├── .gitignore ├── ADC_function.py ├── LICENSE ├── OOF_Rename.py ├── OOF_core.py ├── ReadMe.md ├── actor.py ├── avsox.py ├── config.ini ├── fanza.py ├── fc2fans_club.py ├── jav321.py ├── javbus.py ├── javdb.py ├── linux_make.py ├── mgstage.py ├── py_to_exe.bat ├── readme ├── 1.png ├── 2.png ├── This is readms.md's images folder └── single.gif └── ruquirments.txt /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | pip-wheel-metadata/ 24 | share/python-wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .nox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | nosetests.xml 48 | coverage.xml 49 | *.cover 50 | *.py,cover 51 | .hypothesis/ 52 | .pytest_cache/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | target/ 76 | 77 | # Jupyter Notebook 78 | .ipynb_checkpoints 79 | 80 | # IPython 81 | profile_default/ 82 | ipython_config.py 83 | 84 | # pyenv 85 | .python-version 86 | 87 | # pipenv 88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 91 | # install all needed dependencies. 92 | #Pipfile.lock 93 | 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 95 | __pypackages__/ 96 | 97 | # Celery stuff 98 | celerybeat-schedule 99 | celerybeat.pid 100 | 101 | # SageMath parsed files 102 | *.sage.py 103 | 104 | # Environments 105 | .env 106 | .venv 107 | env/ 108 | venv/ 109 | ENV/ 110 | env.bak/ 111 | venv.bak/ 112 | 113 | # Spyder project settings 114 | .spyderproject 115 | .spyproject 116 | 117 | # Rope project settings 118 | .ropeproject 119 | 120 | # mkdocs documentation 121 | /site 122 | 123 | # mypy 124 | .mypy_cache/ 125 | .dmypy.json 126 | dmypy.json 127 | 128 | # Pyre type checker 129 | .pyre/ 130 | -------------------------------------------------------------------------------- /ADC_function.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | 4 | import requests 5 | from configparser import ConfigParser 6 | import os 7 | import re 8 | import time 9 | import sys 10 | from lxml import etree 11 | import sys 12 | import io 13 | # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True) 14 | # sys.setdefaultencoding('utf-8') 15 | 16 | config_file='config.ini' 17 | config = ConfigParser() 18 | 19 | if os.path.exists(config_file): 20 | try: 21 | config.read(config_file, encoding='UTF-8') 22 | except: 23 | print('[-]Config.ini read failed! Please use the offical file!') 24 | else: 25 | print('[+]config.ini: not found, creating...',end='') 26 | with open("config.ini", "wt", encoding='UTF-8') as code: 27 | file_text = """[common] 28 | main_mode=1 29 | failed_output_folder=failed 30 | success_output_folder=JAV_output 31 | soft_link=0 32 | 33 | [proxy] 34 | proxy=192.168.2.2:1080 35 | timeout=10 36 | retry=3 37 | 38 | [Name_Rule] 39 | location_rule=actor+'/'+number 40 | naming_rule=number+'-'+title 41 | 42 | [update] 43 | update_check=1 44 | 45 | [media] 46 | media_warehouse=emby 47 | #emby or plex or kodi ,emby=jellyfin 48 | 49 | [escape] 50 | literals=\()/ 51 | folders=failed,JAV_output 52 | 53 | [debug_mode] 54 | switch=0 55 | 56 | """ 57 | print(file_text, file=code) 58 | time.sleep(2) 59 | print('.') 60 | print('[+]config.ini: created!') 61 | print('[+]Please restart the program!') 62 | time.sleep(4) 63 | os._exit(0) 64 | try: 65 | config.read(config_file, encoding='UTF-8') 66 | except: 67 | print('[-]Config.ini read failed! Please use the offical file!') 68 | 69 | def get_network_settings(): 70 | try: 71 | proxy = config["proxy"]["proxy"] 72 | timeout = int(config["proxy"]["timeout"]) 73 | retry_count = int(config["proxy"]["retry"]) 74 | assert timeout > 0 75 | assert retry_count > 0 76 | except: 77 | raise ValueError("[-]Proxy config error! Please check the config.") 78 | return proxy, timeout, retry_count 79 | 80 | 81 | def get_data_state(data: dict) -> bool: # 元数据获取失败检测 82 | if data["title"] is None or data["title"] == "" or data["title"] == "null": 83 | return False 84 | 85 | if data["number"] is None or data["number"] == "" or data["number"] == "null": 86 | return False 87 | 88 | return True 89 | 90 | def ReadMediaWarehouse(): 91 | return config['media']['media_warehouse'] 92 | 93 | def UpdateCheckSwitch(): 94 | check=str(config['update']['update_check']) 95 | if check == '1': 96 | return '1' 97 | elif check == '0': 98 | return '0' 99 | elif check == '': 100 | return '0' 101 | 102 | def getXpathSingle(htmlcode,xpath): 103 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 104 | result1 = str(html.xpath(xpath)).strip(" ['']") 105 | return result1 106 | 107 | def get_html(url,cookies = None):#网页请求核心 108 | proxy, timeout, retry_count = get_network_settings() 109 | i = 0 110 | while i < retry_count: 111 | try: 112 | if not proxy == '': 113 | #proxies = {"http": "http://" + proxy,"https": "https://" + proxy} 114 | proxies={"http": str(proxy), "https": str(proxy)} 115 | headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'} 116 | getweb = requests.get(str(url), headers=headers, timeout=timeout,proxies=proxies, cookies=cookies) 117 | getweb.encoding = 'utf-8' 118 | return getweb.text 119 | else: 120 | headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'} 121 | getweb = requests.get(str(url), headers=headers, timeout=timeout, cookies=cookies) 122 | getweb.encoding = 'utf-8' 123 | return getweb.text 124 | except: 125 | i += 1 126 | print('[-]Connect retry '+str(i)+'/'+str(retry_count)) 127 | print('[-]Connect Failed! Please check your Proxy or Network!') 128 | 129 | 130 | def post_html(url: str, query: dict) -> requests.Response: 131 | proxy, timeout, retry_count = get_network_settings() 132 | 133 | if proxy: 134 | #proxies = {"http": "http://" + proxy, "https": "https://" + proxy} 135 | proxies={"http": str(proxy), "https": str(proxy)} 136 | else: 137 | proxies = {} 138 | 139 | for i in range(retry_count): 140 | try: 141 | result = requests.post(url, data=query, proxies=proxies) 142 | return result 143 | except requests.exceptions.ProxyError: 144 | print("[-]Connect retry {}/{}".format(i+1, retry_count)) 145 | print("[-]Connect Failed! Please check your Proxy or Network!") 146 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /OOF_Rename.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | 4 | import glob 5 | import os 6 | import time 7 | import re 8 | import codecs 9 | from ADC_function import * 10 | from OOF_core import * 11 | import json 12 | import shutil 13 | from configparser import ConfigParser 14 | 15 | def delExistFile(path): #重命名已存在的文件，加上时间戳 16 | if os.path.exists(path): 17 | time_stamp = int(time.time()) #时间戳 18 | file_timestamp = time.strftime("%Y%m%d%H%M%S", time.localtime(time_stamp))#YYYYMMDDhh24miss 19 | filename=os.path.splitext(path)[0] #文件名 20 | filetype=os.path.splitext(path)[1] 21 | Newpath=os.path.join(filename+"_"+file_timestamp+filetype) 22 | try: 23 | os.rename(path,Newpath) 24 | print("[!]"+path+" 已存在! 已重命名为"+Newpath) 25 | except: 26 | print("[-]failed!can not rename file 'failed'\n[-](Please run as Administrator)") 27 | os._exit(0) 28 | 29 | 30 | def getNumber(filepath,absolute_path = False): #从路径中得到番号 31 | if absolute_path == True: 32 | filepath=filepath.replace('\\','/') 33 | file_number = str(re.findall(r'(.+?)\.', str(re.search('([^<>/\\\\|:""\\*\\?]+)\\.\\w+$', filepath).group()))).strip("['']").replace('_', '-') 34 | return file_number 35 | if '-' in filepath or '_' in filepath: # 普通提取番号 主要处理包含减号-和_的番号 36 | filepath = filepath.replace("_", "-") 37 | filepath.strip('22-sht.me').strip('-HD').strip('-hd') 38 | filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath)) # 去除文件名中时间 39 | if 'FC2' or 'fc2' in filename: 40 | filename = filename.replace('-PPV', '').replace('PPV-', '').replace('FC2PPV-', 'FC2-').replace('FC2PPV_', 'FC2-') 41 | filename = filename.replace('-ppv', '').replace('ppv-', '').replace('fc2ppv-', 'FC2-').replace('fc2ppv_', 'FC2-') 42 | file_number = re.search(r'\w+-\w+', filename, re.A).group() 43 | return file_number 44 | else: # 提取不含减号-的番号，FANZA CID 45 | try: 46 | return str(re.findall(r'(.+?)\.', str(re.search('([^<>/\\\\|:""\\*\\?]+)\\.\\w+$', filepath).group()))).strip("['']").replace('_', '-') 47 | except: 48 | return re.search(r'(.+?)\.', filepath)[0] 49 | 50 | 51 | if __name__ == '__main__': 52 | config_file = 'config.ini' 53 | config = ConfigParser() 54 | config.read(config_file, encoding='UTF-8') 55 | input_file = config['common']['input_file'] # 输入文件 56 | success_folder = config['common']['success_output_folder'] # 成功输出目录 57 | failed_file = config['common']['failed_output_file'] # 失败输出 58 | print('[*]================== 开始重命名，请联网 ===================') 59 | 60 | #备份旧文件和文件夹 61 | delExistFile(success_folder) 62 | delExistFile(failed_file) 63 | 64 | for l in open(input_file,'r', encoding='UTF-8'): #遍历txt文件，交给core 65 | link=l.split('|') 66 | filename=link[0] 67 | try: 68 | print("[!]Making Data for [" + filename + "], the number is [" + getNumber(filename) + "]") 69 | core_main(l, getNumber(filename)) 70 | print("[*]======================================================") 71 | except Exception as e: # 番号提取异常 72 | print('[-]' + filename + ' ERRPR :') 73 | print('[-]',e) 74 | try: 75 | print('[-]Move ' + filename + ' to failed file') 76 | #输出链接到失败文件 77 | open_failed= codecs.open(failed_file,'a+', encoding='utf-8') 78 | open_failed.write(l) 79 | open_failed.close() 80 | except Exception as e2: 81 | print('[!]', e2) 82 | continue 83 | 84 | print("[+]All finished!!!") 85 | input("[+][+]Press enter key exit, you can check the error messge before you exit.") 86 | -------------------------------------------------------------------------------- /OOF_core.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | import re 4 | import os 5 | import os.path 6 | import shutil 7 | from PIL import Image 8 | import time 9 | import json 10 | from ADC_function import * 11 | from configparser import ConfigParser 12 | import argparse 13 | import codecs 14 | # =========website======== 15 | import fc2fans_club 16 | import mgstage 17 | import avsox 18 | import javbus 19 | import javdb 20 | import fanza 21 | import jav321 22 | import requests 23 | import random 24 | 25 | 26 | # =====================本地文件处理=========================== 27 | 28 | def escapePath(path, Config): # Remove escape literals 29 | escapeLiterals = Config['escape']['literals'] 30 | backslash = '\\' 31 | for literal in escapeLiterals: 32 | path = path.replace(backslash + literal, '') 33 | return path 34 | 35 | def moveToFailedFile(full_link, failed_file): 36 | print('[-]Move to Failed file') 37 | open_failed= codecs.open(failed_file,'a+', encoding='utf-8') 38 | open_failed.write(full_link) 39 | open_failed.close() 40 | return 41 | ''' 42 | def moveFailedFolder(filepath, failed_folder): #移动文件到失败文件夹 43 | print('[-]Move to Failed output folder') 44 | shutil.move(filepath, str(os.getcwd()) + '/' + failed_folder + '/') 45 | return 46 | 47 | 48 | def CreatFailedFolder(failed_folder): 49 | if not os.path.exists(failed_folder + '/'): # 新建failed文件夹 50 | try: 51 | os.makedirs(failed_folder + '/') 52 | except: 53 | print("[-]failed!can not be make Failed output folder\n[-](Please run as Administrator)") 54 | return 55 | ''' 56 | def getDataFromJSON(file_number, filepath, failed_folder): # 从JSON返回元数据 57 | """ 58 | iterate through all services and fetch the data 59 | """ 60 | 61 | func_mapping = { 62 | "avsox": avsox.main, 63 | "fc2": fc2fans_club.main, 64 | "fanza": fanza.main, 65 | "javdb": javdb.main, 66 | "javbus": javbus.main, 67 | "mgstage": mgstage.main, 68 | "jav321": jav321.main, 69 | } 70 | 71 | # default fetch order list, from the begining to the end 72 | sources = ["javbus", "javdb", "fanza", "mgstage", "fc2", "avsox", "jav321"] 73 | 74 | # if the input file name matches centain rules, 75 | # move some web service to the begining of the list 76 | if re.match(r"^\d{5,}", file_number) or ( 77 | "HEYZO" in file_number or "heyzo" in file_number or "Heyzo" in file_number 78 | ): 79 | sources.insert(0, sources.pop(sources.index("avsox"))) 80 | elif re.match(r"\d+\D+", file_number) or ( 81 | "siro" in file_number or "SIRO" in file_number or "Siro" in file_number 82 | ): 83 | sources.insert(0, sources.pop(sources.index("fanza"))) 84 | elif "fc2" in file_number or "FC2" in file_number: 85 | sources.insert(0, sources.pop(sources.index("fc2"))) 86 | 87 | for source in sources: 88 | json_data = json.loads(func_mapping[source](file_number)) 89 | # if any service return a valid return, break 90 | if get_data_state(json_data): 91 | break 92 | 93 | # ================================================网站规则添加结束================================================ 94 | 95 | title = json_data['title'] 96 | actor_list = str(json_data['actor']).strip("[ ]").replace("'", '').split(',') # 字符串转列表 97 | release = json_data['release'] 98 | number = json_data['number'] 99 | studio = json_data['studio'] 100 | source = json_data['source'] 101 | runtime = json_data['runtime'] 102 | outline = json_data['outline'] 103 | label = json_data['label'] 104 | year = json_data['year'] 105 | try: 106 | cover_small = json_data['cover_small'] 107 | except: 108 | cover_small = '' 109 | imagecut = json_data['imagecut'] 110 | tag = str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(',') # 字符串转列表 @ 111 | actor = str(actor_list).strip("[ ]").replace("'", '').replace(" ", '') 112 | 113 | 114 | if title == '' or number == '': 115 | print('[-]Movie Data not found!') 116 | ''' 117 | moveFailedFolder(filepath, failed_folder) 118 | ''' 119 | moveToFailedFile(filepath, failed_folder) 120 | return 121 | 122 | # if imagecut == '3': 123 | # DownloadFileWithFilename() 124 | 125 | # ====================处理异常字符====================== #\/:*?"<>| 126 | title = title.replace('\\', '') 127 | title = title.replace('/', '') 128 | title = title.replace(':', '') 129 | title = title.replace('*', '') 130 | title = title.replace('?', '') 131 | title = title.replace('"', '') 132 | title = title.replace('<', '') 133 | title = title.replace('>', '') 134 | title = title.replace('|', '') 135 | title = title.replace('&', '') 136 | release = release.replace('/', '-') 137 | tmpArr = cover_small.split(',') 138 | if len(tmpArr) > 0: 139 | cover_small = tmpArr[0].strip('\"').strip('\'') 140 | # ====================处理异常字符 END================== #\/:*?"<>| 141 | 142 | naming_rule = eval(config['Name_Rule']['naming_rule']) 143 | location_rule = eval(config['Name_Rule']['location_rule']) 144 | if 'actor' in config['Name_Rule']['location_rule'] and len(actor) > 100: 145 | print(config['Name_Rule']['location_rule']) 146 | location_rule = eval(config['Name_Rule']['location_rule'].replace("actor","'多人作品'")) 147 | if 'title' in config['Name_Rule']['location_rule'] and len(title) > 100: 148 | location_rule = eval(config['Name_Rule']['location_rule'].replace("title",'number')) 149 | 150 | # 返回处理后的json_data 151 | json_data['title'] = title 152 | json_data['actor'] = actor 153 | json_data['release'] = release 154 | json_data['cover_small'] = cover_small 155 | json_data['tag'] = tag 156 | json_data['naming_rule'] = naming_rule 157 | json_data['location_rule'] = location_rule 158 | json_data['year'] = year 159 | json_data['actor_list'] = actor_list 160 | return json_data 161 | 162 | 163 | def get_info(json_data): # 返回json里的数据 164 | title = json_data['title'] 165 | studio = json_data['studio'] 166 | year = json_data['year'] 167 | outline = json_data['outline'] 168 | runtime = json_data['runtime'] 169 | director = json_data['director'] 170 | actor_photo = json_data['actor_photo'] 171 | release = json_data['release'] 172 | number = json_data['number'] 173 | cover = json_data['cover'] 174 | website = json_data['website'] 175 | return title, studio, year, outline, runtime, director, actor_photo, release, number, cover, website 176 | 177 | 178 | def smallCoverCheck(path, number, imagecut, cover_small, c_word, Config, filepath, failed_folder): 179 | if imagecut == 3: 180 | DownloadFileWithFilename(cover_small, path + '/' + number + c_word + '-poster.jpg', path, Config, filepath, failed_folder) 181 | print('[+]Image Downloaded! '+ path + '/' + number + c_word + '-poster.jpg') 182 | 183 | 184 | def creatFolder(success_folder, location_rule, json_data, Config): # 创建文件夹 185 | title, studio, year, outline, runtime, director, actor_photo, release, number, cover, website= get_info(json_data) 186 | if len(location_rule) > 240: # 新建成功输出文件夹 187 | path = success_folder + '/' + location_rule.replace("'actor'", "'manypeople'", 3).replace("actor","'manypeople'",3) # path为影片+元数据所在目录 188 | else: 189 | path = success_folder + '/' + location_rule 190 | if not os.path.exists(path): 191 | path = escapePath(path, Config) 192 | try: 193 | os.makedirs(path) 194 | except: 195 | path = success_folder + '/' + location_rule.replace('/[' + number + ']-' + title, "/number") 196 | path = escapePath(path, Config) 197 | 198 | os.makedirs(path) 199 | return path 200 | 201 | 202 | # =====================资源下载部分=========================== 203 | def DownloadFileWithFilename(url, filename, path, Config, filepath, failed_folder): # path = examle:photo , video.in the Project Folder! 