bacow/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #698 from naughtyGitCat/master

Browse Source 
typo transalte to translate,and some blank lines
This commit is contained in:
Yoshiko2
2022-02-23 05:28:59 +08:00
committed by GitHub
parent aa0f72edd8 950a4dce13
commit bb0d49ee4e
5 changed files with 235 additions and 166 deletions
Download Patch File Download Diff File Expand all files Collapse all files

86
Movie_Data_Capture.py
View File

@@ -3,18 +3,19 @@ import json
import os import os
import re import re
import sys import sys
import time
import shutil import shutil
import typing import typing
import urllib3 import urllib3
import signal import signal
import platform import platform
import multiprocessing
from datetime import datetime, timedelta
from pathlib import Path
from opencc import OpenCC from opencc import OpenCC
import ADC_function
import config import config
from datetime import datetime, timedelta
import time
from pathlib import Path
from ADC_function import file_modification_days, get_html, parallel_download_files from ADC_function import file_modification_days, get_html, parallel_download_files
from number_parser import get_number from number_parser import get_number
from core import core_main, moveFailedFolder from core import core_main, moveFailedFolder
@@ -44,7 +45,8 @@ def argparse_function(ver: str) -> typing.Tuple[str, str, str, str, bool]:
parser = argparse.ArgumentParser(epilog=f"Load Config file '{conf.ini_path}'.") parser = argparse.ArgumentParser(epilog=f"Load Config file '{conf.ini_path}'.")
parser.add_argument("file", default='', nargs='?', help="Single Movie file path.") parser.add_argument("file", default='', nargs='?', help="Single Movie file path.")
parser.add_argument("-p", "--path", default='', nargs='?', help="Analysis folder path.") parser.add_argument("-p", "--path", default='', nargs='?', help="Analysis folder path.")
parser.add_argument("-m","--main-mode",default='',nargs='?',help="Main mode. 1:Scraping 2:Organizing 3:Scraping in analysis folder") parser.add_argument("-m", "--main-mode", default='', nargs='?',
help="Main mode. 1:Scraping 2:Organizing 3:Scraping in analysis folder")
parser.add_argument("-n", "--number", default='', nargs='?', help="Custom file number of single movie file.") parser.add_argument("-n", "--number", default='', nargs='?', help="Custom file number of single movie file.")
# parser.add_argument("-C", "--config", default='config.ini', nargs='?', help="The config file Path.") # parser.add_argument("-C", "--config", default='config.ini', nargs='?', help="The config file Path.")
default_logdir = str(Path.home() / '.mlogs') default_logdir = str(Path.home() / '.mlogs')
@@ -52,9 +54,12 @@ def argparse_function(ver: str) -> typing.Tuple[str, str, str, str, bool]:
help=f"""Duplicate stdout and stderr to logfiles in logging folder, default on. help=f"""Duplicate stdout and stderr to logfiles in logging folder, default on.
default folder for current user: '{default_logdir}'. Change default folder to an empty file, default folder for current user: '{default_logdir}'. Change default folder to an empty file,
or use --log-dir= to turn log off.""") or use --log-dir= to turn log off.""")
parser.add_argument("-q","--regex-query",dest='regexstr',default='',nargs='?',help="python re module regex filepath filtering.") parser.add_argument("-q", "--regex-query", dest='regexstr', default='', nargs='?',
parser.add_argument("-d","--nfo-skip-days",dest='days',default='',nargs='?', help="Override nfo_skip_days value in config.") help="python re module regex filepath filtering.")
parser.add_argument("-c","--stop-counter",dest='cnt',default='',nargs='?', help="Override stop_counter value in config.") parser.add_argument("-d", "--nfo-skip-days", dest='days', default='', nargs='?',
help="Override nfo_skip_days value in config.")
parser.add_argument("-c", "--stop-counter", dest='cnt', default='', nargs='?',
help="Override stop_counter value in config.")
parser.add_argument("-i", "--ignore-failed-list", action="store_true", help="Ignore failed list '{}'".format( parser.add_argument("-i", "--ignore-failed-list", action="store_true", help="Ignore failed list '{}'".format(
os.path.join(os.path.abspath(conf.failed_folder()), 'failed_list.txt'))) os.path.join(os.path.abspath(conf.failed_folder()), 'failed_list.txt')))
parser.add_argument("-a", "--auto-exit", action="store_true", parser.add_argument("-a", "--auto-exit", action="store_true",
@@ -67,12 +72,16 @@ is performed. It may help you correct wrong numbers before real job.""")
parser.add_argument("-v", "--version", action="version", version=ver) parser.add_argument("-v", "--version", action="version", version=ver)
args = parser.parse_args() args = parser.parse_args()
def get_natural_number_or_none(value): def get_natural_number_or_none(value):
return int(value) if isinstance(value, str) and value.isnumeric() and int(value) >= 0 else None return int(value) if isinstance(value, str) and value.isnumeric() and int(value) >= 0 else None
def get_str_or_none(value): def get_str_or_none(value):
return value if isinstance(value, str) and len(value) else None return value if isinstance(value, str) and len(value) else None
def get_bool_or_none(value): def get_bool_or_none(value):
return True if isinstance(value, bool) and value else None return True if isinstance(value, bool) and value else None
config.G_conf_override["common:main_mode"] = get_natural_number_or_none(args.main_mode) config.G_conf_override["common:main_mode"] = get_natural_number_or_none(args.main_mode)
config.G_conf_override["common:source_folder"] = get_str_or_none(args.path) config.G_conf_override["common:source_folder"] = get_str_or_none(args.path)
config.G_conf_override["common:auto_exit"] = get_bool_or_none(args.auto_exit) config.G_conf_override["common:auto_exit"] = get_bool_or_none(args.auto_exit)
@@ -83,43 +92,53 @@ is performed. It may help you correct wrong numbers before real job.""")
return args.file, args.number, args.logdir, args.regexstr, args.zero_op return args.file, args.number, args.logdir, args.regexstr, args.zero_op
class OutLogger(object): class OutLogger(object):
def __init__(self, logfile) -> None: def __init__(self, logfile) -> None:
self.term = sys.stdout self.term = sys.stdout
self.log = open(logfile, "w", encoding='utf-8', buffering=1) self.log = open(logfile, "w", encoding='utf-8', buffering=1)
self.filepath = logfile self.filepath = logfile
def __del__(self): def __del__(self):
self.close() self.close()
def __enter__(self): def __enter__(self):
pass pass
def __exit__(self, *args): def __exit__(self, *args):
self.close() self.close()
def write(self, msg): def write(self, msg):
self.term.write(msg) self.term.write(msg)
self.log.write(msg) self.log.write(msg)
def flush(self): def flush(self):
self.term.flush() self.term.flush()
self.log.flush() self.log.flush()
os.fsync(self.log.fileno()) os.fsync(self.log.fileno())
def close(self): def close(self):
if self.term != None: if self.term is not None:
sys.stdout = self.term sys.stdout = self.term
self.term = None self.term = None
if self.log != None: if self.log is not None:
self.log.close() self.log.close()
self.log = None self.log = None
class ErrLogger(OutLogger): class ErrLogger(OutLogger):
def __init__(self, logfile) -> None: def __init__(self, logfile) -> None:
self.term = sys.stderr self.term = sys.stderr
self.log = open(logfile, "w", encoding='utf-8', buffering=1) self.log = open(logfile, "w", encoding='utf-8', buffering=1)
self.filepath = logfile self.filepath = logfile
def close(self): def close(self):
if self.term != None: if self.term is not None:
sys.stderr = self.term sys.stderr = self.term
self.term = None self.term = None
if self.log != None:
if self.log is not None:
self.log.close() self.log.close()
self.log = None self.log = None
@@ -254,13 +273,14 @@ def signal_handler(*args):
print('[!]Ctrl+C detected, Exit.') print('[!]Ctrl+C detected, Exit.')
sys.exit(9) sys.exit(9)
def sigdebug_handler(*args): def sigdebug_handler(*args):
config.G_conf_override["debug_mode:switch"] = not config.G_conf_override["debug_mode:switch"] config.G_conf_override["debug_mode:switch"] = not config.G_conf_override["debug_mode:switch"]
print('[!]Debug {}'.format('On' if config.getInstance().debug() else 'oFF')) print('[!]Debug {}'.format('On' if config.getInstance().debug() else 'oFF'))
# 新增失败文件列表跳过处理，及.nfo修改天数跳过处理，提示跳过视频总数，调试模式(-g)下详细被跳过文件，跳过小广告 # 新增失败文件列表跳过处理，及.nfo修改天数跳过处理，提示跳过视频总数，调试模式(-g)下详细被跳过文件，跳过小广告
def movie_lists(source_folder, regexstr): def movie_lists(source_folder, regexstr: str) -> list[str]:
conf = config.getInstance() conf = config.getInstance()
main_mode = conf.main_mode() main_mode = conf.main_mode()
debug = conf.debug() debug = conf.debug()
@@ -311,11 +331,12 @@ def movie_lists(source_folder, regexstr):
continue # file is symlink or hardlink(Linux/NTFS/Darwin) continue # file is symlink or hardlink(Linux/NTFS/Darwin)
# 调试用0字节样本允许通过，去除小于120MB的广告'苍老师强力推荐.mp4'(102.2MB)'黑道总裁.mp4'(98.4MB)'有趣的妹子激情表演.MP4'(95MB)'有趣的臺灣妹妹直播.mp4'(15.1MB) # 调试用0字节样本允许通过，去除小于120MB的广告'苍老师强力推荐.mp4'(102.2MB)'黑道总裁.mp4'(98.4MB)'有趣的妹子激情表演.MP4'(95MB)'有趣的臺灣妹妹直播.mp4'(15.1MB)
movie_size = 0 if is_sym else full_name.stat().st_size # 同上 符号链接不取stat()及st_size，直接赋0跳过小视频检测 movie_size = 0 if is_sym else full_name.stat().st_size # 同上 符号链接不取stat()及st_size，直接赋0跳过小视频检测
if movie_size > 0 and movie_size < 125829120: # 1024*1024*120=125829120 if 0 < movie_size < 125829120: # 1024*1024*120=125829120
continue continue
if cliRE and not cliRE.search(absf) or trailerRE.search(full_name.name): if cliRE and not cliRE.search(absf) or trailerRE.search(full_name.name):
continue continue
if main_mode == 3 and nfo_skip_days > 0 and file_modification_days(full_name.with_suffix('.nfo')) <= nfo_skip_days: if main_mode == 3 and nfo_skip_days > 0 and file_modification_days(
full_name.with_suffix('.nfo')) <= nfo_skip_days:
skip_nfo_days_cnt += 1 skip_nfo_days_cnt += 1
if debug: if debug:
print(f"[!]Skip movie by it's .nfo which modified within {nfo_skip_days} days: '{absf}'") print(f"[!]Skip movie by it's .nfo which modified within {nfo_skip_days} days: '{absf}'")
@@ -325,7 +346,8 @@ def movie_lists(source_folder, regexstr):
if skip_failed_cnt: if skip_failed_cnt:
print(f"[!]Skip {skip_failed_cnt} movies in failed list '{failed_list_txt_path}'.") print(f"[!]Skip {skip_failed_cnt} movies in failed list '{failed_list_txt_path}'.")
if skip_nfo_days_cnt: if skip_nfo_days_cnt:
print(f"[!]Skip {skip_nfo_days_cnt} movies in source folder '{source}' who's .nfo modified within {nfo_skip_days} days.") print(
f"[!]Skip {skip_nfo_days_cnt} movies in source folder '{source}' who's .nfo modified within {nfo_skip_days} days.")
if nfo_skip_days <= 0 or not soft_link or main_mode == 3: if nfo_skip_days <= 0 or not soft_link or main_mode == 3:
return total return total
# 软连接方式，已经成功削刮的也需要从成功目录中检查.nfo更新天数，跳过N天内更新过的 # 软连接方式，已经成功削刮的也需要从成功目录中检查.nfo更新天数，跳过N天内更新过的
@@ -351,13 +373,17 @@ def movie_lists(source_folder, regexstr):
if debug: if debug:
print(f"[!]Skip file successfully processed within {nfo_skip_days} days: '{f}'") print(f"[!]Skip file successfully processed within {nfo_skip_days} days: '{f}'")
if len(rm_list): if len(rm_list):
print(f"[!]Skip {len(rm_list)} movies in success folder '{success_folder}' who's .nfo modified within {nfo_skip_days} days.") print(
f"[!]Skip {len(rm_list)} movies in success folder '{success_folder}' who's .nfo modified within {nfo_skip_days} days.")
return total return total
def create_failed_folder(failed_folder): def create_failed_folder(failed_folder: str):
if not os.path.exists(failed_folder): # 新建failed文件夹 """
新建failed文件夹
"""
if not os.path.exists(failed_folder):
try: try:
os.makedirs(failed_folder) os.makedirs(failed_folder)
except: except:
@@ -370,9 +396,7 @@ def rm_empty_folder(path):
deleted = set() deleted = set()
for current_dir, subdirs, files in os.walk(abspath, topdown=False): for current_dir, subdirs, files in os.walk(abspath, topdown=False):
try: try:
still_has_subdirs = any( still_has_subdirs = any(_ for subdir in subdirs if os.path.join(current_dir, subdir) not in deleted)
_ for subdir in subdirs if os.path.join(current_dir, subdir) not in deleted
)
if not any(files) and not still_has_subdirs and not os.path.samefile(path, current_dir): if not any(files) and not still_has_subdirs and not os.path.samefile(path, current_dir):
os.rmdir(current_dir) os.rmdir(current_dir)
deleted.add(current_dir) deleted.add(current_dir)
@@ -387,7 +411,7 @@ def create_data_and_move(file_path: str, zero_op, oCC):
n_number = get_number(debug, os.path.basename(file_path)) n_number = get_number(debug, os.path.basename(file_path))
file_path = os.path.abspath(file_path) file_path = os.path.abspath(file_path)
if debug == True: if debug is True:
print(f"[!] [{n_number}] As Number making data for '{file_path}'") print(f"[!] [{n_number}] As Number making data for '{file_path}'")
if zero_op: if zero_op:
return return
@@ -456,7 +480,7 @@ def main():
main_mode = conf.main_mode() main_mode = conf.main_mode()
folder_path = "" folder_path = ""
if not main_mode in (1, 2, 3): if main_mode not in (1, 2, 3):
print(f"[-]Main mode must be 1 or 2 or 3! You can run '{os.path.basename(sys.argv[0])} --help' for more help.") print(f"[-]Main mode must be 1 or 2 or 3! You can run '{os.path.basename(sys.argv[0])} --help' for more help.")
sys.exit(4) sys.exit(4)
@@ -467,7 +491,8 @@ def main():
signal.signal(signal.SIGWINCH, sigdebug_handler) signal.signal(signal.SIGWINCH, sigdebug_handler)
dupe_stdout_to_logfile(logdir) dupe_stdout_to_logfile(logdir)
platform_total = str(' - ' + platform.platform() + ' \n[*] - ' + platform.machine() + ' - Python-' + platform.python_version()) platform_total = str(
' - ' + platform.platform() + ' \n[*] - ' + platform.machine() + ' - Python-' + platform.python_version())
print('[*]================= Movie Data Capture =================') print('[*]================= Movie Data Capture =================')
print('[*]' + version.center(54)) print('[*]' + version.center(54))
@@ -504,6 +529,7 @@ def main():
def fmd(f): def fmd(f):
return ('https://raw.githubusercontent.com/yoshiko2/Movie_Data_Capture/master/MappingTable/' + f, return ('https://raw.githubusercontent.com/yoshiko2/Movie_Data_Capture/master/MappingTable/' + f,
Path.home() / '.local' / 'share' / 'mdc' / f) Path.home() / '.local' / 'share' / 'mdc' / f)
map_tab = (fmd('mapping_actor.xml'), fmd('mapping_info.xml'), fmd('c_number.json')) map_tab = (fmd('mapping_actor.xml'), fmd('mapping_info.xml'), fmd('c_number.json'))
for k, v in map_tab: for k, v in map_tab:
if v.exists(): if v.exists():
@@ -525,14 +551,15 @@ def main():
try: try:
oCC = None if ccm == 0 else OpenCC('t2s.json' if ccm == 1 else 's2t.json') oCC = None if ccm == 0 else OpenCC('t2s.json' if ccm == 1 else 's2t.json')
except: except:
# some OS no OpennCC cpython, try opencc-python-reimplemented. # some OS no OpenCC cpython, try opencc-python-reimplemented.
# pip uninstall opencc && pip install opencc-python-reimplemented # pip uninstall opencc && pip install opencc-python-reimplemented
oCC = None if ccm == 0 else OpenCC('t2s' if ccm == 1 else 's2t') oCC = None if ccm == 0 else OpenCC('t2s' if ccm == 1 else 's2t')
if not single_file_path == '': # Single File if not single_file_path == '': # Single File
print('[+]==================== Single File =====================') print('[+]==================== Single File =====================')
if custom_number == '': if custom_number == '':
create_data_and_move_with_custom_number(single_file_path, get_number(conf.debug(), os.path.basename(single_file_path)), oCC) create_data_and_move_with_custom_number(single_file_path,
get_number(conf.debug(), os.path.basename(single_file_path)), oCC)
else: else:
create_data_and_move_with_custom_number(single_file_path, custom_number, oCC) create_data_and_move_with_custom_number(single_file_path, custom_number, oCC)
else: else:
@@ -555,7 +582,8 @@ def main():
for movie_path in movie_list: # 遍历电影列表 交给core处理 for movie_path in movie_list: # 遍历电影列表 交给core处理
count = count + 1 count = count + 1
percentage = str(count / int(count_all) * 100)[:4] + '%' percentage = str(count / int(count_all) * 100)[:4] + '%'
print('[!] {:>30}{:>21}'.format('- ' + percentage + ' [' + str(count) + '/' + count_all + '] -', time.strftime("%H:%M:%S"))) print('[!] {:>30}{:>21}'.format('- ' + percentage + ' [' + str(count) + '/' + count_all + '] -',
time.strftime("%H:%M:%S")))
create_data_and_move(movie_path, zero_op, oCC) create_data_and_move(movie_path, zero_op, oCC)
if count >= stop_count: if count >= stop_count:
print("[!]Stop counter triggered!") print("[!]Stop counter triggered!")
@@ -581,7 +609,7 @@ def main():
sys.exit(0) sys.exit(0)
import multiprocessing
if __name__ == '__main__': if __name__ == '__main__':
multiprocessing.freeze_support() multiprocessing.freeze_support()
main() main()

10
WebCrawler/__init__.py
View File

@@ -235,8 +235,8 @@ def get_data_from_json(file_number, oCC): # 从JSON返回元数据
json_data['studio'] = studio json_data['studio'] = studio
json_data['director'] = director json_data['director'] = director
if conf.is_transalte(): if conf.is_translate():
translate_values = conf.transalte_values().split(",") translate_values = conf.translate_values().split(",")
for translate_value in translate_values: for translate_value in translate_values:
if json_data[translate_value] == "": if json_data[translate_value] == "":
continue continue
@@ -248,12 +248,12 @@ def get_data_from_json(file_number, oCC): # 从JSON返回元数据
continue continue
except: except:
pass pass
if conf.get_transalte_engine() == "azure": if conf.get_translate_engine() == "azure":
t = translate( t = translate(
json_data[translate_value], json_data[translate_value],
target_language="zh-Hans", target_language="zh-Hans",
engine=conf.get_transalte_engine(), engine=conf.get_translate_engine(),
key=conf.get_transalte_key(), key=conf.get_translate_key(),
) )
else: else:
t = translate(json_data[translate_value]) t = translate(json_data[translate_value])

4
config.ini
View File

@@ -8,7 +8,7 @@ success_output_folder=JAV_output
soft_link=0 soft_link=0
failed_move=1 failed_move=1
auto_exit=0 auto_exit=0
transalte_to_sc=0 translate_to_sc=0
multi_threading=0 multi_threading=0
;actor_gender value: female(♀) or male(♂) or both(♀ ♂) or all(♂ ♀ ⚧) ;actor_gender value: female(♀) or male(♂) or both(♀ ♂) or all(♂ ♀ ⚧)
actor_gender=female actor_gender=female
@@ -51,7 +51,7 @@ folders=failed,JAV_output
switch=0 switch=0
; 机器翻译 ; 机器翻译
[transalte] [translate]
switch=0 switch=0
;可选项 google-free,azure ;可选项 google-free,azure
engine=google-free engine=google-free

80
config.py
View File

@@ -5,7 +5,6 @@ import configparser
import time import time
from pathlib import Path from pathlib import Path
G_conf_override = { G_conf_override = {
# index 0 save Config() first instance for quick access by using getInstance() # index 0 save Config() first instance for quick access by using getInstance()
0: None, 0: None,
@@ -98,14 +97,18 @@ class Config:
# print("[-]",e) # print("[-]",e)
# sys.exit(3) # sys.exit(3)
# #self.conf = self._default_config() # #self.conf = self._default_config()
def getboolean_override(self, section, item) -> bool: def getboolean_override(self, section, item) -> bool:
return self.conf.getboolean(section, item) if G_conf_override[f"{section}:{item}"] is None else bool(G_conf_override[f"{section}:{item}"]) return self.conf.getboolean(section, item) if G_conf_override[f"{section}:{item}"] is None else bool(
G_conf_override[f"{section}:{item}"])
def getint_override(self, section, item) -> int: def getint_override(self, section, item) -> int:
return self.conf.getint(section, item) if G_conf_override[f"{section}:{item}"] is None else int(G_conf_override[f"{section}:{item}"]) return self.conf.getint(section, item) if G_conf_override[f"{section}:{item}"] is None else int(
G_conf_override[f"{section}:{item}"])
def get_override(self, section, item) -> str: def get_override(self, section, item) -> str:
return self.conf.get(section, item) if G_conf_override[f"{section}:{item}"] is None else str(G_conf_override[f"{section}:{item}"]) return self.conf.get(section, item) if G_conf_override[f"{section}:{item}"] is None else str(
G_conf_override[f"{section}:{item}"])
def main_mode(self) -> int: def main_mode(self) -> int:
try: try:
@@ -127,34 +130,46 @@ class Config:
def soft_link(self) -> bool: def soft_link(self) -> bool:
return self.conf.getboolean("common", "soft_link") return self.conf.getboolean("common", "soft_link")
def failed_move(self) -> bool: def failed_move(self) -> bool:
return self.conf.getboolean("common", "failed_move") return self.conf.getboolean("common", "failed_move")
def auto_exit(self) -> bool: def auto_exit(self) -> bool:
return self.getboolean_override("common", "auto_exit") return self.getboolean_override("common", "auto_exit")
def transalte_to_sc(self) -> bool:
return self.conf.getboolean("common", "transalte_to_sc") def translate_to_sc(self) -> bool:
