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

Merge pull request #746 from lededev/num-4k

Browse Source 
新功能：完整的多次少量处理功能，增加再次运行延迟
This commit is contained in:
Yoshiko2
2022-04-12 18:59:07 +08:00
committed by GitHub
parent 38b18efdb2 475f02fbe6
commit 3bcaf8d318
14 changed files with 464 additions and 244 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
ADC_function.py
View File

@@ -18,6 +18,7 @@ from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry from urllib3.util.retry import Retry
from cloudscraper import create_scraper from cloudscraper import create_scraper
from concurrent.futures import ThreadPoolExecutor from concurrent.futures import ThreadPoolExecutor
from unicodedata import category
def getXpathSingle(htmlcode, xpath): def getXpathSingle(htmlcode, xpath):
@@ -26,7 +27,7 @@ def getXpathSingle(htmlcode, xpath):
return result1 return result1
G_USER_AGENT = r'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36' G_USER_AGENT = r'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36'
def get_html(url, cookies: dict = None, ua: str = None, return_type: str = None, encoding: str = None): def get_html(url, cookies: dict = None, ua: str = None, return_type: str = None, encoding: str = None):
@@ -381,7 +382,7 @@ def load_cookies(cookie_json_filename: str):
break break
if not cookies_filename: if not cookies_filename:
return None, None return None, None
return json.load(open(cookies_filename)), cookies_filename return json.loads(Path(cookies_filename).read_text(encoding='utf-8')), cookies_filename
except: except:
return None, None return None, None
@@ -519,14 +520,13 @@ def download_one_file(args) -> str:
wrapped for map function wrapped for map function
""" """
def _inner(url: str, save_path: Path): (url, save_path) = args
filebytes = get_html(url, return_type='content') filebytes = get_html(url, return_type='content')
if isinstance(filebytes, bytes) and len(filebytes): if isinstance(filebytes, bytes) and len(filebytes):
if len(filebytes) == save_path.open('wb').write(filebytes): with save_path.open('wb') as fpbyte:
if len(filebytes) == fpbyte.write(filebytes):
return str(save_path) return str(save_path)
return _inner(*args)
def parallel_download_files(dn_list: typing.Iterable[typing.Sequence], parallel: int = 0): def parallel_download_files(dn_list: typing.Iterable[typing.Sequence], parallel: int = 0):
""" """
@@ -567,6 +567,7 @@ def delete_all_elements_in_list(string: str, lists: typing.Iterable[str]):
new_lists.append(i) new_lists.append(i)
return new_lists return new_lists
def delete_all_elements_in_str(string_delete: str, string: str): def delete_all_elements_in_str(string_delete: str, string: str):
""" """
delete same string in given list delete same string in given list
@@ -574,4 +575,14 @@ def delete_all_elements_in_str(string_delete: str, string: str):
for i in string: for i in string:
if i == string_delete: if i == string_delete:
string = string.replace(i,"") string = string.replace(i,"")
return string return string
def cnspace(v: str, n: int) -> int:
"""
print format空格填充对齐内容包含中文时的空格计算
"""
cw = 0
for c in v:
cw += 1 if category(c) in ('Lo',) else 0
return n - cw

29
ImageProcessing/__init__.py
View File

@@ -2,11 +2,14 @@ import logging
import os import os
import config import config
import importlib import importlib
from pathlib import Path
from PIL import Image from PIL import Image
import shutil import shutil
from ADC_function import file_not_exist_or_empty from ADC_function import file_not_exist_or_empty
def face_crop_width(filename, width, height): def face_crop_width(filename, width, height):
aspect_ratio = config.getInstance().face_aspect_ratio()
# 新宽度是高度的2/3 # 新宽度是高度的2/3
cropWidthHalf = int(height/3) cropWidthHalf = int(height/3)
try: try:
@@ -21,15 +24,15 @@ def face_crop_width(filename, width, height):
# 越界处理 # 越界处理
if cropLeft < 0: if cropLeft < 0:
cropLeft = 0 cropLeft = 0
cropRight = cropWidthHalf*2 cropRight = cropWidthHalf * aspect_ratio
elif cropRight > width: elif cropRight > width:
cropLeft = width-cropWidthHalf*2 cropLeft = width - cropWidthHalf * aspect_ratio
cropRight = width cropRight = width
return (cropLeft, 0, cropRight, height) return (cropLeft, 0, cropRight, height)
except: except:
print('[-]Not found face! ' + filename) print('[-]Not found face! ' + filename)
# 默认靠右切 # 默认靠右切
return (width-cropWidthHalf*2, 0, width, height) return (width-cropWidthHalf * aspect_ratio, 0, width, height)
def face_crop_height(filename, width, height): def face_crop_height(filename, width, height):
@@ -54,31 +57,39 @@ def face_crop_height(filename, width, height):
return (0, 0, width, cropHeight) return (0, 0, width, cropHeight)
def cutImage(imagecut, path, fanart_path, poster_path): def cutImage(imagecut, path, fanart_path, poster_path, skip_facerec=False):
conf = config.getInstance()
fullpath_fanart = os.path.join(path, fanart_path) fullpath_fanart = os.path.join(path, fanart_path)
fullpath_poster = os.path.join(path, poster_path) fullpath_poster = os.path.join(path, poster_path)
if config.getInstance().download_only_missing_images() and not file_not_exist_or_empty(fullpath_poster): aspect_ratio = conf.face_aspect_ratio()
if conf.face_aways_imagecut():
imagecut = 1
elif conf.download_only_missing_images() and not file_not_exist_or_empty(fullpath_poster):
return return
if imagecut == 1: # 剪裁大封面 if imagecut == 1: # 剪裁大封面
try: try:
img = Image.open(fullpath_fanart) img = Image.open(fullpath_fanart)
width, height = img.size width, height = img.size
if width/height > 2/3: # 如果宽度大于2 if width/height > 2/3: # 如果宽度大于2
# 以人像为中心切取 if skip_facerec:
img2 = img.crop(face_crop_width(fullpath_fanart, width, height)) # 有码封面默认靠右切
img2 = img.crop((width - int(height/3) * aspect_ratio, 0, width, height))
else:
# 以人像为中心切取
img2 = img.crop(face_crop_width(fullpath_fanart, width, height))
elif width/height < 2/3: # 如果高度大于3 elif width/height < 2/3: # 如果高度大于3
# 从底部向上切割 # 从底部向上切割
img2 = img.crop(face_crop_height(fullpath_fanart, width, height)) img2 = img.crop(face_crop_height(fullpath_fanart, width, height))
else: # 如果等于2/3 else: # 如果等于2/3
img2 = img img2 = img
img2.save(fullpath_poster) img2.save(fullpath_poster)
print('[+]Image Cutted! ' + fullpath_poster) print(f"[+]Image Cutted! {Path(fullpath_poster).name}")
except Exception as e: except Exception as e:
print(e) print(e)
print('[-]Cover cut failed!') print('[-]Cover cut failed!')
elif imagecut == 0: # 复制封面 elif imagecut == 0: # 复制封面
shutil.copyfile(fullpath_fanart, fullpath_poster) shutil.copyfile(fullpath_fanart, fullpath_poster)
print('[+]Image Copyed! ' + fullpath_poster) print(f"[+]Image Copyed! {Path(fullpath_poster).name}")
def face_center(filename, model): def face_center(filename, model):

