def alterarTituloNoticias(): listaNoticias = model.buscarListaNoticias() for noticia in listaNoticias: titulo = noticia[1] if "\u200f" in titulo: titulo = titulo.replace("\u200f", "") titulo = titulo.strip() model.atualizarTituloNoticia(idNoticia = noticia[0], novoTitulo = titulo) print(str(noticia[0]) + "/" + str(len(listaNoticias)) + " - Titulo atualizado") else: print(str(noticia[0]) + "/" + str(len(listaNoticias)))
def extrairCitadosTexto(): listaFamosos = model.buscarListaFamoso() listaNoticias = model.buscarListaNoticias() f = open("arquivoTeste.txt", "w") f2 = open("arquivoTeste2.txt", "w") if listaNoticias != False and listaFamosos != False: for i in listaNoticias[:50]: f.writelines(str(i[1]) + "\n") noticia = {'id': i[0], 'titulo': i[1], 'subtitulo': i[2], 'link': i[3], 'tipo': i[4], 'texto': i[5]} print(str(noticia['titulo'])) bestExtract = extrairCitadosTextoBestExtract(noticia['link'],f2) for j in bestExtract: famoso = {'nome': j[0]} ratioTotal = 0 mediaRatio = 0 nomeCompleto = famoso['nome'] todosNomes = famoso['nome'].split(" ") textoTotal = noticia['titulo'] + " " + noticia['subtitulo'] + " " + noticia['texto'] ratioTotal += fuzz.token_set_ratio(nomeCompleto, textoTotal) if len(todosNomes) > 1: for nome in todosNomes: ratioTotal += fuzz.token_set_ratio(nome, textoTotal) if len(todosNomes) == 1: mediaRatio = ratioTotal elif len(todosNomes) > 1: mediaRatio = ratioTotal / (len(todosNomes) + 1) '''print(str(nomeCompleto) + "," + str(mediaRatio))''' if mediaRatio > 20: f.writelines(str(nomeCompleto) + "," + str(round(mediaRatio,1))+"\n") if mediaRatio > 85: '''model.relacionarFamosoNoticia(famoso['nome'], noticia['id'])''' '''print(" - " + str(nomeCompleto))''' f.close() f2.close()
print("tempo loop:" + str(time.clock() - tempoLoop)) print(str(threadName) + " - " + str(noticia['titulo'])) queueLock.acquire() queueLock.release() threadList = [] numero = 1 while numero <= 1: threadList.append("Thread-" + str(numero)) numero += 1 queueLock = threading.Lock() workQueue = queue.Queue(0) listaNoticias = model.buscarListaNoticias() for noticia in listaNoticias: workQueue.put(noticia) threads = [] threadID = 1 for tName in threadList: thread = myThread(threadID, tName, workQueue) thread.start() threads.append(thread) threadID += 1 time.clock() for t in threads: