesWithoutResources())
candidates = files.readJsonFile('sources/resultsGoGoDuck.json')
processed = []
for candidate in candidates:
if ((not candidate["processed"]) and (len(processed) <= 50)):
result = findCandidateResources(
matcher.normalize(candidate["nombre"]),
matcher.normalize(candidate["apellido"]),
matcher.normalize(candidate["distrito"]))
candidate["resources"] = result["resources"]
candidate["url"] = result["url"]
if (len(result["resources"]) > 0):
candidate["processed"] = True
processed.append(candidate)
print "candidates processed {}: {} ".format(
result["url"], len(processed))
time.sleep(10) # seconds
files.save_as_json_2('sources/resultsGoGoDuck.json', candidates)
def main():
precandidates = files.readJsonFile('sources/paso2017.json')
output = map(precandidates)
files.save_as_json_2('sources/boletas.json', output)
def main():
results = files.readJsonFile('sources/cleanedResultsGoGoDuck.json')
cleanedResults = map(cleanResult, results)
files.save_as_json_2('sources/cleanedResultsGoGoDuck.json', cleanedResults)
def main():
data = request.get_content(
"http://olcreativa.lanacion.com.ar/dev/get_url/?key2=1mIchf9frOP7w9IJfqIC7QJ28VB0SwwfAB2bJqP4AaBM&gid=0&output=json"
)
jsonOutput = process(data)
files.save_as_json_2('sources/paso2017.json', jsonOutput)