return self.conf.getboolean("common", "translate_to_sc")
def multi_threading(self) -> bool: def multi_threading(self) -> bool:
return self.conf.getboolean("common", "multi_threading") return self.conf.getboolean("common", "multi_threading")
def del_empty_folder(self) -> bool: def del_empty_folder(self) -> bool:
return self.conf.getboolean("common", "del_empty_folder") return self.conf.getboolean("common", "del_empty_folder")
def nfo_skip_days(self) -> int: def nfo_skip_days(self) -> int:
try: try:
return self.getint_override("common", "nfo_skip_days") return self.getint_override("common", "nfo_skip_days")
except: except:
return 30 return 30
def stop_counter(self) -> int: def stop_counter(self) -> int:
try: try:
return self.getint_override("common", "stop_counter") return self.getint_override("common", "stop_counter")
except: except:
return 0 return 0
def ignore_failed_list(self) -> bool: def ignore_failed_list(self) -> bool:
return self.getboolean_override("common", "ignore_failed_list") return self.getboolean_override("common", "ignore_failed_list")
def download_only_missing_images(self) -> bool: def download_only_missing_images(self) -> bool:
return self.conf.getboolean("common", "download_only_missing_images") return self.conf.getboolean("common", "download_only_missing_images")
def mapping_table_validity(self) -> int: def mapping_table_validity(self) -> int:
return self.conf.getint("common", "mapping_table_validity") return self.conf.getint("common", "mapping_table_validity")
def is_transalte(self) -> bool:
return self.conf.getboolean("transalte", "switch") def is_translate(self) -> bool:
return self.conf.getboolean("translate", "switch")
def is_trailer(self) -> bool: def is_trailer(self) -> bool:
return self.conf.getboolean("trailer", "switch") return self.conf.getboolean("trailer", "switch")
@@ -190,18 +205,25 @@ class Config:
return extrafanart_download return extrafanart_download
except ValueError: except ValueError:
self._exit("extrafanart_folder") self._exit("extrafanart_folder")
def get_transalte_engine(self) -> str:
return self.conf.get("transalte","engine") def get_translate_engine(self) -> str:
# def get_transalte_appId(self) ->str: return self.conf.get("translate", "engine")
# return self.conf.get("transalte","appid")
def get_transalte_key(self) -> str: # def get_translate_appId(self) ->str:
return self.conf.get("transalte","key") # return self.conf.get("translate","appid")
def get_transalte_delay(self) -> int:
return self.conf.getint("transalte","delay") def get_translate_key(self) -> str:
def transalte_values(self) -> str: return self.conf.get("translate", "key")
return self.conf.get("transalte", "values")
def get_translate_delay(self) -> int:
return self.conf.getint("translate", "delay")
def translate_values(self) -> str:
return self.conf.get("translate", "values")
def get_translate_service_site(self) -> str: def get_translate_service_site(self) -> str:
return self.conf.get("transalte", "service_site") return self.conf.get("translate", "service_site")
def proxy(self): def proxy(self):
try: try:
sec = "proxy" sec = "proxy"
@@ -320,7 +342,6 @@ class Config:
except: except:
return "hog" return "hog"
@staticmethod @staticmethod
def _exit(sec: str) -> None: def _exit(sec: str) -> None:
print("[-] Read config error! Please check the {} section in config.ini", sec) print("[-] Read config error! Please check the {} section in config.ini", sec)
@@ -340,7 +361,7 @@ class Config:
conf.set(sec1, "soft_link", "0") conf.set(sec1, "soft_link", "0")
conf.set(sec1, "failed_move", "1") conf.set(sec1, "failed_move", "1")
conf.set(sec1, "auto_exit", "0") conf.set(sec1, "auto_exit", "0")
conf.set(sec1, "transalte_to_sc", "1") conf.set(sec1, "translate_to_sc", "1")
# actor_gender value: female or male or both or all(含人妖) # actor_gender value: female or male or both or all(含人妖)
conf.set(sec1, "actor_gender", "female") conf.set(sec1, "actor_gender", "female")
conf.set(sec1, "del_empty_folder", "1") conf.set(sec1, "del_empty_folder", "1")
@@ -358,7 +379,6 @@ class Config:
conf.set(sec2, "type", "socks5") conf.set(sec2, "type", "socks5")
conf.set(sec2, "cacert_file", "") conf.set(sec2, "cacert_file", "")
sec3 = "Name_Rule" sec3 = "Name_Rule"
conf.add_section(sec3) conf.add_section(sec3)
conf.set(sec3, "location_rule", "actor + '/' + number") conf.set(sec3, "location_rule", "actor + '/' + number")