170
Movie_Data_Capture.py
View File

@@ -18,7 +18,7 @@ from opencc import OpenCC
import config import config
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, core_main_no_net_op, moveFailedFolder
def check_update(local_version): def check_update(local_version):
@@ -40,7 +40,7 @@ def check_update(local_version):
print("[*]======================================================") print("[*]======================================================")
def argparse_function(ver: str) -> typing.Tuple[str, str, str, str, bool]: def argparse_function(ver: str) -> typing.Tuple[str, str, str, str, bool, bool]:
conf = config.getInstance() conf = config.getInstance()
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.")
@@ -62,12 +62,16 @@ def argparse_function(ver: str) -> typing.Tuple[str, str, str, str, bool]:
help="Override nfo_skip_days value in config.") help="Override nfo_skip_days value in config.")
parser.add_argument("-c", "--stop-counter", dest='cnt', default='', nargs='?', parser.add_argument("-c", "--stop-counter", dest='cnt', default='', nargs='?',
help="Override stop_counter value in config.") help="Override stop_counter value in config.")
parser.add_argument("-R", "--rerun-delay", dest='delaytm', default='', nargs='?',
help="Delay (eg. 1h10m30s or 60 (second)) time and rerun, until all movies proceed. Note: stop_counter value in config or -c must none zero.")
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",
help="Auto exit after program complete") help="Auto exit after program complete")
parser.add_argument("-g", "--debug", action="store_true", parser.add_argument("-g", "--debug", action="store_true",
help="Turn on debug mode to generate diagnostic log for issue report.") help="Turn on debug mode to generate diagnostic log for issue report.")
parser.add_argument("-N", "--no-network-operation", action="store_true",
help="No network query, do not get metadata, for cover cropping purposes, only takes effect when main mode is 3.")
parser.add_argument("-z", "--zero-operation", dest='zero_op', action="store_true", parser.add_argument("-z", "--zero-operation", dest='zero_op', action="store_true",
help="""Only show job list of files and numbers, and **NO** actual operation help="""Only show job list of files and numbers, and **NO** actual operation
is performed. It may help you correct wrong numbers before real job.""") is performed. It may help you correct wrong numbers before real job.""")
@@ -92,8 +96,17 @@ is performed. It may help you correct wrong numbers before real job.""")
config.G_conf_override["common:stop_counter"] = get_natural_number_or_none(args.cnt) config.G_conf_override["common:stop_counter"] = get_natural_number_or_none(args.cnt)
config.G_conf_override["common:ignore_failed_list"] = get_bool_or_none(args.ignore_failed_list) config.G_conf_override["common:ignore_failed_list"] = get_bool_or_none(args.ignore_failed_list)
config.G_conf_override["debug_mode:switch"] = get_bool_or_none(args.debug) config.G_conf_override["debug_mode:switch"] = get_bool_or_none(args.debug)
config.G_conf_override["common:rerun_delay"] = get_str_or_none(args.delaytm)
return args.file, args.number, args.logdir, args.regexstr, args.zero_op no_net_op = False
if conf.main_mode() == 3:
no_net_op = args.no_network_operation
if no_net_op:
config.G_conf_override["common:stop_counter"] = 0
config.G_conf_override["common:rerun_delay"] = '0s'
config.G_conf_override["face:aways_imagecut"] = True
return args.file, args.number, args.logdir, args.regexstr, args.zero_op, no_net_op
class OutLogger(object): class OutLogger(object):
@@ -250,29 +263,31 @@ def close_logfile(logdir: str):
except: except:
pass pass
# 第三步，月合并到年 # 第三步，月合并到年
if today.month < 4: for i in range(1):
return if today.month < 4:
mons = [f for f in log_dir.glob(r'*.txt') if re.match(r'^mdc_\d{6}$', f.stem, re.A)] break
if not mons or not len(mons): mons = [f for f in log_dir.glob(r'*.txt') if re.match(r'^mdc_\d{6}$', f.stem, re.A)]
return if not mons or not len(mons):
mons.sort() break
deadline_year = f'mdc_{today.year - 1}13' mons.sort()
year_merge = [f for f in mons if f.stem < deadline_year] deadline_year = f'mdc_{today.year - 1}13'
if not year_merge or not len(year_merge): year_merge = [f for f in mons if f.stem < deadline_year]
return if not year_merge or not len(year_merge):
toyear = len('12.txt') # cut length mdc_2020|12.txt break
for f in year_merge: toyear = len('12.txt') # cut length mdc_2020|12.txt
try: for f in year_merge:
year_file_name = str(f)[:-toyear] + '.txt' # mdc_2020.txt try:
with open(year_file_name, 'a', encoding='utf-8') as y: year_file_name = str(f)[:-toyear] + '.txt' # mdc_2020.txt
y.write(f.read_text(encoding='utf-8')) with open(year_file_name, 'a', encoding='utf-8') as y:
f.unlink(missing_ok=True) y.write(f.read_text(encoding='utf-8'))
except: f.unlink(missing_ok=True)
pass except:
pass
# 第四步，压缩年志 如果有压缩需求，请自行手工压缩，或者使用外部脚本来定时完成。推荐nongnu的lzip，对于 # 第四步，压缩年志 如果有压缩需求，请自行手工压缩，或者使用外部脚本来定时完成。推荐nongnu的lzip，对于
# 这种粒度的文本日志，压缩比是目前最好的。lzip -9的运行参数下，日志压缩比要高于xz -9，而且内存占用更少， # 这种粒度的文本日志，压缩比是目前最好的。lzip -9的运行参数下，日志压缩比要高于xz -9，而且内存占用更少，
# 多核利用率更高(plzip多线程版本)，解压速度更快。压缩后的大小差不多是未压缩时的2.4%到3.7%左右， # 多核利用率更高(plzip多线程版本)，解压速度更快。压缩后的大小差不多是未压缩时的2.4%到3.7%左右，
# 100MB的日志文件能缩小到3.7MB。 # 100MB的日志文件能缩小到3.7MB。
return filepath
def signal_handler(*args): def signal_handler(*args):
@@ -360,7 +375,7 @@ def movie_lists(source_folder, regexstr: str) -> typing.List[str]:
skip_numbers = set() skip_numbers = set()
success_folder = Path(conf.success_folder()).resolve() success_folder = Path(conf.success_folder()).resolve()
for f in success_folder.glob(r'**/*'): for f in success_folder.glob(r'**/*'):
if not re.match(r'\.nfo', f.suffix, re.IGNORECASE): if not re.match(r'\.nfo$', f.suffix, re.IGNORECASE):
continue continue
if file_modification_days(f) > nfo_skip_days: if file_modification_days(f) > nfo_skip_days:
continue continue
@@ -411,38 +426,44 @@ def rm_empty_folder(path):
pass pass
def create_data_and_move(file_path: str, zero_op, oCC): def create_data_and_move(movie_path: str, zero_op: bool, no_net_op: bool, oCC):
# Normalized number, eg: 111xxx-222.mp4 -> xxx-222.mp4 # Normalized number, eg: 111xxx-222.mp4 -> xxx-222.mp4
debug = config.getInstance().debug() debug = config.getInstance().debug()
n_number = get_number(debug, os.path.basename(file_path)) n_number = get_number(debug, os.path.basename(movie_path))
file_path = os.path.abspath(file_path) movie_path = os.path.abspath(movie_path)
if debug is 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 '{movie_path}'")
if zero_op: if zero_op:
return return
if n_number: if n_number:
core_main(file_path, n_number, oCC) if no_net_op:
core_main_no_net_op(movie_path, n_number)
else:
core_main(movie_path, n_number, oCC)
else: else:
print("[-] number empty ERROR") print("[-] number empty ERROR")
moveFailedFolder(file_path) moveFailedFolder(movie_path)
print("[*]======================================================") print("[*]======================================================")
else: else:
try: try:
print(f"[!] [{n_number}] As Number making data for '{file_path}'") print(f"[!] [{n_number}] As Number making data for '{movie_path}'")
if zero_op: if zero_op:
return return
if n_number: if n_number:
core_main(file_path, n_number, oCC) if no_net_op:
core_main_no_net_op(movie_path, n_number)
else:
core_main(movie_path, n_number, oCC)
else: else:
raise ValueError("number empty") raise ValueError("number empty")
print("[*]======================================================") print("[*]======================================================")
except Exception as err: except Exception as err:
print(f"[-] [{file_path}] ERROR:") print(f"[-] [{movie_path}] ERROR:")
print('[-]', err) print('[-]', err)
try: try:
moveFailedFolder(file_path) moveFailedFolder(movie_path)
except Exception as err: except Exception as err:
print('[!]', err) print('[!]', err)
@@ -472,18 +493,9 @@ def create_data_and_move_with_custom_number(file_path: str, custom_number, oCC):
print('[!]', err) print('[!]', err)
def main(): def main(args: tuple) -> Path:
version = '6.0.3' (single_file_path, custom_number, logdir, regexstr, zero_op, no_net_op) = args
urllib3.disable_warnings() # Ignore http proxy warning conf = config.getInstance()
# Read config.ini first, in argparse_function() need conf.failed_folder()
conf = config.Config("config.ini")
# Parse command line args
single_file_path, custom_number, logdir, regexstr, zero_op = argparse_function(version)
main_mode = conf.main_mode() main_mode = conf.main_mode()
folder_path = "" folder_path = ""
if main_mode not in (1, 2, 3): if main_mode not in (1, 2, 3):
@@ -596,7 +608,7 @@ def main():
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 + '] -', print('[!] {:>30}{:>21}'.format('- ' + percentage + ' [' + str(count) + '/' + count_all + '] -',
time.strftime("%H:%M:%S"))) time.strftime("%H:%M:%S")))
create_data_and_move(movie_path, zero_op, oCC) create_data_and_move(movie_path, zero_op, no_net_op, oCC)
if count >= stop_count: if count >= stop_count:
print("[!]Stop counter triggered!") print("[!]Stop counter triggered!")
break break
@@ -614,14 +626,68 @@ def main():
print("[+]All finished!!!") print("[+]All finished!!!")
close_logfile(logdir) return close_logfile(logdir)
def 分析日志文件(logfile):
try:
if not (isinstance(logfile, Path) and logfile.is_file()):
raise FileNotFoundError('log file not found')
logtxt = logfile.read_text(encoding='utf-8')
扫描电影数 = int(re.findall(r'\[\+]Find (.*) movies\.', logtxt)[0])
已处理 = int(re.findall(r'\[1/(.*?)] -', logtxt)[0])
完成数 = logtxt.count(r'[+]Wrote!')
return 扫描电影数, 已处理, 完成数
except:
return None, None, None
def period(delta, pattern):
d = {'d': delta.days}
d['h'], rem = divmod(delta.seconds, 3600)
d['m'], d['s'] = divmod(rem, 60)
return pattern.format(**d)
if __name__ == '__main__':
version = '6.0.3'
multiprocessing.freeze_support()
urllib3.disable_warnings() # Ignore http proxy warning
app_start = time.time()
# Read config.ini first, in argparse_function() need conf.failed_folder()
conf = config.Config("config.ini")
# Parse command line args
args = tuple(argparse_function(version))
再运行延迟 = conf.rerun_delay()
if 再运行延迟 > 0 and conf.stop_counter() > 0:
while True:
try:
logfile = main(args)
(扫描电影数, 已处理, 完成数) = 分析结果元组 = tuple(分析日志文件(logfile))
if all(isinstance(v, int) for v in 分析结果元组):
剩余个数 = 扫描电影数 - 已处理
总用时 = timedelta(seconds = time.time() - app_start)
print(f'All movies:{扫描电影数} processed:{已处理} successes:{完成数} remain:{剩余个数}' +
' Elapsed time {}'.format(
period(总用时, "{d} day {h}:{m:02}:{s:02}") if 总用时.days == 1
else period(总用时, "{d} days {h}:{m:02}:{s:02}") if 总用时.days > 1
else period(总用时, "{h}:{m:02}:{s:02}")))
if 剩余个数 == 0:
break
下次运行 = datetime.now() + timedelta(seconds=再运行延迟)
print(f'Next run time: {下次运行.strftime("%H:%M:%S")}, rerun_delay={再运行延迟}, press Ctrl+C stop run.')
time.sleep(再运行延迟)
else:
break
except:
break
else:
main(args)
if not conf.auto_exit(): if not conf.auto_exit():
input("Press enter key exit, you can check the error message before you exit...") input("Press enter key exit, you can check the error message before you exit...")
sys.exit(0) sys.exit(0)
if __name__ == '__main__':
multiprocessing.freeze_support()
main()

