def readFile(year): '''Reads the World Cup file and cleans the data''' arqName = '/Users/tulionpl/Desktop/mac.folder/python/classePartida/copa/' + str( year) + '.html' file = open(arqName, 'r', encoding="ISO-8859-1") line = file.readline() page = '' canRead = False while '<tr bgcolor="#000000">' not in line: if '<table cellspacing="1">' in line: canRead = True if canRead: page += line line = file.readline() page = readFiles.removeTags(page) data = page.split('\n') cleanData = [] for dataLine in data: if readFiles.hasAlphanumericChar(dataLine): cleanData.append(dataLine) for i in range(len(cleanData)): cleanData[i] = cleanData[i].strip() Partida.createMatches(cleanData, year) file.close()