204 | proxy, timeout, retry_count = get_network_settings() 205 | i = 0 206 | 207 | while i < retry_count: 208 | try: 209 | if not proxy == '': 210 | if not os.path.exists(path): 211 | os.makedirs(path) 212 | headers = { 213 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'} 214 | r = requests.get(url, headers=headers, timeout=timeout, 215 | #proxies={"http": "http://" + str(proxy), "https": "https://" + str(proxy)}) 216 | proxies={"http": str(proxy), "https": str(proxy)}) 217 | if r == '': 218 | print('[-]Movie Data not found!') 219 | return 220 | with open(str(path) + "/" + filename, "wb") as code: 221 | code.write(r.content) 222 | return 223 | else: 224 | if not os.path.exists(path): 225 | os.makedirs(path) 226 | headers = { 227 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'} 228 | r = requests.get(url, timeout=timeout, headers=headers) 229 | if r == '': 230 | print('[-]Movie Data not found!') 231 | return 232 | with open(str(path) + "/" + filename, "wb") as code: 233 | code.write(r.content) 234 | return 235 | except requests.exceptions.RequestException: 236 | i += 1 237 | print('[-]Image Download : Connect retry ' + str(i) + '/' + str(retry_count)) 238 | except requests.exceptions.ConnectionError: 239 | i += 1 240 | print('[-]Image Download : Connect retry ' + str(i) + '/' + str(retry_count)) 241 | except requests.exceptions.ProxyError: 242 | i += 1 243 | print('[-]Image Download : Connect retry ' + str(i) + '/' + str(retry_count)) 244 | except requests.exceptions.ConnectTimeout: 245 | i += 1 246 | print('[-]Image Download : Connect retry ' + str(i) + '/' + str(retry_count)) 247 | print('[-]Connect Failed! Please check your Proxy or Network!') 248 | ''' 249 | moveFailedFolder(filepath, failed_folder) 250 | ''' 251 | moveToFailedFile(filepath, failed_folder) 252 | return 253 | 254 | 255 | def imageDownload(cover, number, c_word, path, multi_part, Config, filepath, failed_folder): # 封面是否下载成功，否则移动到failed 256 | if DownloadFileWithFilename(cover, number + c_word + '-fanart.jpg', path, Config, filepath,failed_folder) == 'failed': 257 | ''' 258 | moveFailedFolder(filepath, failed_folder) 259 | ''' 260 | moveToFailedFile(filepath, failed_folder) 261 | return 262 | i = 1 263 | while i <= int(config['proxy']['retry']): 264 | if os.path.getsize(path + '/' + number + c_word + '-fanart.jpg') == 0: 265 | print('[!]Image Download Failed! Trying again. [' + config['proxy']['retry'] + '/3]') 266 | DownloadFileWithFilename(cover, number + c_word + '-fanart.jpg', path, Config, filepath, failed_folder) 267 | i = i + 1 268 | continue 269 | else: 270 | break 271 | if os.path.getsize(path + '/' + number + c_word + '-fanart.jpg') == 0: 272 | return 273 | print('[+]Image Downloaded!', path + '/' + number + c_word + '-fanart.jpg') 274 | shutil.copyfile(path + '/' + number + c_word + '-fanart.jpg',path + '/' + number + c_word + '-thumb.jpg') 275 | 276 | 277 | def PrintFiles(path, c_word, naming_rule, part, cn_sub, json_data, filepath, failed_folder, tag, actor_list, liuchu): 278 | title, studio, year, outline, runtime, director, actor_photo, release, number, cover, website = get_info(json_data) 279 | try: 280 | if not os.path.exists(path): 281 | os.makedirs(path) 282 | with open(path + "/" + number + c_word + ".nfo", "wt", encoding='UTF-8') as code: 283 | print('', file=code) 284 | print("", file=code) 285 | print(" " + naming_rule + part + "", file=code) 286 | print(" ", file=code) 287 | print(" ", file=code) 288 | print(" " + studio + "+", file=code) 289 | print(" " + year + "", file=code) 290 | print(" " + outline + "", file=code) 291 | print(" " + outline + "", file=code) 292 | print(" " + str(runtime).replace(" ", "") + "", file=code) 293 | print(" " + director + "", file=code) 294 | print(" " + number + c_word + "-poster.jpg", file=code) 295 | print(" " + number + c_word + "-thumb.jpg", file=code) 296 | print(" " + number + c_word + '-fanart.jpg' + "", file=code) 297 | try: 298 | for key in actor_list: 299 | print(" ", file=code) 300 | print(" " + key + "", file=code) 301 | print(" ", file=code) 302 | except: 303 | aaaa = '' 304 | print(" " + studio + "", file=code) 305 | print(" ", file=code) 307 | if cn_sub == '1': 308 | print(" 中文字幕", file=code) 309 | if liuchu == '流出': 310 | print(" 流出", file=code) 311 | try: 312 | for i in tag: 313 | print(" " + i + "", file=code) 314 | except: 315 | aaaaa = '' 316 | try: 317 | for i in tag: 318 | print(" " + i + "", file=code) 319 | except: 320 | aaaaaaaa = '' 321 | if cn_sub == '1': 322 | print(" 中文字幕", file=code) 323 | print(" " + number + "", file=code) 324 | print(" " + release + "", file=code) 325 | print(" " + cover + "", file=code) 326 | print(" " + website + "", file=code) 327 | print("", file=code) 328 | print("[+]Writeed! " + path + "/" + number + c_word + ".nfo") 329 | except IOError as e: 330 | print("[-]Write Failed!") 331 | print(e) 332 | ''' 333 | moveFailedFolder(filepath, failed_folder) 334 | ''' 335 | moveToFailedFile(filepath, failed_folder) 336 | return 337 | except Exception as e1: 338 | print(e1) 339 | print("[-]Write Failed!") 340 | ''' 341 | moveFailedFolder(filepath, failed_folder) 342 | ''' 343 | moveToFailedFile(filepath, failed_folder) 344 | return 345 | 346 | 347 | def cutImage(imagecut, path, number, c_word): 348 | if imagecut == 1: 349 | try: 350 | img = Image.open(path + '/' + number + c_word + '-fanart.jpg') 351 | imgSize = img.size 352 | w = img.width 353 | h = img.height 354 | img2 = img.crop((w / 1.9, 0, w, h)) 355 | img2.save(path + '/' + number + c_word + '-poster.jpg') 356 | print('[+]Image Cutted! ' + path + '/' + number + c_word + '-poster.jpg') 357 | except: 358 | print('[-]Cover cut failed!') 359 | elif imagecut == 0: 360 | shutil.copyfile(path + '/' + number + c_word + '-fanart.jpg',path + '/' + number + c_word + '-poster.jpg') 361 | print('[+]Image Copyed! ' + path + '/' + number + c_word + '-poster.jpg') 362 | 363 | 364 | def pasteFileToFolder(filepath, path, number, c_word): # 文件路径，番号，后缀，要移动至的位置 365 | houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|WEBM|avi|rmvb|wmv|mov|mp4|mkv|flv|ts|webm)$', filepath).group()) 366 | try: 367 | if config['common']['soft_link'] == '1': # 如果soft_link=1 使用软链接 368 | os.symlink(filepath, path + '/' + number + c_word + houzhui) 369 | else: 370 | os.rename(filepath, path + '/' + number + c_word + houzhui) 371 | if os.path.exists(os.getcwd() + '/' + number + c_word + '.srt'): # 字幕移动 372 | os.rename(os.getcwd() + '/' + number + c_word + '.srt', path + '/' + number + c_word + '.srt') 373 | print('[+]Sub moved!') 374 | elif os.path.exists(os.getcwd() + '/' + number + c_word + '.ssa'): 375 | os.rename(os.getcwd() + '/' + number + c_word + '.ssa', path + '/' + number + c_word + '.ssa') 376 | print('[+]Sub moved!') 377 | elif os.path.exists(os.getcwd() + '/' + number + c_word + '.sub'): 378 | os.rename(os.getcwd() + '/' + number + c_word + '.sub', path + '/' + number + c_word + '.sub') 379 | print('[+]Sub moved!') 380 | except FileExistsError: 381 | print('[-]File Exists! Please check your movie!') 382 | print('[-]move to the root folder of the program.') 383 | return 384 | except PermissionError: 385 | print('[-]Error! Please run as administrator!') 386 | return 387 | 388 | ''' 389 | def pasteFileToFolder_mode2(filepath, path, multi_part, number, part, c_word): # 文件路径，番号，后缀，要移动至的位置 390 | if multi_part == 1: 391 | number += part # 这时number会被附加上CD1后缀 392 | houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|WEBM|avi|rmvb|wmv|mov|mp4|mkv|flv|ts|webm)$', filepath).group()) 393 | try: 394 | if config['common']['soft_link'] == '1': 395 | os.symlink(filepath, path + '/' + number + part + c_word + houzhui) 396 | else: 397 | os.rename(filepath, path + '/' + number + part + c_word + houzhui) 398 | if os.path.exists(number + '.srt'): # 字幕移动 399 | os.rename(number + part + c_word + '.srt', path + '/' + number + part + c_word + '.srt') 400 | print('[+]Sub moved!') 401 | elif os.path.exists(number + part + c_word + '.ass'): 402 | os.rename(number + part + c_word + '.ass', path + '/' + number + part + c_word + '.ass') 403 | print('[+]Sub moved!') 404 | elif os.path.exists(number + part + c_word + '.sub'): 405 | os.rename(number + part + c_word + '.sub', path + '/' + number + part + c_word + '.sub') 406 | print('[+]Sub moved!') 407 | print('[!]Success') 408 | except FileExistsError: 409 | print('[-]File Exists! Please check your movie!') 410 | print('[-]move to the root folder of the program.') 411 | return 412 | except PermissionError: 413 | print('[-]Error! Please run as administrator!') 414 | return 415 | ''' 416 | def get_part(filepath, failed_folder): 417 | try: 418 | if re.search('-CD\d+', filepath): 419 | return re.findall('-CD\d+', filepath)[0] 420 | if re.search('-cd\d+', filepath): 421 | return re.findall('-cd\d+', filepath)[0] 422 | except: 423 | print("[-]failed!Please rename the filename again!") 424 | ''' 425 | moveFailedFolder(filepath, failed_folder) 426 | ''' 427 | moveToFailedFile(full_link, failed_file) 428 | return 429 | 430 | def debug_mode(json_data): 431 | try: 432 | if config['debug_mode']['switch'] == '1': 433 | print('[+] ---Debug info---') 434 | for i, v in json_data.items(): 435 | if i == 'outline': 436 | print('[+] -', i, ' :', len(v), 'characters') 437 | continue 438 | if i == 'actor_photo' or i == 'year': 439 | continue 440 | print('[+] -', "%-11s" % i, ':', v) 441 | print('[+] ---Debug info---') 442 | except: 443 | aaa = '' 444 | 445 | 446 | def getNewFileName(json_data, Config, number, part, c_word, liuchu): #目的是把后缀添加到番号后 447 | title = json_data['title'] 448 | actor = json_data['actor'] 449 | studio = json_data['studio'] 450 | director = json_data['director'] 451 | release = json_data['release'] 452 | year = json_data['year'] 453 | number = number+part+c_word+liuchu 454 | cover = json_data['cover'] 455 | tag = json_data['tag'] 456 | outline = json_data['outline'] 457 | runtime = json_data['runtime'] 458 | return eval(Config['Name_Rule']['naming_rule']) 459 | 460 | def moveToTxt(new_name, full_link, folder, success_file): 461 | link = full_link.split('|') 462 | filename = link[0] # 原名 463 | filesize = link[1] 464 | fileid = link[2] 465 | preid = link[3].strip() #去除了换行符\n 466 | houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|WEBM|avi|rmvb|wmv|mov|mp4|mkv|flv|ts|webm)$', filename).group()) 467 | try: 468 | #path = folder + '/' + success_file 469 | #open_file = codecs.open((folder + '/' + success_file),'a+', encoding='utf-8') 470 | if not os.path.exists(folder): 471 | os.mkdir(folder) 472 | open_file = codecs.open((folder + '/' + success_file),'a+', encoding='utf-8') 473 | open_file.write(new_name + houzhui +'|'+ filesize +'|'+ fileid +'|'+ preid +'\n') 474 | open_file.close() 475 | print( "[+] " + filename + " 保存到 " + folder + '/' +success_file) 476 | except PermissionError: 477 | print('[-]Error! Please run as administrator!') 478 | return 479 | 480 | 481 | def core_main(full_link, number_th): 482 | # =======================================================================初始化所需变量 483 | multi_part = 0 #是否是CD1 CD2 484 | part = '' 485 | c_word = '' # 中文字幕影片后缀 486 | cn_sub = '' 487 | liuchu = '' 488 | config_file = 'config.ini' 489 | Config = ConfigParser() 490 | Config.read(config_file, encoding='UTF-8') 491 | program_mode = Config['common']['main_mode'] # 运行模式 492 | file_mode = re.findall(r'\d', program_mode) 493 | ''' 494 | #函数中这两个参数，只是给了传给moveFailedFolder，所以filepath和full_link可替代 495 | failed_folder = Config['common']['failed_output_folder'] # 失败输出目录 496 | filepath = full_link # 影片的路径filepath 497 | ''' 498 | success_folder = Config['common']['success_output_folder'] # 成功输出目录 499 | success_file = "RenameSu.txt" # 成功输出 500 | failed_file = Config['common']['failed_output_file'] # 失败输出 501 | number = number_th 502 | #分割链接 503 | link = full_link.split('|') 504 | filename = link[0] # 原名 505 | 506 | json_data = getDataFromJSON(number, full_link, failed_file) # 爬虫获取元数据, 失败时传给 moveToFailedFile(full_link, failed_file) 507 | if json_data["number"] != number: 508 | # fix issue #119 509 | # the root cause is we normalize the search id 510 | # PrintFiles() will use the normalized id from website, 511 | # but pasteFileToFolder() still use the input raw search id 512 | # so the solution is: use the normalized search id 513 | number = json_data["number"] 514 | imagecut = json_data['imagecut'] 515 | tag = json_data['tag'] 516 | # =======================================================================判断-C,-CD后缀 517 | if '-CD' in filename or '-cd' in filename: 518 | multi_part = 1 519 | ''' 520 | part = get_part(filename, failed_folder) 521 | ''' 522 | part = get_part(filename, failed_file) 523 | if '-c.' in filename or '-C.' in filename or '中文' in filename or '字幕' in filename: 524 | cn_sub = '1' 525 | c_word = '-C' # 中文字幕影片后缀 526 | if '流出' in filename: 527 | liuchu = '流出' 528 | ''' 529 | CreatFailedFolder(failed_folder) # 创建输出失败目录 530 | ''' 531 | debug_mode(json_data) # 调试模式检测 532 | 533 | new_name = getNewFileName(json_data, Config, number, part, c_word, liuchu) #文件全名，在番号后加了后缀，！不带扩展名！ 534 | if file_mode[0] == '1': #全部输出到成功目录 535 | path = success_folder 536 | if file_mode[1] == '1': #只存链接文件 537 | moveToTxt(new_name, full_link, path, success_file) 538 | elif file_mode[1] == '2': #存链接文件和封面图 539 | moveToTxt(new_name, full_link, path, success_file) 540 | imageDownload(json_data['cover'], number, c_word, path, multi_part, Config, full_link, failed_file) 541 | elif file_mode[1] == '3': #存所有文件 542 | moveToTxt(new_name, full_link, path, success_file) 543 | smallCoverCheck(path, number, imagecut, json_data['cover_small'], c_word, Config, full_link, failed_file) # 检查小封面 544 | imageDownload(json_data['cover'], number, c_word, path, multi_part, Config, full_link, failed_file) 545 | cutImage(imagecut, path, number, c_word) # 裁剪图 546 | PrintFiles(path, c_word, json_data['naming_rule'], part, cn_sub, json_data, full_link, failed_file, tag, json_data['actor_list'],liuchu) # 打印nfo文件 547 | elif file_mode[0] == '2': #按location_rule分类输出到文件夹 548 | path = creatFolder(success_folder, json_data['location_rule'], json_data, Config) # 输出的文件夹 549 | if file_mode[1] == '1': 550 | moveToTxt(new_name, full_link, path, success_file) 551 | elif file_mode[1] == '2': 552 | moveToTxt(new_name, full_link, path, success_file) 553 | imageDownload(json_data['cover'], number, c_word, path, multi_part, Config, full_link, failed_file) 554 | elif file_mode[1] == '3': 555 | moveToTxt(new_name, full_link, path, success_file) 556 | smallCoverCheck(path, number, imagecut, json_data['cover_small'], c_word, Config, full_link, failed_file) # 检查小封面 557 | imageDownload(json_data['cover'], number, c_word, path, multi_part, Config, full_link, failed_file) 558 | cutImage(imagecut, path, number, c_word) # 裁剪图 559 | PrintFiles(path, c_word, json_data['naming_rule'], part, cn_sub, json_data, full_link, failed_file, tag, json_data['actor_list'],liuchu) # 打印nfo文件 560 | 561 | ''' 562 | full_link, failed_file 替换 filepath, failed_folder 563 | 原始代码 564 | # =======================================================================刮削模式 565 | if program_mode == '1': 566 | if multi_part == 1: 567 | number += part # 这时number会被附加上CD1后缀 568 | smallCoverCheck(path, number, imagecut, json_data['cover_small'], c_word, Config, filepath, failed_folder) # 检查小封面 569 | imageDownload(json_data['cover'], number, c_word, path, multi_part, Config, filepath, failed_folder) # creatFoder会返回番号路径 570 | cutImage(imagecut, path, number, c_word) # 裁剪图 571 | PrintFiles(path, c_word, json_data['naming_rule'], part, cn_sub, json_data, filepath, failed_folder, tag, json_data['actor_list'],liuchu) # 打印文件 572 | pasteFileToFolder(filepath, path, number, c_word) # 移动文件 573 | # =======================================================================整理模式 574 | elif program_mode == '2': 575 | pasteFileToFolder_mode2(filepath, path, multi_part, number, part, c_word) # 移动文件 576 | ''' -------------------------------------------------------------------------------- /ReadMe.md: -------------------------------------------------------------------------------- 1 | # 115_Code_Rename 2 | 修改自项目 AV Data Capture (CLI) 3 | 4 | 工具的初衷是：为Fake115Upload生成的**日本电影115转存码批量自动重命名。** 5 | 6 | 处理115转存码，识别番号，按规则重命名。重命名后的码转存到网盘后，文件名是完整的，**间接为网盘文件重命名**。 7 | 也可以对转存码**分类、抓取影片封面图、元数据**。 8 | 9 | # 下载 10 | 11 | [Windows版](https://github.com/LSD08KM/115_Code_Rename/releases) 12 | 13 | 其他系统请clone源码包运行，并手动安装Python3环境 14 | 15 | # 如何使用 16 | 17 | ## 注意事项，必读！ 18 | 19 | 工具要处理的文本文档如下图所示： 20 | 21 | ![输入文档](./readme/1.png) 22 | 23 | 文件内每行一条转存码，转存码的开头是文件名。 24 | 25 | 旧文件名必须满足 AV Data Capture (CLI) 的条件：文件名中间要有下划线或者减号"_","-"，没有多余的内容只有番号为最佳。 26 | 27 | 默认将重命名失败的码保存在`115failed.txt` ， 28 | 成功的码保存在AV_output文件夹内的`RenameSu.txt`。 29 | 30 | 重命名后的文档如下： 31 | 32 | ![输出文档](./readme/2.png) 33 | 34 | ## 简要教程: 35 | 36 | 1. 把软件和写有115转存码的文本文档放到同一目录 37 | 2. 修改config.ini参数，把input_file=后的文件名改成要处理的文件 38 | 3. 设置 config.ini 文件的代理（路由器拥有自动代理功能的可以把 proxy= 后面内容去掉） 39 | 4. 运行软件等待完成 40 | 41 | **详细请看以下完整文档** 42 | 43 | # 完整使用文档 44 | 45 | ## 模块安装 46 | 如果运行**源码**版，运行前请安装**Python环境**和安装以下**模块** 47 | 48 | 在终端 cmd/Powershell/Terminal 中输入以下代码来安装模块 49 | 50 | ```python 51 | pip install requests pyquery lxml Beautifulsoup4 pillow 52 | ``` 53 | 54 | ## 配置文件config.ini 55 | ### 配置文件的参数 56 | ``` 57 | [common] 58 | 运行模式： 59 | main_mode=21 60 | 输入文档(要处理的文档)： 61 | input_file=115s.txt 62 | 保存重命名失败的转存码的文档： 63 | failed_output_file=115failed.txt 64 | 保存重命名成功的转存码的文件夹 65 | success_output_folder=AV_output 66 | 没用，不要修改： 67 | soft_link=0 68 | 69 | 网络设置： 70 | [proxy] 71 | 代理设置： 72 | proxy=socks5://127.0.0.1:10808 73 | 连接超时重试： 74 | timeout=5 75 | 连接重试次数： 76 | retry=2 77 | 78 | 重命名规则： 79 | [Name_Rule] 80 | 自定义目录： 81 | location_rule= year+'/'+studio 82 | 命名规则： 83 | naming_rule=number+' '+actor+' '+title 84 | 85 | 没用，不要修改： 86 | [update] 87 | update_check=0 88 | 89 | 没用，不要修改： 90 | [escape] 91 | literals=\()/ 92 | folders=AV_output 93 | 94 | 调试模式： 95 | [debug_mode] 96 | switch=0 97 | ``` 98 | 99 | ### 运行模式 100 | 101 | ``` 102 | [common] 103 | main_mode=11 104 | ``` 105 | 11 转存码存到输出目录下的单一文档 106 | 12 转存码存到输出目录下的单一文档，并下载封面图 107 | 13 转存码存到输出目录下的单一文档，并下载全部图片及元数据文件 108 | 21 转存码按目录结构规则分类 109 | 22 转存码按目录结构规则分类，并下载封面图 110 | 23 转存码按目录结构规则分类，并下载全部图片及元数据文件 111 | 112 | --- 113 | ### 设置输入文档、失败输出文档和成功输出目录 114 | 115 | ``` 116 | input_file=115s.txt 117 | failed_output_file=115failed.txt 118 | success_output_folder=AV_output 119 | ``` 120 | --- 121 | ### 网络设置 122 | ``` 123 | [proxy] 124 | proxy=127.0.0.1:1081 125 | timeout=10 126 | retry=3 127 | ``` 128 | #### 针对某些地区的代理设置 129 | ``` 130 | proxy=127.0.0.1:1081 131 | ``` 132 | 133 | 打开```config.ini```,在```[proxy]```下的```proxy```行设置本地代理地址和端口，支持Shadowxxxx/X,V2XXX本地代理端口 134 | 素人系列抓取建议使用日本代理 135 | **路由器拥有自动代理功能的可以把proxy=后面内容去掉** 136 | **本地代理软件开全局模式的用户同上** 137 | **如果遇到tineout错误，可以把文件的proxy=后面的地址和端口删除，并开启代理软件全局模式，或者重启电脑，代理软件，网卡** 138 | 139 | --- 140 | #### 连接超时重试设置 141 | ``` 142 | timeout=10 143 | ``` 144 | 10为超时重试时间 单位：秒 145 | 146 | --- 147 | #### 连接重试次数设置 148 | ``` 149 | retry=3 150 | ``` 151 | 3即为重试次数 152 | 153 | --- 154 | ### 设置目录结构规则和影片重命名规则 155 | 156 | 默认配置： 157 | 158 | ``` 159 | [Name_Rule] 160 | location_rule= year+'/'+studio 161 | naming_rule=number+' '+actor+' '+title 162 | ``` 163 | #### 命名参数 164 | ``` 165 | title = 片名 166 | actor = 演员 167 | studio = 公司 168 | director = 导演 169 | release = 发售日 170 | year = 发行年份 171 | number = 番号 172 | cover = 封面链接 173 | tag = 类型 174 | outline = 简介 175 | runtime = 时长 176 | ``` 177 | 178 | 上面的参数以下都称之为**变量** 179 | 180 | #### 例子： 181 | 自定义规则方法：有两种元素，变量和字符，无论是任何一种元素之间连接必须要用加号 **+** ，比如：```'naming_rule=['+number+']-'+title```，其中冒号 ' ' 内的文字是字符，没有冒号包含的文字是变量，元素之间连接必须要用加号 **+** 182 | 183 | **目录结构规则：**通过文件夹结构实现分类。默认 ```location_rule= year+'/'+studio ```。 184 | **不推荐修改时在这里添加 title**，有时 title 过长，因为 Windows API 问题，抓取数据时新建文件夹容易出错。 185 | 186 | **影片命名规则：**默认 ```naming_rule=number+'-'+title``` 187 | 188 | --- 189 | ### 调试模式 190 | ``` 191 | [debug_mode] 192 | switch=1 193 | ``` 194 | 195 | 如要开启调试模式，请手动输入以上代码到```config.ini```中，开启后可在抓取中显示影片元数据 196 | 197 | --- 198 | 199 | ## 多集影片处理 200 | 201 | 可以把多集电影按照集数后缀命名为类似`ssni-xxx-cd1.mp4m,ssni-xxx-cd2.mp4，abp-xxx-CD1.mp4`的规则，只要含有`-CDn./-cdn.`类似命名规则，即可使用分集功能 202 | 203 | ## 中文字幕处理 204 | 205 | 当文件名包含: 中文，字幕，-c., -C., 会在番号后添加-C后缀。 206 | 207 | 处理元数据时会加上**中文字幕**标签。 208 | 209 | ## 旧文件处理 210 | 211 | 当该目录存在以前的输出文档或文件夹，例如`115failed.txt`或`AV_output`文件夹。会将旧文件重命名，例如`AV_output_20200411170755`，以防文件混乱。 212 | 213 | -------------------------------------------------------------------------------- /actor.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | 4 | 5 | import requests, os 6 | from configparser import RawConfigParser 7 | from base64 import b64encode 8 | from traceback import format_exc 9 | from json import loads 10 | from os.path import exists 11 | 12 | # 检查“actor_photos”文件夹是否就绪 13 | if not exists('actor_photos'): 14 | print('\n“actor_photos” folder lost！Please put it to the same location with program\n') 15 | os.system('pause') 16 | # 读取配置文件，这个ini文件用来给用户设置emby网址和api id 17 | print('Reading ini Setting...') 18 | config_settings = RawConfigParser() 19 | try: 20 | config_settings.read('ap_config.ini', encoding='utf-8-sig') 21 | url_emby = config_settings.get("emby/jellyfin", "website") 22 | api_key = config_settings.get("emby/jellyfin", "api id") 23 | bool_replace = True if config_settings.get("emby/jellyfin", "是否覆盖以前上传的头像？") == '是' else False 24 | except: 25 | print(format_exc()) 26 | print('Cannot read ini files!') 