4
WebCrawler/__init__.py
View File

@@ -248,8 +248,8 @@ def get_data_from_json(file_number, oCC):
if json_data[translate_value] == "": if json_data[translate_value] == "":
continue continue
if translate_value == "title": if translate_value == "title":
title_dict = json.load( title_dict = json.loads(
open(str(Path.home() / '.local' / 'share' / 'mdc' / 'c_number.json'), 'r', encoding="utf-8")) (Path.home() / '.local' / 'share' / 'mdc' / 'c_number.json').read_text(encoding="utf-8"))
try: try:
json_data[translate_value] = title_dict[number] json_data[translate_value] = title_dict[number]
continue continue

1
WebCrawler/carib.py
View File

@@ -40,6 +40,7 @@ def main(number: str) -> json:
'website': f'{G_SITE}/moviepages/{number}/index.html', 'website': f'{G_SITE}/moviepages/{number}/index.html',
'source': 'carib.py', 'source': 'carib.py',
'series': get_series(lx), 'series': get_series(lx),
'无码': True
} }
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )
return js return js

11
WebCrawler/fanza.py
View File

@@ -250,6 +250,13 @@ def main(number):
# but the hinban on the page is test00012 # but the hinban on the page is test00012
# so get the hinban first, and then pass it to following functions # so get the hinban first, and then pass it to following functions
fanza_hinban = getNum(htmlcode) fanza_hinban = getNum(htmlcode)
out_num = fanza_hinban
number_lo = number.lower()
if (re.sub('-|_', '', number_lo) == fanza_hinban or
number_lo.replace('-', '00') == fanza_hinban or
number_lo.replace('-', '') + 'so' == fanza_hinban
):
out_num = number
data = { data = {
"title": getTitle(htmlcode).strip(), "title": getTitle(htmlcode).strip(),
"studio": getStudio(htmlcode), "studio": getStudio(htmlcode),
@@ -258,7 +265,7 @@ def main(number):
"director": getDirector(htmlcode) if "anime" not in chosen_url else "", "director": getDirector(htmlcode) if "anime" not in chosen_url else "",
"actor": getActor(htmlcode) if "anime" not in chosen_url else "", "actor": getActor(htmlcode) if "anime" not in chosen_url else "",
"release": getRelease(htmlcode), "release": getRelease(htmlcode),
"number": fanza_hinban, "number": out_num,
"cover": getCover(htmlcode, fanza_hinban), "cover": getCover(htmlcode, fanza_hinban),
"imagecut": 1, "imagecut": 1,
"tag": getTag(htmlcode), "tag": getTag(htmlcode),
@@ -315,3 +322,5 @@ if __name__ == "__main__":
# print(main("DV-1562")) # print(main("DV-1562"))
# print(main("96fad1217")) # print(main("96fad1217"))
print(main("pred00251")) print(main("pred00251"))
print(main("MIAA-391"))
print(main("OBA-326"))

27
WebCrawler/javbus.py
View File

@@ -83,9 +83,13 @@ def getExtrafanart(htmlcode): # 获取剧照
if extrafanart_imgs: if extrafanart_imgs:
return [urljoin('https://www.javbus.com',img) for img in extrafanart_imgs] return [urljoin('https://www.javbus.com',img) for img in extrafanart_imgs]
return '' return ''
def getUncensored(html):
x = html.xpath('//*[@id="navbar"]/ul[1]/li[@class="active"]/a[contains(@href,"uncensored")]')
return bool(x)
def main_uncensored(number): def main_uncensored(number):
htmlcode = get_html('https://www.javbus.com/ja/' + number) w_number = number.replace('.', '-')
htmlcode = get_html('https://www.javbus.red/' + w_number)
if "<title>404 Page Not Found" in htmlcode: if "<title>404 Page Not Found" in htmlcode:
raise Exception('404 page not found') raise Exception('404 page not found')
lx = etree.fromstring(htmlcode, etree.HTMLParser()) lx = etree.fromstring(htmlcode, etree.HTMLParser())
@@ -94,7 +98,7 @@ def main_uncensored(number):
'title': title, 'title': title,
'studio': getStudioJa(lx), 'studio': getStudioJa(lx),
'year': getYear(lx), 'year': getYear(lx),
'outline': getOutline(number, title), 'outline': getOutline(w_number, title),
'runtime': getRuntime(lx), 'runtime': getRuntime(lx),
'director': getDirectorJa(lx), 'director': getDirectorJa(lx),
'actor': getActor(lx), 'actor': getActor(lx),
@@ -106,9 +110,10 @@ def main_uncensored(number):
'label': getSeriseJa(lx), 'label': getSeriseJa(lx),
'imagecut': 0, 'imagecut': 0,
# 'actor_photo': '', # 'actor_photo': '',
'website': 'https://www.javbus.com/ja/' + number, 'website': 'https://www.javbus.red/' + w_number,
'source': 'javbus.py', 'source': 'javbus.py',
'series': getSeriseJa(lx), 'series': getSeriseJa(lx),
'无码': True
} }
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js return js
@@ -151,6 +156,7 @@ def main(number):
'website': 'https://www.javbus.com/' + number, 'website': 'https://www.javbus.com/' + number,
'source': 'javbus.py', 'source': 'javbus.py',
'series': getSerise(lx), 'series': getSerise(lx),
'无码': getUncensored(lx)
} }
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,separators=(',', ':'), ) # .encode('UTF-8') js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,separators=(',', ':'), ) # .encode('UTF-8')
return js return js
@@ -169,12 +175,13 @@ def main(number):
if __name__ == "__main__" : if __name__ == "__main__" :
config.G_conf_override['debug_mode:switch'] = True config.G_conf_override['debug_mode:switch'] = True
print(main('ABP-888')) # print(main('ABP-888'))
print(main('ABP-960')) # print(main('ABP-960'))
print(main('ADV-R0624')) # 404 # print(main('ADV-R0624')) # 404
print(main('MMNT-010')) # print(main('MMNT-010'))
print(main('ipx-292')) # print(main('ipx-292'))
print(main('CEMD-011')) # print(main('CEMD-011'))
print(main('CJOD-278')) # print(main('CJOD-278'))
print(main('BrazzersExxtra.21.02.01'))
print(main('100221_001')) print(main('100221_001'))
print(main('AVSW-061')) print(main('AVSW-061'))

