diff --git a/get115list.exe b/get115list.exe index 169a944..730f739 100644 Binary files a/get115list.exe and b/get115list.exe differ diff --git a/get115list.py b/get115list.py index f376cc1..095c0e8 100644 --- a/get115list.py +++ b/get115list.py @@ -7,12 +7,25 @@ import time import traceback import os import re +import sys +import traceback count=0 +failcount=0 + +fullscan=True def walk_dir(fs,f,replaceroot): dirlist=list() - file_list = fs.listdir_attr() + try: + file_list = fs.listdir_attr() + except KeyboardInterrupt: + print("get ctrl+c, exit") + sys.exit(1) + except: + traceback.print_exc() + time.sleep(1) + return filetype_re=re.compile(r'\.(png|jpg|jpeg|bmp|gif|doc|nfo|flac|mp3|wma|ape|cue|wav|dst|dff|dts|ac3|eac3|txt)$') for file_obj in file_list: if not file_obj.is_directory: @@ -31,11 +44,18 @@ def walk_dir(fs,f,replaceroot): dirlist.append(file_obj.path) for dirItem in dirlist: fs.chdir(dirItem) - # global count - # count=count+1 - # if count%4==0: - # time.sleep(1) - walk_dir(fs,f,replaceroot) + global count + count=count+1 + if count%3==0: + time.sleep(1) + try: + walk_dir(fs,f,replaceroot) + except KeyboardInterrupt: + print("get ctrl+c, exit") + sys.exit(1) + except: + traceback.print_exc() + time.sleep(1) return def main(): @@ -53,8 +73,19 @@ def main(): shareUrl = "https://115.com/s/" + shareUrl print("cookie:"+args.cookie+", shareurl:"+shareUrl) + cidre = re.compile(r'cid=([0-9]+)') + matches = cidre.findall(shareUrl) + cid = None + if len(matches)>0: + cid=int(matches[0]) + shareUrl = cidre.sub("", shareUrl).replace("?&","?").replace("&&","&") + fs = client.get_share_fs(shareUrl) + #if cid != None: + # fs.chdir(cid) + + count=0 f=open(args.output, mode="a", encoding="utf-8") walk_dir(fs,f,args.replaceroot) diff --git a/getalist.exe b/getalist.exe new file mode 100644 index 0000000..e389a1d Binary files /dev/null and b/getalist.exe differ diff --git a/getalist.py b/getalist.py new file mode 100644 index 0000000..29db4fe --- /dev/null +++ b/getalist.py @@ -0,0 +1,173 @@ +#!/usr/bin/env python +# -*- coding: utf- -*- + +import argparse +import os +import time +import re +import requests +import traceback +import json +import sys + +count=0 + +failcount=0 + +fullscan=True + +def walk(headers:dict, api_url:str, current_path="/", output_file=None, replaceroot=None, lastpath=None): + params = {"path": current_path} + #print(f"params:{params}") + try: + resp = requests.post( + api_url+"/api/fs/list", + headers=headers, + json=params, + stream=True, + timeout=(5,15), + ) + except KeyboardInterrupt: + print("get ctrl+c, exit") + sys.exit(1) + except: + traceback.print_exc() + print(f"request fail to server:{api_url}") + time.sleep(1) + #sys.exit(1) + return + resp.raise_for_status() + body = resp.content.decode('utf-8') + resp.close() + # 解析 JSON 数据 + data_dict = json.loads(body) + + # 获取 raw_url + global failcount + try: + items = data_dict['data']['content'] + failcount=0 + except: + traceback.print_exc() + time.sleep(1) + #sys.exit(1) + failcount += 1 + if failcount>10: + sys.exit(1) + return + + print(f"contentlist len:{len(items)}") + # items=client.list(current_path) + + filetype_re=re.compile(r'\.(png|jpg|jpeg|bmp|gif|doc|nfo|flac|mp3|wma|ape|cue|wav|dst|dff|dts|ac3|eac3|txt)$') + # print(items) + for item in items: + full_path = f"{current_path}/{item['name']}".replace("//", "/") + try: + # is_dir = client.is_dir(full_path) + # is_dir = full_path.endswith("/") + is_dir = item["is_dir"] + except: + continue + global fullscan + # print(f"fullscan:{fullscan}, full_path:{full_path}, lastpath:{lastpath}") + if is_dir: # 判断是否为目录 + global count + count=count+1 + if fullscan: + if count%3==0: + time.sleep(1) + #else: + # if count%10==0: + # time.sleep(1) + if not fullscan and not full_path in lastpath: + print(f"not fullscan and full_path:{full_path} not in lastpath:{lastpath}, skip") + continue + if full_path == lastpath: + print(f"found full_path:{full_path} equal lastpath:{lastpath}, enter fullscan mode") + time.sleep(3) + fullscan = True + try: + walk(headers, api_url, full_path, output_file, replaceroot, lastpath) + except KeyboardInterrupt: + print("get ctrl+c, exit") + sys.exit(1) + except: + traceback.print_exc() + #sys.exit(1) + pass + elif not fullscan: + continue + else: + if filetype_re.search(full_path) != None or "BDMV" in full_path: + continue + # size = client.info(full_path).get('size', 0) + size = item["size"] + if replaceroot!