@@ -382,7 +402,7 @@ class Config:
conf.add_section(sec7) conf.add_section(sec7)
conf.set(sec7, "switch", "0") conf.set(sec7, "switch", "0")
sec8 = "transalte" sec8 = "translate"
conf.add_section(sec8) conf.add_section(sec8)
conf.set(sec8, "switch", "0") conf.set(sec8, "switch", "0")
conf.set(sec8, "engine", "google-free") conf.set(sec8, "engine", "google-free")
@@ -402,8 +422,10 @@ class Config:
sec11 = "media" sec11 = "media"
conf.add_section(sec11) conf.add_section(sec11)
conf.set(sec11, "media_type", ".mp4,.avi,.rmvb,.wmv,.mov,.mkv,.flv,.ts,.webm,.MP4,.AVI,.RMVB,.WMV,.MOV,.MKV,.FLV,.TS,.WEBM,iso,ISO") conf.set(sec11, "media_type",
conf.set(sec11, "sub_type", ".smi,.srt,.idx,.sub,.sup,.psb,.ssa,.ass,.txt,.usf,.xss,.ssf,.rt,.lrc,.sbv,.vtt,.ttml") ".mp4,.avi,.rmvb,.wmv,.mov,.mkv,.flv,.ts,.webm,.MP4,.AVI,.RMVB,.WMV,.MOV,.MKV,.FLV,.TS,.WEBM,iso,ISO")
conf.set(sec11, "sub_type",
".smi,.srt,.idx,.sub,.sup,.psb,.ssa,.ass,.txt,.usf,.xss,.ssf,.rt,.lrc,.sbv,.vtt,.ttml")
sec12 = "watermark" sec12 = "watermark"
conf.add_section(sec12) conf.add_section(sec12)
@@ -464,7 +486,8 @@ class IniProxy():
''' '''
if self.address: if self.address:
if self.proxytype in self.SUPPORT_PROXY_TYPE: if self.proxytype in self.SUPPORT_PROXY_TYPE:
proxies = {"http": self.proxytype + "://" + self.address, "https": self.proxytype + "://" + self.address} proxies = {"http": self.proxytype + "://" + self.address,
"https": self.proxytype + "://" + self.address}
else: else:
proxies = {"http": "http://" + self.address, "https": "https://" + self.address} proxies = {"http": "http://" + self.address, "https": "https://" + self.address}
else: else:
@@ -477,8 +500,11 @@ if __name__ == "__main__":
def evprint(evstr): def evprint(evstr):
code = compile(evstr, "<string>", "eval") code = compile(evstr, "<string>", "eval")
print('{}: "{}"'.format(evstr, eval(code))) print('{}: "{}"'.format(evstr, eval(code)))
config = Config() config = Config()
mfilter = {'conf', 'proxy', '_exit', '_default_config', 'getboolean_override', 'getint_override', 'get_override', 'ini_path'} mfilter = {'conf', 'proxy', '_exit', '_default_config', 'getboolean_override', 'getint_override', 'get_override',
'ini_path'}
for _m in [m for m in dir(config) if not m.startswith('__') and m not in mfilter]: for _m in [m for m in dir(config) if not m.startswith('__') and m not in mfilter]:
evprint(f'config.{_m}()') evprint(f'config.{_m}()')
pfilter = {'proxies', 'SUPPORT_PROXY_TYPE'} pfilter = {'proxies', 'SUPPORT_PROXY_TYPE'}

67
number_parser.py
View File

@@ -2,6 +2,7 @@ import os
import re import re
import sys import sys
import config import config
import typing
G_spat = re.compile( G_spat = re.compile(
"^22-sht\.me|-fhd|_fhd|^fhd_|^fhd-|-hd|_hd|^hd_|^hd-|-sd|_sd|-1080p|_1080p|-720p|_720p|" "^22-sht\.me|-fhd|_fhd|^fhd_|^fhd-|-hd|_hd|^hd_|^hd-|-sd|_sd|-1080p|_1080p|-720p|_720p|"
@@ -9,30 +10,30 @@ G_spat = re.compile(
re.IGNORECASE) re.IGNORECASE)
def get_number(debug,file_path: str) -> str: def get_number(debug: bool, file_path: str) -> str:
# """ """
# >>> from number_parser import get_number 从文件路径中提取番号 from number_parser import get_number
# >>> get_number("/Users/Guest/AV_Data_Capture/snis-829.mp4") >>> get_number(False, "/Users/Guest/AV_Data_Capture/snis-829.mp4")
# 'snis-829' 'snis-829'
# >>> get_number("/Users/Guest/AV_Data_Capture/snis-829-C.mp4") >>> get_number(False, "/Users/Guest/AV_Data_Capture/snis-829-C.mp4")
# 'snis-829' 'snis-829'
# >>> get_number("C:¥Users¥Guest¥snis-829.mp4") >>> get_number(False, "C:¥Users¥Guest¥snis-829.mp4")
# 'snis-829' 'snis-829'
# >>> get_number("C:¥Users¥Guest¥snis-829-C.mp4") >>> get_number(False, "C:¥Users¥Guest¥snis-829-C.mp4")
# 'snis-829' 'snis-829'
# >>> get_number("./snis-829.mp4") >>> get_number(False, "./snis-829.mp4")
# 'snis-829' 'snis-829'
# >>> get_number("./snis-829-C.mp4") >>> get_number(False, "./snis-829-C.mp4")
# 'snis-829' 'snis-829'
# >>> get_number(".¥snis-829.mp4") >>> get_number(False, ".¥snis-829.mp4")
# 'snis-829' 'snis-829'
# >>> get_number(".¥snis-829-C.mp4") >>> get_number(False, ".¥snis-829-C.mp4")
# 'snis-829' 'snis-829'
# >>> get_number("snis-829.mp4") >>> get_number(False, "snis-829.mp4")
# 'snis-829' 'snis-829'
# >>> get_number("snis-829-C.mp4") >>> get_number(False, "snis-829-C.mp4")
# 'snis-829' 'snis-829'
# """ """
filepath = os.path.basename(file_path) filepath = os.path.basename(file_path)