9
WebCrawler/javdb.py
View File

@@ -179,6 +179,10 @@ def getUserRating(html):
return float(v[0][0]), int(v[0][1]) return float(v[0][0]), int(v[0][1])
except: except:
return return
def getUncensored(html):
x = html.xpath('//strong[contains(text(),"類別")]/../span/a[contains(@href,"/tags/uncensored?")'
' or contains(@href,"/tags/western?")]')
return bool(x)
def main(number): def main(number):
# javdb更新后同一时间只能登录一个数字站，最新登录站会踢出旧的登录，因此按找到的第一个javdb*.json文件选择站点， # javdb更新后同一时间只能登录一个数字站，最新登录站会踢出旧的登录，因此按找到的第一个javdb*.json文件选择站点，
@@ -300,7 +304,7 @@ def main(number):
'website': urljoin('https://javdb.com', correct_url), 'website': urljoin('https://javdb.com', correct_url),
'source': 'javdb.py', 'source': 'javdb.py',
'series': getSeries(lx), 'series': getSeries(lx),
'无码': getUncensored(lx)
} }
userrating = getUserRating(lx) userrating = getUserRating(lx)
if isinstance(userrating, tuple) and len(userrating) == 2: if isinstance(userrating, tuple) and len(userrating) == 2:
@@ -328,7 +332,7 @@ if __name__ == "__main__":
# print(main('blacked.20.05.30')) # print(main('blacked.20.05.30'))
# print(main('AGAV-042')) # print(main('AGAV-042'))
# print(main('BANK-022')) # print(main('BANK-022'))
# print(main('070116-197')) print(main('070116-197'))
# print(main('093021_539')) # 没有剧照 片商pacopacomama # print(main('093021_539')) # 没有剧照 片商pacopacomama
#print(main('FC2-2278260')) #print(main('FC2-2278260'))
# print(main('FC2-735670')) # print(main('FC2-735670'))
@@ -339,3 +343,4 @@ if __name__ == "__main__":
# print(main('EBOD-646')) # print(main('EBOD-646'))
# print(main('LOVE-262')) # print(main('LOVE-262'))
print(main('ABP-890')) print(main('ABP-890'))
print(main('blacked.14.12.08'))

3
WebCrawler/madou.py
View File

@@ -146,7 +146,8 @@ def main(number):
'website': url, 'website': url,
'source': 'madou.py', 'source': 'madou.py',
# 使用 # 使用
'series': getSerise(html) 'series': getSerise(html),
'无码': True
} }
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, js = json.dumps(dic, ensure_ascii=False, sort_keys=True,
indent=4, separators=(',', ':'), ) # .encode('UTF-8') indent=4, separators=(',', ':'), ) # .encode('UTF-8')

71
WebCrawler/storyline.py
View File

@@ -80,34 +80,34 @@ def getStoryline(number, title, sites: list=None):
def getStoryline_mp(args): def getStoryline_mp(args):
def _inner(site, number, title, debug): (site, number, title, debug) = args
start_time = time.time() start_time = time.time()
storyline = None storyline = None
if not isinstance(site, str): if not isinstance(site, str):
return storyline
elif site == "airavwiki":
storyline = getStoryline_airavwiki(number, debug)
elif site == "airav":
storyline = getStoryline_airav(number, debug)
elif site == "avno1":
storyline = getStoryline_avno1(number, debug)
elif site == "xcity":
storyline = getStoryline_xcity(number, debug)
elif site == "amazon":
storyline = getStoryline_amazon(title, number, debug)
elif site == "58avgo":
storyline = getStoryline_58avgo(number, debug)
if not debug:
return storyline
# 进程池模式的子进程getStoryline_*()的print()不会写入日志中，线程池和顺序执行不受影响
print("[!]MP 进程[{}]运行{:.3f}秒，结束于{}返回结果: {}".format(
site,
time.time() - start_time,
time.strftime("%H:%M:%S"),
storyline if isinstance(storyline, str) and len(storyline) else '[空]')
)
return storyline return storyline
return _inner(*args) elif site == "airavwiki":
storyline = getStoryline_airavwiki(number, debug)
#storyline = getStoryline_airavwiki_super(number, debug)
elif site == "airav":
storyline = getStoryline_airav(number, debug)
elif site == "avno1":
storyline = getStoryline_avno1(number, debug)
elif site == "xcity":
storyline = getStoryline_xcity(number, debug)
elif site == "amazon":
storyline = getStoryline_amazon(title, number, debug)
elif site == "58avgo":
storyline = getStoryline_58avgo(number, debug)
if not debug:
return storyline
# 进程池模式的子进程getStoryline_*()的print()不会写入日志中，线程池和顺序执行不受影响
print("[!]MP 进程[{}]运行{:.3f}秒，结束于{}返回结果: {}".format(
site,
time.time() - start_time,
time.strftime("%H:%M:%S"),
storyline if isinstance(storyline, str) and len(storyline) else '[空]')
)
return storyline
def getStoryline_airav(number, debug): def getStoryline_airav(number, debug):
@@ -308,8 +308,8 @@ def getStoryline_amazon(q_title, number, debug):
res = session.get(urljoin(res.url, lks[0])) res = session.get(urljoin(res.url, lks[0]))
cookie = None cookie = None
lx = fromstring(res.text) lx = fromstring(res.text)
titles = lx.xpath("//span[contains(@class,'a-color-base a-text-normal')]/text()") titles = lx.xpath("//span[contains(@class,'a-size-base-plus a-color-base a-text-normal')]/text()")
urls = lx.xpath("//span[contains(@class,'a-color-base a-text-normal')]/../@href") urls = lx.xpath("//span[contains(@class,'a-size-base-plus a-color-base a-text-normal')]/../@href")
if not len(urls) or len(urls) != len(titles): if not len(urls) or len(urls) != len(titles):
raise ValueError("titles not found") raise ValueError("titles not found")
idx = amazon_select_one(titles, q_title, number, debug) idx = amazon_select_one(titles, q_title, number, debug)
@@ -325,8 +325,9 @@ def getStoryline_amazon(q_title, number, debug):
res = session.get(urljoin(res.url, lks[0])) res = session.get(urljoin(res.url, lks[0]))
cookie = None cookie = None
lx = fromstring(res.text) lx = fromstring(res.text)
div = lx.xpath('//*[@id="productDescription"]')[0] p1 = lx.xpath('//*[@id="productDescription"]/p[1]/span/text()')
ama_t = ' '.join([e.text.strip() for e in div if not re.search('Comment|h3', str(e.tag), re.I) and isinstance(e.text, str)]) p2 = lx.xpath('//*[@id="productDescription"]/p[2]/span/text()')
ama_t = ' '.join(p1) + ' '.join(p2)
ama_t = re.sub(r'審査番号:\d+', '', ama_t).strip() ama_t = re.sub(r'審査番号:\d+', '', ama_t).strip()
if cookie is None: if cookie is None:
@@ -406,10 +407,10 @@ def amazon_select_one(a_titles, q_title, number, debug):
# debug 模式下记录识别准确率日志 # debug 模式下记录识别准确率日志
if ratio < 0.9: if ratio < 0.9:
# 相似度[0.5, 0.9)的淘汰结果单独记录日志 # 相似度[0.5, 0.9)的淘汰结果单独记录日志
(Path.home() / '.avlogs/ratio0.5.txt').open('a', encoding='utf-8').write( with (Path.home() / '.mlogs/ratio0.5.txt').open('a', encoding='utf-8') as hrt:
f' [{number}] Ratio:{ratio}\n{a_titles[sel]}\n{q_title}\n{save_t_}\n{que_t}\n') hrt.write(f' [{number}] Ratio:{ratio}\n{a_titles[sel]}\n{q_title}\n{save_t_}\n{que_t}\n')
return -1 return -1
# 被采信的结果日志 # 被采信的结果日志
(Path.home() / '.avlogs/ratio.txt').open('a', encoding='utf-8').write( with (Path.home() / '.mlogs/ratio.txt').open('a', encoding='utf-8') as hrt:
f' [{number}] Ratio:{ratio}\n{a_titles[sel]}\n{q_title}\n{save_t_}\n{que_t}\n') hrt.write(f' [{number}] Ratio:{ratio}\n{a_titles[sel]}\n{q_title}\n{save_t_}\n{que_t}\n')
return sel return sel

17
config.ini
View File

@@ -20,7 +20,10 @@ del_empty_folder=1
nfo_skip_days=30 nfo_skip_days=30
; 处理完多少个视频文件后停止，0为处理所有视频文件 ; 处理完多少个视频文件后停止，0为处理所有视频文件
stop_counter=0 stop_counter=0
; 以上两个参数配合使用可以以多次少量的方式刮削或整理数千个文件而不触发翻译或元数据站封禁 ; 再运行延迟时间，单位：h时m分s秒 举例: 1h30m45s(1小时30分45秒) 45(45秒)
; stop_counter不为零的条件下才有效，每处理stop_counter部影片后延迟rerun_delay秒再次运行
rerun_delay=0
; 以上三个参数配合使用可以以多次少量的方式刮削或整理数千个文件而不触发翻译或元数据站封禁
ignore_failed_list=0 ignore_failed_list=0
download_only_missing_images=1 download_only_missing_images=1
mapping_table_validity=7 mapping_table_validity=7
@@ -76,7 +79,7 @@ uncensored_prefix=S2M,BT,LAF,SMD,SMBD,SM3D2DBD,SKY-,SKYHD,CWP,CWDV,CWBD,CW3D2DBD
; 影片后缀 ; 影片后缀
media_type=.mp4,.avi,.rmvb,.wmv,.mov,.mkv,.flv,.ts,.webm,.iso,.mpg,.m4v media_type=.mp4,.avi,.rmvb,.wmv,.mov,.mkv,.flv,.ts,.webm,.iso,.mpg,.m4v
; 字幕后缀 ; 字幕后缀
sub_type=.smi,.srt,.idx,.sub,.sup,.psb,.ssa,.ass,.txt,.usf,.xss,.ssf,.rt,.lrc,.sbv,.vtt,.ttml sub_type=.smi,.srt,.idx,.sub,.sup,.psb,.ssa,.ass,.usf,.xss,.ssf,.rt,.lrc,.sbv,.vtt,.ttml
; 水印 ; 水印
[watermark] [watermark]
@@ -114,8 +117,14 @@ mode=1
vars=outline,series,studio,tag,title vars=outline,series,studio,tag,title
[javdb] [javdb]
sites=37,38 sites=38,39
; 人脸识别 hog:方向梯度直方图(不太准确，速度快) cnn:深度学习模型(准确，需要GPU/CUDA,速度慢) ; 人脸识别 locations_model=hog:方向梯度直方图(不太准确，速度快) cnn:深度学习模型(准确，需要GPU/CUDA,速度慢)
; uncensored_only=0:对全部封面进行人脸识别 1:只识别无码封面，有码封面直接切右半部分
; aways_imagecut=0:按各网站默认行为 1:总是裁剪封面，开启此项将无视[common]download_only_missing_images=1总是覆盖封面
; 封面裁剪的宽高比可配置，公式为aspect_ratio/3。默认aspect_ratio=2.12: 适配大部分有码影片封面，前一版本默认为2/3即aspect_ratio=2
[face] [face]
locations_model=hog locations_model=hog
uncensored_only=1
aways_imagecut=0
aspect_ratio=2.12

85
config.py
View File

@@ -3,6 +3,7 @@ import re
import sys import sys
import configparser import configparser
import time import time
import typing
from pathlib import Path from pathlib import Path
G_conf_override = { G_conf_override = {
@@ -16,7 +17,9 @@ G_conf_override = {
"common:nfo_skip_days": None, "common:nfo_skip_days": None,
"common:stop_counter": None, "common:stop_counter": None,
"common:ignore_failed_list": None, "common:ignore_failed_list": None,
"debug_mode:switch": None "common:rerun_delay": None,
"debug_mode:switch": None,
"face:aways_imagecut": None
} }
@@ -99,13 +102,19 @@ class Config:
# 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, fallback=None) -> bool:
return self.conf.getboolean(section, item) if G_conf_override[f"{section}:{item}"] is None else bool( if G_conf_override[f"{section}:{item}"] is not None:
G_conf_override[f"{section}:{item}"]) return bool(G_conf_override[f"{section}:{item}"])
if fallback is not None:
return self.conf.getboolean(section, item, fallback=fallback)
return self.conf.getboolean(section, item)
def getint_override(self, section, item) -> int: def getint_override(self, section, item, fallback=None) -> int:
return self.conf.getint(section, item) if G_conf_override[f"{section}:{item}"] is None else int( if G_conf_override[f"{section}:{item}"] is not None:
G_conf_override[f"{section}:{item}"]) return int(G_conf_override[f"{section}:{item}"])
if fallback is not None:
return self.conf.getint(section, item, fallback=fallback)
return self.conf.getint(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( return self.conf.get(section, item) if G_conf_override[f"{section}:{item}"] is None else str(
@@ -151,16 +160,10 @@ class Config:
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: return self.getint_override("common", "nfo_skip_days", fallback=30)
return self.getint_override("common", "nfo_skip_days")
except:
return 30
def stop_counter(self) -> int: def stop_counter(self) -> int:
try: return self.getint_override("common", "stop_counter", fallback=0)
return self.getint_override("common", "stop_counter")
except:
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")
@@ -171,6 +174,24 @@ class Config:
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 rerun_delay(self) -> int:
value = self.get_override("common", "rerun_delay")
if not (isinstance(value, str) and re.match(r'^[\dsmh]+$', value, re.I)):
return 0 # not match '1h30m45s' or '30' or '1s2m1h4s5m'
if value.isnumeric() and int(value) >= 0:
return int(value)
sec = 0
sv = re.findall(r'(\d+)s', value, re.I)
mv = re.findall(r'(\d+)m', value, re.I)
hv = re.findall(r'(\d+)h', value, re.I)
for v in sv:
sec += int(v)
for v in mv:
sec += int(v) * 60
for v in hv:
sec += int(v) * 3600
return sec
def is_translate(self) -> bool: def is_translate(self) -> bool:
return self.conf.getboolean("translate", "switch") return self.conf.getboolean("translate", "switch")
@@ -247,8 +268,8 @@ class Config:
def media_type(self) -> str: def media_type(self) -> str:
return self.conf.get('media', 'media_type') return self.conf.get('media', 'media_type')
def sub_rule(self): def sub_rule(self) -> typing.Set[str]:
return self.conf.get('media', 'sub_type').split(',') return set(self.conf.get('media', 'sub_type').lower().split(','))
def naming_rule(self) -> str: def naming_rule(self) -> str:
return self.conf.get("Name_Rule", "naming_rule") return self.conf.get("Name_Rule", "naming_rule")
@@ -329,22 +350,23 @@ class Config:
return 1 return 1
def cc_convert_vars(self) -> str: def cc_convert_vars(self) -> str:
try: return self.conf.get("cc_convert", "vars",
return self.conf.get("cc_convert", "vars") fallback="actor,director,label,outline,series,studio,tag,title")
except:
return "actor,director,label,outline,series,studio,tag,title"
def javdb_sites(self) -> str: def javdb_sites(self) -> str:
try: return self.conf.get("javdb", "sites", fallback="38,39")
return self.conf.get("javdb", "sites")
except:
return "33,34"
def face_locations_model(self) -> str: def face_locations_model(self) -> str:
try: return self.conf.get("face", "locations_model", fallback="hog")
return self.conf.get("face", "locations_model")
except: def face_uncensored_only(self) -> bool:
return "hog" return self.conf.getboolean("face", "uncensored_only", fallback=True)
def face_aways_imagecut(self) -> bool:
return self.getboolean_override("face", "aways_imagecut", fallback=False)
def face_aspect_ratio(self) -> float:
return self.conf.getfloat("face", "aspect_ratio", fallback=2.12)
@staticmethod @staticmethod
def _exit(sec: str) -> None: def _exit(sec: str) -> None:
@@ -375,6 +397,7 @@ class Config:
conf.set(sec1, "ignore_failed_list", 0) conf.set(sec1, "ignore_failed_list", 0)
conf.set(sec1, "download_only_missing_images", 1) conf.set(sec1, "download_only_missing_images", 1)
conf.set(sec1, "mapping_table_validity", 7) conf.set(sec1, "mapping_table_validity", 7)
conf.set(sec1, "rerun_delay", 0)
sec2 = "proxy" sec2 = "proxy"
conf.add_section(sec2) conf.add_section(sec2)
@@ -428,9 +451,9 @@ class Config:
sec11 = "media" sec11 = "media"
conf.add_section(sec11) conf.add_section(sec11)
conf.set(sec11, "media_type", 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") ".mp4,.avi,.rmvb,.wmv,.mov,.mkv,.flv,.ts,.webm,iso")
conf.set(sec11, "sub_type", conf.set(sec11, "sub_type",
".smi,.srt,.idx,.sub,.sup,.psb,.ssa,.ass,.txt,.usf,.xss,.ssf,.rt,.lrc,.sbv,.vtt,.ttml") ".smi,.srt,.idx,.sub,.sup,.psb,.ssa,.ass,.usf,.xss,.ssf,.rt,.lrc,.sbv,.vtt,.ttml")
sec12 = "watermark" sec12 = "watermark"
conf.add_section(sec12) conf.add_section(sec12)

220
core.py
View File

@@ -10,6 +10,7 @@ from PIL import Image
from io import BytesIO from io import BytesIO
from pathlib import Path from pathlib import Path
from datetime import datetime from datetime import datetime
from lxml import etree
from ADC_function import * from ADC_function import *
from WebCrawler import get_data_from_json from WebCrawler import get_data_from_json
@@ -69,10 +70,12 @@ def get_info(json_data): # 返回json里的数据
return title, studio, year, outline, runtime, director, actor_photo, release, number, cover, trailer, website, series, label return title, studio, year, outline, runtime, director, actor_photo, release, number, cover, trailer, website, series, label
def small_cover_check(path, number, cover_small, leak_word, c_word, hack_word, filepath): def small_cover_check(path, filename, cover_small, movie_path):
filename = f"{number}{leak_word}{c_word}{hack_word}-poster.jpg" full_filepath = Path(path) / filename
download_file_with_filename(cover_small, filename, path, filepath) if config.getInstance().download_only_missing_images() and not file_not_exist_or_empty(str(full_filepath)):
print('[+]Image Downloaded! ' + os.path.join(path, filename)) return
download_file_with_filename(cover_small, filename, path, movie_path)
print('[+]Image Downloaded! ' + full_filepath.name)
def create_folder(json_data): # 创建文件夹 def create_folder(json_data): # 创建文件夹
@@ -213,7 +216,7 @@ def extrafanart_download_one_by_one(data, path, filepath):
break break
if file_not_exist_or_empty(jpg_fullpath): if file_not_exist_or_empty(jpg_fullpath):
return return
print('[+]Image Downloaded!', jpg_fullpath) print('[+]Image Downloaded!', Path(jpg_fullpath).name)
j += 1 j += 1
if conf.debug(): if conf.debug():
print(f'[!]Extrafanart download one by one mode runtime {time.perf_counter() - tm_start:.3f}s') print(f'[!]Extrafanart download one by one mode runtime {time.perf_counter() - tm_start:.3f}s')
@@ -244,7 +247,7 @@ def extrafanart_download_threadpool(url_list, save_dir, number):
if failed: # 非致命错误，电影不移入失败文件夹，将来可以用模式3补齐 if failed: # 非致命错误，电影不移入失败文件夹，将来可以用模式3补齐
print(f"[-]Failed downloaded {failed}/{len(result)} extrafanart images for [{number}] to '{extrafanart_dir}', you may retry run mode 3 later.") print(f"[-]Failed downloaded {failed}/{len(result)} extrafanart images for [{number}] to '{extrafanart_dir}', you may retry run mode 3 later.")
else: else:
print(f"[+]Successfully downloaded {len(result)} extrafanart to '{extrafanart_dir}'") print(f"[+]Successfully downloaded {len(result)} extrafanarts.")
if conf.debug(): if conf.debug():
print(f'[!]Extrafanart download ThreadPool mode runtime {time.perf_counter() - tm_start:.3f}s') print(f'[!]Extrafanart download ThreadPool mode runtime {time.perf_counter() - tm_start:.3f}s')
@@ -255,7 +258,7 @@ def image_ext(url):
return ".jpg" return ".jpg"
# 封面是否下载成功，否则移动到failed # 封面是否下载成功，否则移动到failed
def image_download(cover, fanart_path,thumb_path, path, filepath): def image_download(cover, fanart_path, thumb_path, path, filepath):
full_filepath = os.path.join(path, fanart_path) full_filepath = os.path.join(path, fanart_path)
if config.getInstance().download_only_missing_images() and not file_not_exist_or_empty(full_filepath): if config.getInstance().download_only_missing_images() and not file_not_exist_or_empty(full_filepath):
return return
@@ -273,7 +276,7 @@ def image_download(cover, fanart_path,thumb_path, path, filepath):
break break
if file_not_exist_or_empty(full_filepath): if file_not_exist_or_empty(full_filepath):
return return
print('[+]Image Downloaded!', full_filepath) print('[+]Image Downloaded!', Path(full_filepath).name)
shutil.copyfile(full_filepath, os.path.join(path, thumb_path)) shutil.copyfile(full_filepath, os.path.join(path, thumb_path))
@@ -291,6 +294,12 @@ def print_files(path, leak_word, c_word, naming_rule, part, cn_sub, json_data, f
print(f"[-]Fatal error! can not make folder '{path}'") print(f"[-]Fatal error! can not make folder '{path}'")
sys.exit(0) sys.exit(0)
old_nfo = None
try:
if os.path.isfile(nfo_path):
old_nfo = etree.parse(nfo_path)
except:
pass
# KODI内查看影片信息时找不到number，配置naming_rule=number+'#'+title虽可解决 # KODI内查看影片信息时找不到number，配置naming_rule=number+'#'+title虽可解决
# 但使得标题太长，放入时常为空的outline内会更适合，软件给outline留出的显示版面也较大 # 但使得标题太长，放入时常为空的outline内会更适合，软件给outline留出的显示版面也较大
outline = f"{number}#{outline}" outline = f"{number}#{outline}"
@@ -354,11 +363,17 @@ def print_files(path, leak_word, c_word, naming_rule, part, cn_sub, json_data, f
print(" <premiered>" + release + "</premiered>", file=code) print(" <premiered>" + release + "</premiered>", file=code)
print(" <releasedate>" + release + "</releasedate>", file=code) print(" <releasedate>" + release + "</releasedate>", file=code)
print(" <release>" + release + "</release>", file=code) print(" <release>" + release + "</release>", file=code)
if old_nfo:
try:
xur = old_nfo.xpath('//userrating/text()')[0]
if isinstance(xur, str) and re.match('\d+\.\d+|\d+', xur.strip()):
print(f" <userrating>{xur.strip()}</userrating>", file=code)
except:
pass
try: try:
f_rating = json_data['用户评分'] f_rating = json_data['用户评分']
uc = json_data['评分人数'] uc = json_data['评分人数']
print(f""" <userrating>{round(f_rating * 2.0)}</userrating> print(f""" <rating>{round(f_rating * 2.0, 1)}</rating>
<rating>{round(f_rating * 2.0, 1)}</rating>
<criticrating>{round(f_rating * 20.0, 1)}</criticrating> <criticrating>{round(f_rating * 20.0, 1)}</criticrating>
<ratings> <ratings>
<rating name="javdb" max="5" default="true"> <rating name="javdb" max="5" default="true">
@@ -476,10 +491,9 @@ def add_to_pic(pic_path, img_pic, size, count, mode):
# ========================结束================================= # ========================结束=================================
def paste_file_to_folder(filepath, path, number, leak_word, c_word, hack_word): # 文件路径，番号，后缀，要移动至的位置 def paste_file_to_folder(filepath, path, multi_part, number, part, leak_word, c_word, hack_word): # 文件路径，番号，后缀，要移动至的位置
filepath_obj = pathlib.Path(filepath) filepath_obj = pathlib.Path(filepath)
houzhui = filepath_obj.suffix houzhui = filepath_obj.suffix
file_parent_origin_path = str(filepath_obj.parent)
try: try:
targetpath = os.path.join(path, f"{number}{leak_word}{c_word}{hack_word}{houzhui}") targetpath = os.path.join(path, f"{number}{leak_word}{c_word}{hack_word}{houzhui}")
# 任何情况下都不要覆盖，以免遭遇数据源或者引擎错误导致所有文件得到同一个number，逐一 # 任何情况下都不要覆盖，以免遭遇数据源或者引擎错误导致所有文件得到同一个number，逐一
@@ -505,25 +519,21 @@ def paste_file_to_folder(filepath, path, number, leak_word, c_word, hack_word):
filerelpath = os.path.relpath(filepath, path) filerelpath = os.path.relpath(filepath, path)
os.symlink(filerelpath, targetpath) os.symlink(filerelpath, targetpath)
except: except:
os.symlink(filepath_obj.resolve(), targetpath) os.symlink(str(filepath_obj.resolve()), targetpath)
sub_res = config.getInstance().sub_rule()
for subname in sub_res: sub_res = config.getInstance().sub_rule()
sub_filepath = str(filepath_obj.with_suffix(subname)) for subfile in filepath_obj.parent.glob('**/*'):
if os.path.isfile(sub_filepath.replace(subname,".chs" + subname)): if subfile.is_file() and subfile.suffix.lower() in sub_res:
sub_filepath = sub_filepath.replace(subname,".chs" + subname) if multi_part and part.lower() not in subfile.name.lower():
subname = ".chs" + subname continue
elif os.path.isfile(sub_filepath.replace(subname,".cht" + subname)): sub_targetpath = Path(path) / f"{number}{leak_word}{c_word}{hack_word}{''.join(subfile.suffixes)}"
sub_filepath = sub_filepath.replace(subname, ".cht" + subname)
subname = ".cht" + subname
if os.path.isfile(sub_filepath):
if link_mode not in (1, 2): if link_mode not in (1, 2):
shutil.move(sub_filepath, os.path.join(path, f"{number}{leak_word}{c_word}{hack_word}{subname}")) shutil.move(str(subfile), str(sub_targetpath))
print('[+]Sub moved!') print(f"[+]Sub Moved! {sub_targetpath.name}")
else: else:
shutil.copyfile(sub_filepath, os.path.join(path, f"{number}{leak_word}{c_word}{hack_word}{subname}")) shutil.copyfile(str(subfile), str(sub_targetpath))
print('[+]Sub Copied!') print(f"[+]Sub Copied! {sub_targetpath.name}")
return True return
except FileExistsError as fee: except FileExistsError as fee:
print(f'[-]FileExistsError: {fee}') print(f'[-]FileExistsError: {fee}')
@@ -542,24 +552,39 @@ def paste_file_to_folder_mode2(filepath, path, multi_part, number, part, leak_wo
number += part # 这时number会被附加上CD1后缀 number += part # 这时number会被附加上CD1后缀
filepath_obj = pathlib.Path(filepath) filepath_obj = pathlib.Path(filepath)
houzhui = filepath_obj.suffix houzhui = filepath_obj.suffix
file_parent_origin_path = str(filepath_obj.parent)
targetpath = os.path.join(path, f"{number}{part}{leak_word}{c_word}{hack_word}{houzhui}") targetpath = os.path.join(path, f"{number}{part}{leak_word}{c_word}{hack_word}{houzhui}")
if os.path.exists(targetpath): if os.path.exists(targetpath):
raise FileExistsError('File Exists on destination path, we will never overwriting.') raise FileExistsError('File Exists on destination path, we will never overwriting.')
try: try:
if config.getInstance().link_mode(): link_mode = config.getInstance().link_mode()
os.symlink(filepath, targetpath) create_softlink = False
else: if link_mode not in (1, 2):
shutil.move(filepath, targetpath) shutil.move(filepath, targetpath)
elif link_mode == 2:
try:
os.link(filepath, targetpath, follow_symlinks=False)
except:
create_softlink = True
if link_mode == 1 or create_softlink:
try:
filerelpath = os.path.relpath(filepath, path)
os.symlink(filerelpath, targetpath)
except:
os.symlink(str(filepath_obj.resolve()), targetpath)
sub_res = config.getInstance().sub_rule() sub_res = config.getInstance().sub_rule()
for subname in sub_res: for subfile in filepath_obj.parent.glob('**/*'):
sub_filepath = str(filepath_obj.with_suffix(subname)) if subfile.is_file() and subfile.suffix.lower() in sub_res:
if os.path.isfile(sub_filepath): # 字幕移动 if multi_part and part.lower() not in subfile.name.lower():
shutil.move(sub_filepath, os.path.join(path, f"{number}{part}{leak_word}{c_word}{hack_word}{subname}")) continue
print('[+]Sub moved!') sub_targetpath = Path(path) / f"{number}{leak_word}{c_word}{hack_word}{''.join(subfile.suffixes)}"
print('[!]Success') if link_mode not in (1, 2):
return True shutil.move(str(subfile), str(sub_targetpath))
print(f"[+]Sub Moved! {sub_targetpath.name}")
else:
shutil.copyfile(str(subfile), str(sub_targetpath))
