def do_stuff(): # Get rid of the older file in order to create a new file common_lib.delete_file(common_lib.TICKER_FILE_DIR + common_lib.OUTPUT_FILENAME) # Download data from the web for x in range(3): if x == 0: exchangeName = "nasdaq" elif x == 1: exchangeName = "nyse" elif x == 2: exchangeName = "amex" write_stock_tickers(exchangeName) # Start combining aggregate data into one file for x in range(0, 3): if x == 0: exchangeName = "nasdaq" elif x == 1: exchangeName = "nyse" elif x == 2: exchangeName = "amex" combine_all_data_into_one_file(exchangeName) print("function end for " + exchangeName + ".csv") concatenateStr = '"Symbol","Name","LastSale","MarketCap","ADR TSO","IPOyear","Sector","Industry","Summary Quote",\n' readStr = common_lib.open_file(common_lib.TICKER_FILE_DIR + "tmpFile.txt") targetStr = open(common_lib.TICKER_FILE_DIR + common_lib.OUTPUT_FILENAME, 'a') targetStr.write(concatenateStr) targetStr.write(readStr) targetStr.close() pickup_garbage() return
def combine_all_data_into_one_file(exchangeName): readStr = common_lib.open_file(common_lib.TICKER_FILE_DIR + exchangeName + "Tickers.csv") readStr = parse_stock_tickers_file(readStr) targetStr = open(common_lib.TICKER_FILE_DIR + "tmpFile.txt", 'a') targetStr.write(readStr) targetStr.close() return
def cleanup(): data = common_lib.open_file(common_lib.NBA_LEADING_TEAM_CHAMPION_CHECK_CSV_FILE) if data == 'FileNotFoundError': pass else: data = None from os import remove remove(common_lib.NBA_LEADING_TEAM_CHAMPION_CHECK_CSV_FILE)
def start_main(): data = common_lib.open_file(common_lib.NBA_STANDING_HTML_FILE) data = get_all_expanded_standings(data) while data.find('<a href="/teams/') > 0: data = parse_data_get_true_pct(data) ######################### # while data.find('<td class="team">') > 0: # data = parse_html_file(data) ######################### thisList = common_lib.convert_list_into_str(list_of_team_stats.listOfTeamStats) common_lib.write_file(thisList, common_lib.NBA_STANDING_CSV_FILE)
def start_main(): data = common_lib.open_file(common_lib.NBA_STANDING_HTML_FILE) data = get_all_expanded_standings(data) while data.find('<a href="/teams/') > 0: data = parse_data_get_true_pct(data) ######################### # while data.find('<td class="team">') > 0: # data = parse_html_file(data) ######################### thisList = common_lib.convert_list_into_str( list_of_team_stats.listOfTeamStats) common_lib.write_file(thisList, common_lib.NBA_STANDING_CSV_FILE)
def get_team_champion_from_html(filename): data = common_lib.open_file(filename) # Parsing through the file to get League Champion startPos = data.find('League Champion:') endPos = data.__len__() data = data[startPos:endPos] startPos = data.find('.html">') endPos = data.__len__() data = data[startPos:endPos] startPos = data.find('>') endPos = data.find('</a>') leagueChampion = data[startPos:endPos] leagueChampion = leagueChampion.replace('>', '') return leagueChampion
def start_main(): cleanup() finalList = [] teamList = common_lib.get_multiple_col(NBA_POWER_RANKING_CSV_FILE, 0) leadingTeamsTuple = get_two_leading_teams_of_true_power_ranking(teamList) leadingTeam = leadingTeamsTuple[0] secondLeadingTeam = leadingTeamsTuple[1] championTeam = get_team_champion_from_html(common_lib.NBA_CHAMPION_HTML_FILE) finalsRunnerUpTeam = get_team_finals_runner_up_from_html(common_lib.NBA_CHAMPION_HTML_FILE) # Check if file exist. data = common_lib.open_file(common_lib.NBA_LEADING_TEAM_CHAMPION_CHECK_CSV_FILE) if data == 'FileNotFoundError': finalList.append(['YEAR', 'TRUE_POWER_RANK_LEAD_TEAM', 'TRUE_POWER_RANK_SECOND_LEAD_TEAM', 'CHAMPION_TEAM', 'FINALS_RUNNER_UP_TEAM', 'SAME?']) # if the program cannot find a championTeam, then print 'No Champion'. if not championTeam: championTeam = 'No Champion' if not finalsRunnerUpTeam: finalsRunnerUpTeam = 'No Runner Up' # Check if leadingTeam is the same as championTeam leadingTeam = change_element_into_str(leadingTeam) secondLeadingTeam = change_element_into_str(secondLeadingTeam) if leadingTeam.lower() == championTeam.lower(): sameTeam = True elif leadingTeam.lower() == finalsRunnerUpTeam.lower(): sameTeam = True elif secondLeadingTeam.lower() == championTeam.lower(): sameTeam = True elif secondLeadingTeam.lower() == finalsRunnerUpTeam.lower(): sameTeam = True else: sameTeam = False finalList.append([YEAR, leadingTeam, secondLeadingTeam, championTeam, finalsRunnerUpTeam, sameTeam]) dataStr = common_lib.convert_list_into_str(finalList) dataStr = dataStr + '\n' common_lib.append_file(dataStr, common_lib.NBA_LEADING_TEAM_CHAMPION_CHECK_CSV_FILE)
def get_statements_to_csv(stockFileDir, ticker): #print("in get_statements_to_csv") if ticker != 'Symbol': if(flagLastPriceClass.flagLastPrice == True): get_last_price_to_csv(ticker) elif(flagLastPriceClass.flagLastPrice == False): get_last_price_to_csv(ticker) time.sleep(1) get_everything_else(ticker) # I separated get_last_price_to_csv() from get_everything_else to allow commenting out get_everything_else, # because balance sheets, income statements and cashflow statements doesn't change everyday, # but the last price does. It would be faster this way. # Parse csv files readStr = common_lib.open_file(stockFileDir + ticker + " " + "Income" + " " + "Quarterly" + ".csv") readStr = parse_statements(readStr) common_lib.write_file(readStr, stockFileDir + ticker + " " + "Income" + " " + "Quarterly" + ".csv") # ttmList = get_col_ttm(stockFileDir + ticker + " " + "Income" + " " + "Quarterly" + ".csv") # print(ttmList) return
def get_team_finals_runner_up_from_html(filename): data = common_lib.open_file(filename) # Parsing through the file to get Finals Runner Up startPos = data.find('League Playoffs') endPos = data.__len__() data = data[startPos:endPos] startPos = data.find('Finals</span>') endPos = data.__len__() data = data[startPos:endPos] startPos = data.find('over <a href="') endPos = data.__len__() data = data[startPos:endPos] startPos = data.find('>') endPos = data.find('</a>') runnerUp = data[startPos:endPos] runnerUp = runnerUp.replace('>', '') return runnerUp