# debug True 和 False 两块代码块合并，原因是此模块及函数只涉及字符串计算，没有IO操作，debug on时输出导致异常信息即可 # debug True 和 False 两块代码块合并，原因是此模块及函数只涉及字符串计算，没有IO操作，debug on时输出导致异常信息即可
try: try:
@@ -79,7 +80,8 @@ G_TAKE_NUM_RULES = {
'heyzo': lambda x: 'HEYZO-' + re.findall(r'heyzo[^\d]*(\d{4})', x, re.I)[0] 'heyzo': lambda x: 'HEYZO-' + re.findall(r'heyzo[^\d]*(\d{4})', x, re.I)[0]
} }
def get_number_by_dict(filename: str) -> str:
def get_number_by_dict(filename: str) -> typing.Optional[str]:
try: try:
for k, v in G_TAKE_NUM_RULES.items(): for k, v in G_TAKE_NUM_RULES.items():
if re.search(k, filename, re.I): if re.search(k, filename, re.I):
@@ -88,10 +90,13 @@ def get_number_by_dict(filename: str) -> str:
pass pass
return None return None
class Cache_uncensored_conf: class Cache_uncensored_conf:
prefix = None prefix = None
def is_empty(self): def is_empty(self):
return bool(self.prefix is None) return bool(self.prefix is None)
def set(self, v: list): def set(self, v: list):
if not v or not len(v) or not len(v[0]): if not v or not len(v) or not len(v[0]):
raise ValueError('input prefix list empty or None') raise ValueError('input prefix list empty or None')
@@ -100,13 +105,16 @@ class Cache_uncensored_conf:
for i in v[1:]: for i in v[1:]:
s += f"|{i}.+" s += f"|{i}.+"
self.prefix = re.compile(s, re.I) self.prefix = re.compile(s, re.I)
def check(self, number): def check(self, number):
if self.prefix is None: if self.prefix is None:
raise ValueError('No init re compile') raise ValueError('No init re compile')
return self.prefix.match(number) return self.prefix.match(number)
G_cache_uncensored_conf = Cache_uncensored_conf() G_cache_uncensored_conf = Cache_uncensored_conf()
# ========================================================================是否为无码 # ========================================================================是否为无码
def is_uncensored(number): def is_uncensored(number):
if re.match( if re.match(
@@ -119,6 +127,7 @@ r'[\d-]{4,}|\d{6}_\d{2,3}|(cz|gedo|k|n|red-|se)\d{2,4}|heyzo.+|xxx-av-.+|heydoug
G_cache_uncensored_conf.set(config.getInstance().get_uncensored().split(',')) G_cache_uncensored_conf.set(config.getInstance().get_uncensored().split(','))
return G_cache_uncensored_conf.check(number) return G_cache_uncensored_conf.check(number)
if __name__ == "__main__": if __name__ == "__main__":
# import doctest # import doctest
# doctest.testmod(raise_on_error=True) # doctest.testmod(raise_on_error=True)
@@ -145,9 +154,13 @@ if __name__ == "__main__":
"pacopacomama-093021_539-FHD.mkv", # 新支持片商格式 093021_539 命名规则来自javdb数据源 "pacopacomama-093021_539-FHD.mkv", # 新支持片商格式 093021_539 命名规则来自javdb数据源
"sbw99.cc@heyzo_hd_2636_full.mp4" "sbw99.cc@heyzo_hd_2636_full.mp4"
) )
def evprint(evstr): def evprint(evstr):
code = compile(evstr, "<string>", "eval") code = compile(evstr, "<string>", "eval")
print("{1:>20} # '{0}'".format(evstr[18:-2], eval(code))) print("{1:>20} # '{0}'".format(evstr[18:-2], eval(code)))
for t in test_use_cases: for t in test_use_cases:
evprint(f'get_number(True, "{t}")') evprint(f'get_number(True, "{t}")')
@@ -170,6 +183,7 @@ if __name__ == "__main__":
# 示例： # 示例：
# python3 ./number_parser.py ALL # python3 ./number_parser.py ALL
import subprocess import subprocess
ES_search_path = "ALL disks" ES_search_path = "ALL disks"
if sys.argv[1] == "ALL": if sys.argv[1] == "ALL":
if sys.platform == "win32": if sys.platform == "win32":
@@ -181,7 +195,8 @@ if __name__ == "__main__":
out_list = out_text.splitlines() out_list = out_text.splitlines()
elif sys.platform in ("linux", "darwin"): elif sys.platform in ("linux", "darwin"):
ES_prog_path = 'locate' if sys.platform == 'linux' else 'glocate' ES_prog_path = 'locate' if sys.platform == 'linux' else 'glocate'
ES_cmdline = r"{} -b -i --regex '\.mp4$|\.avi$|\.rmvb$|\.wmv$|\.mov$|\.mkv$|\.webm$|\.iso$|\.mpg$|\.m4v$'".format(ES_prog_path) ES_cmdline = r"{} -b -i --regex '\.mp4$|\.avi$|\.rmvb$|\.wmv$|\.mov$|\.mkv$|\.webm$|\.iso$|\.mpg$|\.m4v$'".format(
ES_prog_path)
out_bytes = subprocess.check_output(ES_cmdline.split(' ')) out_bytes = subprocess.check_output(ES_cmdline.split(' '))
out_text = out_bytes.decode('utf-8') out_text = out_bytes.decode('utf-8')
out_list = [os.path.basename(line) for line in out_text.splitlines()] out_list = [os.path.basename(line) for line in out_text.splitlines()]