print(f"[+]Sub Copied! {sub_targetpath.name}")
return
except FileExistsError as fee: except FileExistsError as fee:
print(f'[-]FileExistsError: {fee}') print(f'[-]FileExistsError: {fee}')
return return
@@ -571,18 +596,6 @@ def paste_file_to_folder_mode2(filepath, path, multi_part, number, part, leak_wo
return return
def get_part(filepath):
try:
if re.search('-CD\d+', filepath):
return re.findall('-CD\d+', filepath)[0]
if re.search('-cd\d+', filepath):
return re.findall('-cd\d+', filepath)[0]
except:
print("[-]failed!Please rename the filename again!")
moveFailedFolder(filepath)
return
def debug_print(data: json): def debug_print(data: json):
try: try:
print("[+] ------- DEBUG INFO -------") print("[+] ------- DEBUG INFO -------")
@@ -595,14 +608,65 @@ def debug_print(data: json):
if i == 'extrafanart': if i == 'extrafanart':
print('[+] -', "%-14s" % i, ':', len(v), 'links') print('[+] -', "%-14s" % i, ':', len(v), 'links')
continue continue
print('[+] -', "%-14s" % i, ':', v) print(f'[+] - {i:<{cnspace(i,14)}} : {v}')
print("[+] ------- DEBUG INFO -------") print("[+] ------- DEBUG INFO -------")
except: except:
pass pass
def core_main(file_path, number_th, oCC): def core_main_no_net_op(movie_path, number):
conf = config.getInstance()
part = ''
leak_word = ''
leak = 0
c_word = ''
cn_sub = ''
hack = ''
hack_word = ''
ext = '.jpg'
imagecut = 1
path = str(Path(movie_path).parent)
if re.search('-CD\d+', movie_path, re.IGNORECASE):
part = re.findall('-CD\d+', movie_path, re.IGNORECASE)[0].upper()
if re.search(r'-C(\.\w+$|-\w+)|\d+ch(\.\w+$|-\w+)', movie_path,
re.I) or '中文' in movie_path or '字幕' in movie_path:
cn_sub = '1'
c_word = '-C' # 中文字幕影片后缀
uncensored = 1 if is_uncensored(number) else 0
if '流出' in movie_path or 'uncensored' in movie_path:
leak_word = '-流出' # 流出影片后缀
leak = 1
if 'hack'.upper() in str(movie_path).upper() or '破解' in movie_path:
hack = 1
hack_word = "-hack"
prestr = f"{number}{leak_word}{c_word}{hack_word}"
fanart_path = f"{prestr}-fanart{ext}"
poster_path = f"{prestr}-poster{ext}"
thumb_path = f"{prestr}-thumb{ext}"
full_fanart_path = os.path.join(path, fanart_path)
full_poster_path = os.path.join(path, poster_path)
full_thumb_path = os.path.join(path, thumb_path)
full_nfo = Path(path) / f"{prestr}{part}.nfo"
if full_nfo.is_file():
if full_nfo.read_text(encoding='utf-8').find(r'<tag>无码</tag>') >= 0:
uncensored = 1
else:
return
if not all(os.path.isfile(f) for f in (full_fanart_path, full_thumb_path)):
return
cutImage(imagecut, path, fanart_path, poster_path, bool(conf.face_uncensored_only() and not uncensored))
if conf.is_watermark():
add_mark(full_poster_path, full_thumb_path, cn_sub, leak, uncensored, hack)
def core_main(movie_path, number_th, oCC):
conf = config.getInstance() conf = config.getInstance()
# =======================================================================初始化所需变量 # =======================================================================初始化所需变量
multi_part = 0 multi_part = 0
@@ -614,8 +678,6 @@ def core_main(file_path, number_th, oCC):
hack = '' hack = ''
hack_word = '' hack_word = ''
filepath = file_path # 影片的路径 绝对路径
# 下面被注释的变量不需要 # 下面被注释的变量不需要
#rootpath= os.getcwd #rootpath= os.getcwd
number = number_th number = number_th
@@ -623,7 +685,7 @@ def core_main(file_path, number_th, oCC):
# Return if blank dict returned (data not found) # Return if blank dict returned (data not found)
if not json_data: if not json_data:
moveFailedFolder(filepath) moveFailedFolder(movie_path)
return return
if json_data["number"] != number: if json_data["number"] != number:
@@ -636,25 +698,28 @@ def core_main(file_path, number_th, oCC):
imagecut = json_data.get('imagecut') imagecut = json_data.get('imagecut')
tag = json_data.get('tag') tag = json_data.get('tag')
# =======================================================================判断-C,-CD后缀 # =======================================================================判断-C,-CD后缀
if '-CD' in filepath or '-cd' in filepath: if re.search('-CD\d+', movie_path, re.IGNORECASE):
multi_part = 1 multi_part = 1
part = get_part(filepath) part = re.findall('-CD\d+', movie_path, re.IGNORECASE)[0].upper()
if '-c.' in filepath or '-C.' in filepath or '中文' in filepath or '字幕' in filepath: if re.search(r'-C(\.\w+$|-\w+)|\d+ch(\.\w+$|-\w+)', movie_path,
re.I) or '中文' in movie_path or '字幕' in movie_path:
cn_sub = '1' cn_sub = '1'
c_word = '-C' # 中文字幕影片后缀 c_word = '-C' # 中文字幕影片后缀
# 判断是否无码 # 判断是否无码
uncensored = 1 if is_uncensored(number) else 0 uncensored = 1 if is_uncensored(number) else 0
unce = json_data.get('无码')
if type(unce) is bool:
uncensored = 1 if unce else 0
if '流出' in movie_path or 'uncensored' in movie_path:
if '流出' in filepath or 'uncensored' in filepath:
liuchu = '流出' liuchu = '流出'
leak = 1 leak = 1
leak_word = '-流出' # 流出影片后缀 leak_word = '-流出' # 流出影片后缀
else: else:
leak = 0 leak = 0
if 'hack'.upper() in str(filepath).upper() or '破解' in filepath: if 'hack'.upper() in str(movie_path).upper() or '破解' in movie_path:
hack = 1 hack = 1
hack_word = "-hack" hack_word = "-hack"
@@ -683,77 +748,76 @@ def core_main(file_path, number_th, oCC):
# 检查小封面, 如果image cut为3，则下载小封面 # 检查小封面, 如果image cut为3，则下载小封面
if imagecut == 3: if imagecut == 3:
small_cover_check(path, number, json_data.get('cover_small'), leak_word, c_word, hack_word, filepath) small_cover_check(path, poster_path, json_data.get('cover_small'), movie_path)
# creatFolder会返回番号路径 # creatFolder会返回番号路径
image_download( cover, fanart_path,thumb_path, path, filepath) image_download( cover, fanart_path,thumb_path, path, movie_path)
if not multi_part or part.lower() == '-cd1': if not multi_part or part.lower() == '-cd1':
try: try:
# 下载预告片 # 下载预告片
if conf.is_trailer() and json_data.get('trailer'): if conf.is_trailer() and json_data.get('trailer'):
trailer_download(json_data.get('trailer'), leak_word, c_word, hack_word, number, path, filepath) trailer_download(json_data.get('trailer'), leak_word, c_word, hack_word, number, path, movie_path)
except: except:
pass pass
try: try:
# 下载剧照 data, path, filepath # 下载剧照 data, path, filepath
if conf.is_extrafanart() and json_data.get('extrafanart'): if conf.is_extrafanart() and json_data.get('extrafanart'):
extrafanart_download(json_data.get('extrafanart'), path, number, filepath) extrafanart_download(json_data.get('extrafanart'), path, number, movie_path)
except: except:
pass pass
# 裁剪图 # 裁剪图
cutImage(imagecut, path , fanart_path, poster_path) cutImage(imagecut, path, fanart_path, poster_path, bool(conf.face_uncensored_only() and not uncensored))
# 添加水印 # 添加水印
if conf.is_watermark(): if conf.is_watermark():
add_mark(os.path.join(path,poster_path), os.path.join(path,thumb_path), cn_sub, leak, uncensored, hack) add_mark(os.path.join(path,poster_path), os.path.join(path,thumb_path), cn_sub, leak, uncensored, hack)
# 移动电影 # 移动电影
paste_file_to_folder(filepath, path, number, leak_word, c_word, hack_word) paste_file_to_folder(movie_path, path, multi_part, number, part, leak_word, c_word, hack_word)
# 最后输出.nfo元数据文件，以完成.nfo文件创建作为任务成功标志 # 最后输出.nfo元数据文件，以完成.nfo文件创建作为任务成功标志
print_files(path, leak_word, c_word, json_data.get('naming_rule'), part, cn_sub, json_data, filepath, tag, json_data.get('actor_list'), liuchu, uncensored, hack_word print_files(path, leak_word, c_word, json_data.get('naming_rule'), part, cn_sub, json_data, movie_path, tag, json_data.get('actor_list'), liuchu, uncensored, hack_word
,fanart_path,poster_path,thumb_path) ,fanart_path,poster_path,thumb_path)
elif conf.main_mode() == 2: elif conf.main_mode() == 2:
# 创建文件夹 # 创建文件夹
path = create_folder(json_data) path = create_folder(json_data)
# 移动文件 # 移动文件
paste_file_to_folder_mode2(filepath, path, multi_part, number, part, leak_word, c_word, hack_word) paste_file_to_folder_mode2(movie_path, path, multi_part, number, part, leak_word, c_word, hack_word)
if conf.is_watermark(): if conf.is_watermark():
add_mark(os.path.join(path,poster_path), os.path.join(path,thumb_path), cn_sub, leak, uncensored, hack) add_mark(os.path.join(path,poster_path), os.path.join(path,thumb_path), cn_sub, leak, uncensored, hack)
elif conf.main_mode() == 3: elif conf.main_mode() == 3:
path = str(Path(file_path).parent) path = str(Path(movie_path).parent)
if multi_part == 1: if multi_part == 1:
number += part # 这时number会被附加上CD1后缀 number += part # 这时number会被附加上CD1后缀
# 检查小封面, 如果image cut为3，则下载小封面 # 检查小封面, 如果image cut为3，则下载小封面
if imagecut == 3: if imagecut == 3:
small_cover_check(path, number, json_data.get('cover_small'), leak_word, c_word, hack_word, filepath) small_cover_check(path, poster_path, json_data.get('cover_small'), movie_path)
# creatFolder会返回番号路径 # creatFolder会返回番号路径
image_download( cover, fanart_path,thumb_path, path, filepath) image_download( cover, fanart_path, thumb_path, path, movie_path)
if not multi_part or part.lower() == '-cd1': if not multi_part or part.lower() == '-cd1':
# 下载预告片 # 下载预告片
if conf.is_trailer() and json_data.get('trailer'): if conf.is_trailer() and json_data.get('trailer'):
trailer_download(json_data.get('trailer'), leak_word, c_word, hack_word, number, path, filepath) trailer_download(json_data.get('trailer'), leak_word, c_word, hack_word, number, path, movie_path)
# 下载剧照 data, path, filepath # 下载剧照 data, path, filepath
if conf.is_extrafanart() and json_data.get('extrafanart'): if conf.is_extrafanart() and json_data.get('extrafanart'):
extrafanart_download(json_data.get('extrafanart'), path, number, filepath) extrafanart_download(json_data.get('extrafanart'), path, number, movie_path)
# 裁剪图 # 裁剪图
cutImage(imagecut, path , fanart_path, poster_path) cutImage(imagecut, path, fanart_path, poster_path, bool(conf.face_uncensored_only() and not uncensored))
# 添加水印 # 添加水印
if conf.is_watermark(): if conf.is_watermark():
add_mark(os.path.join(path,poster_path), os.path.join(path,thumb_path), cn_sub, leak, uncensored, hack) add_mark(os.path.join(path,poster_path), os.path.join(path,thumb_path), cn_sub, leak, uncensored, hack)
# 最后输出.nfo元数据文件，以完成.nfo文件创建作为任务成功标志 # 最后输出.nfo元数据文件，以完成.nfo文件创建作为任务成功标志
print_files(path, leak_word, c_word, json_data.get('naming_rule'), part, cn_sub, json_data, filepath, print_files(path, leak_word, c_word, json_data.get('naming_rule'), part, cn_sub, json_data, movie_path,
tag, json_data.get('actor_list'), liuchu, uncensored, hack_word,fanart_path,poster_path,thumb_path) tag, json_data.get('actor_list'), liuchu, uncensored, hack_word,fanart_path,poster_path,thumb_path)