=None: + if replaceroot=="": + full_path=os.path.join("/",*full_path.split("/")[2:]) + else: + full_path=os.path.join("/",replaceroot,*full_path.split("/")[2:]) + print(f"{full_path}\t{size}") + if output_file != None: + output_file.write(f"{full_path}\t{size}\n") + output_file.flush() + + +from urllib.parse import urlparse + +def extract_url_components(url): + """分解 URL 为 schema（协议）、hostname（主机地址）、path（路径）""" + parsed = urlparse(url) + + # 提取核心组件 + schema = parsed.scheme or "http" # 默认协议处理 + hostname = f"{parsed.hostname}:{parsed.port}" # 自动过滤端口和认证信息 + path = parsed.path.rstrip('/') or '/' # 路径标准化 + + return schema, hostname, path + + +def main(): + parser = argparse.ArgumentParser(description='快速遍历AList目录') + parser.add_argument('--url', type=str, required=True, help='AList URL') + parser.add_argument('--token', type=str, default=None, required=False, help='AList token') + parser.add_argument('--output', type=str, required=True, help='输出文件') + parser.add_argument('--lastpath', type=str, default=None, required=False, help='最后扫到的路径（从此开始继续）') + parser.add_argument('--replaceroot', type=str, default=None, required=False, help='替换根目录名称') + args = parser.parse_args() + + schema, hostname, path = extract_url_components(args.url) + print(schema,hostname,path) + + print("AList URL:", args.url) + if args.lastpath == None: + try: + with open(args.output, "r", encoding="utf-8") as f: + tmplines = f.readlines() + for i in range(len(tmplines)-1, -1, -1): + line=tmplines[i].strip() + if line != None and line != "": + args.lastpath = os.path.dirname(line.split("\t")[0]) + break + except: + traceback.print_exc() + + output_file = open(args.output, mode="a", encoding="utf-8") + if args.lastpath != None and args.lastpath != "": + global fullscan + fullscan = False + if args.lastpath != None: + args.lastpath=args.lastpath.rstrip('/') + print(f"lastpath:{args.lastpath}") + headers = { + "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36", + "Content-Type": "application/json", + } + if args.token != None and args.token != "": + headers["Authorization"] = args.token + walk(headers, schema+"://"+hostname, path, output_file,args.replaceroot, args.lastpath) + output_file.close() + +if __name__ == '__main__': + main() diff --git a/getwebdavlist.exe b/getwebdavlist.exe index 83b9722..8c49abc 100644 Binary files a/getwebdavlist.exe and b/getwebdavlist.exe differ diff --git a/getwebdavlist.py b/getwebdavlist.py index ef7e0af..a9b0f7f 100644 --- a/getwebdavlist.py +++ b/getwebdavlist.py @@ -6,11 +6,29 @@ from webdav3.client import Client import os import time import re +import sys +import traceback count=0 +failcount=0 -def walk(client, current_path="/", output_file=None, replaceroot=None): - items=client.list(current_path) +fullscan=True + +def walk(client, current_path="/", output_file=None, replaceroot=None, lastpath=None): + global failcount + try: + items=client.list(current_path) + failcount=0 + except KeyboardInterrupt: + print("get ctrl+c, exit") + sys.exit(1) + except: + traceback.print_exc() + time.sleep(1) + failcount+=1 + if failcount>10: + sys.exit(1) + return filetype_re=re.compile(r'\.