diff --git a/AV_Data_Capture.py b/AV_Data_Capture.py index b6b65b6..8ac0d9c 100755 --- a/AV_Data_Capture.py +++ b/AV_Data_Capture.py @@ -8,7 +8,7 @@ import typing import urllib3 import config -from datetime import datetime +from datetime import datetime, timedelta import time from pathlib import Path from ADC_function import file_modification_days, get_html, is_link @@ -58,7 +58,7 @@ Use --log-dir= to turn off logging feature.""") class OutLogger(object): def __init__(self, logfile) -> None: self.term = sys.stdout - self.log = open(logfile,"w",encoding='utf-8') + self.log = open(logfile,"w",encoding='utf-8',buffering=1) def __del__(self): self.close() def __enter__(self): @@ -84,7 +84,7 @@ class OutLogger(object): class ErrLogger(OutLogger): def __init__(self, logfile) -> None: self.term = sys.stderr - self.log = open(logfile,"w",encoding='utf-8') + self.log = open(logfile,"w",encoding='utf-8',buffering=1) def close(self): if self.term != None: sys.stderr = self.term @@ -126,14 +126,6 @@ def close_logfile(logdir: str): pass -_print = print # Hook print -_stdout = sys.stdout -def print(*args, **kw): - _print(*args, **kw) - if _stdout != sys.stdout: - sys.stdout.flush() - - # 重写视频文件扫描,消除递归,取消全局变量,新增失败文件列表跳过处理 def movie_lists(root, conf, regexstr): escape_folder = re.split("[,,]", conf.escape_folder()) @@ -325,7 +317,7 @@ if __name__ == '__main__': count = 0 count_all = str(len(movie_list)) - print('[+]Find', count_all, 'movies') + print('[+]Find', count_all, 'movies. Start at', time.strftime("%Y-%m-%d %H:%M:%S")) main_mode = conf.main_mode() stop_count = conf.stop_counter() if stop_count<1: @@ -351,8 +343,9 @@ f'[!]运行模式:**维护模式**,本程序将在处理{count_all}个视频 rm_empty_folder(folder_path) end_time = time.time() - total_time = end_time - start_time - print("[+]Used " + str(round(total_time,2)) + "s") + total_time = str(timedelta(seconds=end_time - start_time)) + print("[+]Running time", total_time[:len(total_time) if total_time.rfind('.') < 0 else -3], + " End at", time.strftime("%Y-%m-%d %H:%M:%S")) print("[+]All finished!!!") if not (conf.auto_exit() or auto_exit): diff --git a/WebCrawler/carib.py b/WebCrawler/carib.py index f4fa9c0..8eee1af 100755 --- a/WebCrawler/carib.py +++ b/WebCrawler/carib.py @@ -39,7 +39,7 @@ def main(number: str) -> json: 'extrafanart': get_extrafanart(lx), 'label': get_series(lx), 'imagecut': 1, - 'actor_photo': get_actor_photo(browser), +# 'actor_photo': get_actor_photo(browser), 'website': 'https://www.caribbeancom.com/moviepages/' + number + '/index.html', 'source': 'carib.py', 'series': get_series(lx), diff --git a/WebCrawler/xcity.py b/WebCrawler/xcity.py index f531470..a7b4cff 100644 --- a/WebCrawler/xcity.py +++ b/WebCrawler/xcity.py @@ -109,7 +109,8 @@ def getTag(a): for i in result1: i=i.replace(u'\n','') i=i.replace(u'\t','') - result2.append(i) + if len(i): + result2.append(i) return result2 @@ -217,7 +218,7 @@ def main(number): 'tag': getTag(detail_page), 'label': getLabel(detail_page), 'year': getYear(getRelease(detail_page)), # str(re.search('\d{4}',getRelease(a)).group()), - 'actor_photo': getActorPhoto(browser), +# 'actor_photo': getActorPhoto(browser), 'website': url, 'source': 'xcity.py', 'series': getSeries(detail_page),