32
number_parser.py
View File

@@ -5,8 +5,9 @@ import config
import typing 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|" "^\w+\.(cc|com|net|me|club|jp|tv|xyz|biz|wiki|info|tw|us|de)@|^22-sht\.me|"
"^\w+\.(cc|com)@|-uncensored|_uncensored|-leak|_leak|-4K|_4K", "^(fhd|hd|sd|1080p|720p|4K)(-|_)|"
"(-|_)(fhd|hd|sd|1080p|720p|4K|uncensored|leak)",
re.IGNORECASE) re.IGNORECASE)
@@ -46,9 +47,13 @@ def get_number(debug: bool, file_path: str) -> str:
lower_check = filename.lower() lower_check = filename.lower()
if 'fc2' in lower_check: if 'fc2' in lower_check:
filename = lower_check.replace('ppv', '').replace('--', '-').replace('_', '-').upper() filename = lower_check.replace('ppv', '').replace('--', '-').replace('_', '-').upper()
filename = re.sub("(-|_)cd\d{1,2}", "", filename, flags=re.IGNORECASE) filename = re.sub("-cd\d{1,2}", "", filename, flags=re.IGNORECASE)
if not re.search("-|_", filename): # 去掉-CD1之后再无-的情况，例如n1012-CD1.wmv
return str(re.search(r'\w+', filename[:filename.find('.')], re.A).group())
file_number = str(re.search(r'\w+(-|_)\w+', filename, re.A).group()) file_number = str(re.search(r'\w+(-|_)\w+', filename, re.A).group())
file_number = re.sub("(-|_)c$", "", file_number, flags=re.IGNORECASE) file_number = re.sub("(-|_)c$", "", file_number, flags=re.IGNORECASE)
if re.search("\d+ch$", file_number, flags=re.I):
file_number = file_number[:-2]
return file_number.upper() return file_number.upper()
else: # 提取不含减号-的番号，FANZA CID else: # 提取不含减号-的番号，FANZA CID
# 欧美番号匹配规则 # 欧美番号匹配规则
@@ -146,16 +151,23 @@ if __name__ == "__main__":
"caribean-020317_001.nfo", # -号误命名为_号的 "caribean-020317_001.nfo", # -号误命名为_号的
"257138_3xplanet_1Pondo_080521_001.mp4", "257138_3xplanet_1Pondo_080521_001.mp4",
"ADV-R0624-CD3.wmv", # 多碟影片 "ADV-R0624-CD3.wmv", # 多碟影片
"XXX-AV 22061-CD5.iso", # 新支持片商格式 xxx-av-22061 命名规则来自javdb数据源 "XXX-AV 22061-CD5.iso", # 支持片商格式 xxx-av-22061 命名规则来自javdb数据源
"xxx-av 20589.mp4", "xxx-av 20589.mp4",
"Muramura-102114_145-HD.wmv", # 新支持片商格式 102114_145 命名规则来自javdb数据源 "Muramura-102114_145-HD.wmv", # 支持片商格式 102114_145 命名规则来自javdb数据源
"heydouga-4102-023-CD2.iso", # 新支持片商格式 heydouga-4102-023 命名规则来自javdb数据源 "heydouga-4102-023-CD2.iso", # 支持片商格式 heydouga-4102-023 命名规则来自javdb数据源
"HeyDOuGa4236-1048 Ai Qiu - .mp4", # heydouga-4236-1048 命名规则来自javdb数据源 "HeyDOuGa4236-1048 Ai Qiu - .mp4", # heydouga-4236-1048 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 "pacopacomama-093021_539-FHD.mkv", # 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",
"hhd800.com@STARS-566.mp4", "hhd800.com@STARS-566-HD.mp4",
"jav20s8.com@GIGL-677.mp4", "jav20s8.com@GIGL-677_4K.mp4",
"sbw99.cc@iesp-653.mp4" "sbw99.cc@iesp-653-4K.mp4",
"4K-ABP-358_C.mkv",
"n1012-CD1.wmv",
"[]n1012-CD2.wmv",
"rctd-460ch.mp4", # 除支持-C硬字幕外，新支持ch硬字幕
"rctd-461CH-CD2.mp4", # ch后可加CDn
"rctd-461-Cd3-C.mp4", # CDn后可加-C
"rctd-461-C-cD4.mp4", # cD1 Cd1 cd1 CD1 最终生成.nfo时统一为大写CD1
) )