(png|jpg|jpeg|bmp|gif|doc|nfo|flac|mp3|wma|ape|cue|wav|dst|dff|dts|ac3|eac3|txt)$') # print(items) for item in items[1:]: @@ -20,15 +38,28 @@ def walk(client, current_path="/", output_file=None, replaceroot=None): is_dir = full_path.endswith("/") except: continue + global fullscan + # print(f"fullscan:{fullscan}, full_path:{full_path}, lastpath:{lastpath}") if is_dir: # 判断是否为目录 #global count #count=count+1 #if count%4==0: # time.sleep(1) + if not fullscan and not full_path in lastpath: + continue + if full_path == lastpath: + fullscan = True try: - walk(client, full_path, output_file, replaceroot) + walk(client, full_path, output_file, replaceroot, lastpath) + except KeyboardInterrupt: + print("get ctrl+c, exit") + sys.exit(1) except: + time.sleep(1) + #sys.exit(1) pass + elif not fullscan: + continue else: if filetype_re.search(full_path) != None or "BDMV" in full_path: continue @@ -41,6 +72,7 @@ def walk(client, current_path="/", output_file=None, replaceroot=None): print(f"{full_path}\t{size}") if output_file != None: output_file.write(f"{full_path}\t{size}\n") + output_file.flush() from urllib.parse import urlparse @@ -62,7 +94,8 @@ def main(): parser.add_argument('--url', type=str, required=True, help='WebDAV URL') parser.add_argument('--username', type=str, required=True, help='WebDAV username') parser.add_argument('--password', type=str, required=True, help='WebDAV password') - parser.add_argument('--output', type=str, required=True, help='outputfile') + parser.add_argument('--output', type=str, required=True, help='输出文件') + parser.add_argument('--lastpath', type=str, default=None, required=False, help='最后扫到的路径（从此开始继续）') parser.add_argument('--replaceroot', type=str, default=None, required=False, help='替换根目录名称') args = parser.parse_args() @@ -80,8 +113,26 @@ def main(): client = Client(options) print("WebDAV URL:", args.url) + if args.lastpath == None: + try: + with open(args.output, "r", encoding="utf-8") as f: + tmplines = f.readlines() + for i in range(len(tmplines)-1, -1, -1): + line=tmplines[i].strip() + if line != None and line != "": + args.lastpath = os.path.dirname(line.split("\t")[0]) + break + except: + traceback.print_exc() output_file = open(args.output, mode="a", encoding="utf-8") - walk(client, path, output_file,args.replaceroot) + if args.lastpath != None and args.lastpath != "": + global fullscan + fullscan = False + if args.lastpath != None: + if not args.lastpath.endswith("/"): + args.lastpath = args.lastpath+"/" + print(f"lastpath:{args.lastpath}") + walk(client, path, output_file,args.replaceroot, args.lastpath) output_file.close() if __name__ == '__main__': diff --git a/run.bat b/run.bat index 1ff9fc2..37b2991 100644 --- a/run.bat +++ b/run.bat @@ -1,3 +1,3 @@ @echo off -webdav_simulator.exe --alist_config "http://192.168.1.2:5678/,,#http://192.168.1.3:5678,alist-1234-5678," "xy115-all.txt.xz#xy.txt.xz" +webdav_simulator.exe --alist_config "http://192.168.1.2:5678/,,#http://192.168.1.3:5678,alist-1234-5678," "xy115-all.txt.xz#xy-dy.txt.xz" diff --git a/run.sh b/run.sh index c41ec89..179196b 100644 --- a/run.sh +++ b/run.sh @@ -18,4 +18,4 @@ cd "${progdir}" mkdir tmp chmod 777 tmp export TMPDIR=tmp -./webdav_simulator.amd64 --alist_config "http://192.168.1.2:5678,,#http://192.168.1.3:5678,alist-1234-5678," "xy115-all.txt.xz#xy.txt.xz" +./webdav_simulator.amd64 --alist_config "http://192.168.1.2:5678,,#http://192.168.1.3:5678,alist-1234-5678," "xy115-all.txt.xz#xy-dy.txt.xz" diff --git a/webdav_simulator.amd64 b/webdav_simulator.amd64 index 88b5786..2c1a1b8 100644 Binary files a/webdav_simulator.amd64 and b/webdav_simulator.amd64 differ diff --git a/webdav_simulator.arm64 b/webdav_simulator.arm64 index 6771947..1c7fbd1 100644 Binary files a/webdav_simulator.arm64 and b/webdav_simulator.arm64 differ diff --git a/webdav_simulator.exe b/webdav_simulator.exe index e060788..14e655c 100644 Binary files a/webdav_simulator.exe and b/webdav_simulator.exe differ diff --git a/xy-dailynew.txt.xz b/xy-dailynew.txt.xz new file mode 100644 index 0000000..14423b1 Binary files /dev/null and b/xy-dailynew.txt.xz differ diff --git a/xy-dy.txt.xz b/xy-dy.txt.xz new file mode 100644 index 0000000..0efd07b Binary files /dev/null and b/xy-dy.txt.xz differ