27 | os.system('pause') 28 | print('Read Success!\n') 29 | # 修正用户输入的emby网址，无论是不是带“/” 30 | if not url_emby.endswith('/'): 31 | url_emby += '/' 32 | # 成功的个数 33 | num_suc = 0 34 | num_fail = 0 35 | num_exist = 0 36 | sep = os.sep 37 | try: 38 | print('Getting emby/jellyfin Person`s form...') 39 | # curl -X GET "http://localhost:8096/emby/Persons?api_key=3291434710e342089565ad05b6b2f499" -H "accept: application/json" 40 | # 得到所有“人员” emby api没有细分“演员”还是“导演”“编剧”等等 下面得到的是所有“有关人员” 41 | url_emby_persons = url_emby + 'emby/Persons?api_key=' + api_key # &PersonTypes=Actor 42 | try: 43 | rqs_emby = requests.get(url=url_emby_persons) 44 | except requests.exceptions.ConnectionError: 45 | print('Cannot connect to emby/jellyfin server ,Please check：', url_emby, '\n') 46 | os.system('pause') 47 | except: 48 | print(format_exc()) 49 | print('Unkown Error ,Please submit screenshot to issues', url_emby, '\n') 50 | os.system('pause') 51 | # 401，无权访问 52 | if rqs_emby.status_code == 401: 53 | print('Please check API KEY！\n') 54 | os.system('pause') 55 | # print(rqs_emby.text) 56 | try: 57 | list_persons = loads(rqs_emby.text)['Items'] 58 | except: 59 | print(rqs_emby.text) 60 | print('Error! emby response：') 61 | print('Please submit screenshot to issues！') 62 | os.system('pause') 63 | num_persons = len(list_persons) 64 | print('There are currently' + str(num_persons) + ' People！\n') 65 | # os.system('pause') 66 | # 用户emby中的persons，在“actor_photos”文件夹中，已有头像的，记录下来 67 | f_txt = open("included.txt", 'w', encoding="utf-8") 68 | f_txt.close() 69 | f_txt = open("no_included.txt", 'w', encoding="utf-8") 70 | f_txt.close() 71 | for dic_each_actor in list_persons: 72 | actor_name = dic_each_actor['Name'] 73 | # 头像jpg/png在“actor_photos”中的路径 74 | actor_pic_path = 'actor_photos' + sep + actor_name[0] + sep + actor_name 75 | if exists(actor_pic_path + '.jpg'): 76 | actor_pic_path = actor_pic_path + '.jpg' 77 | header = {"Content-Type": 'image/jpeg', } 78 | elif exists(actor_pic_path + '.png'): 79 | actor_pic_path = actor_pic_path + '.png' 80 | header = {"Content-Type": 'image/png', } 81 | else: 82 | print('>>No image：', actor_name) 83 | f_txt = open("no_included.txt", 'a', encoding="utf-8") 84 | f_txt.write(actor_name + '\n') 85 | f_txt.close() 86 | num_fail += 1 87 | continue 88 | # emby有某个演员，“actor_photos”文件夹也有这个演员的头像，记录一下 89 | f_txt = open("included.txt", 'a', encoding="utf-8") 90 | f_txt.write(actor_name + '\n') 91 | f_txt.close() 92 | # emby有某个演员，已经有他的头像，不再进行下面“上传头像”的操作 93 | if dic_each_actor['ImageTags']: # emby已经收录头像 94 | num_exist += 1 95 | if not bool_replace: # 不需要覆盖已有头像 96 | continue # 那么不进行下面的上传操作 97 | f_pic = open(actor_pic_path, 'rb') # 二进制方式打开图文件 98 | b6_pic = b64encode(f_pic.read()) # 读取文件内容，转换为base64编码 99 | f_pic.close() 100 | url_post_img = url_emby + 'emby/Items/' + dic_each_actor['Id'] + '/Images/Primary?api_key=' + api_key 101 | requests.post(url=url_post_img, data=b6_pic, headers=header) 102 | print('>>Success：', actor_name) 103 | num_suc += 1 104 | 105 | print('\nemby/jellyfin people: ', num_persons, '') 106 | print('include photos: ', num_exist, '') 107 | if bool_replace: 108 | print('Mode：Overwrite existed images') 109 | else: 110 | print('Mode：Skip existed images') 111 | print('Success Upload', num_suc, '个！') 112 | print('No images', num_fail, '个！') 113 | print('Saved to “no_included.txt”\n') 114 | os.system('pause') 115 | except: 116 | print(format_exc()) 117 | os.system('pause') 118 | 119 | 120 | -------------------------------------------------------------------------------- /avsox.py: -------------------------------------------------------------------------------- 1 | import re 2 | from lxml import etree 3 | import json 4 | from bs4 import BeautifulSoup 5 | from ADC_function import * 6 | # import sys 7 | # import io 8 | # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True) 9 | 10 | def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img 11 | soup = BeautifulSoup(htmlcode, 'lxml') 12 | a = soup.find_all(attrs={'class': 'avatar-box'}) 13 | d = {} 14 | for i in a: 15 | l = i.img['src'] 16 | t = i.span.get_text() 17 | p2 = {t: l} 18 | d.update(p2) 19 | return d 20 | def getTitle(a): 21 | try: 22 | html = etree.fromstring(a, etree.HTMLParser()) 23 | result = str(html.xpath('/html/body/div[2]/h3/text()')).strip(" ['']") #[0] 24 | return result.replace('/', '') 25 | except: 26 | return '' 27 | def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text() 28 | soup = BeautifulSoup(a, 'lxml') 29 | a = soup.find_all(attrs={'class': 'avatar-box'}) 30 | d = [] 31 | for i in a: 32 | d.append(i.span.get_text()) 33 | return d 34 | def getStudio(a): 35 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 36 | result1 = str(html.xpath('//p[contains(text(),"制作商: ")]/following-sibling::p[1]/a/text()')).strip(" ['']").replace("', '",' ') 37 | return result1 38 | def getRuntime(a): 39 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 40 | result1 = str(html.xpath('//span[contains(text(),"长度:")]/../text()')).strip(" ['分钟']") 41 | return result1 42 | def getLabel(a): 43 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 44 | result1 = str(html.xpath('//p[contains(text(),"系列:")]/following-sibling::p[1]/a/text()')).strip(" ['']") 45 | return result1 46 | def getNum(a): 47 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 48 | result1 = str(html.xpath('//span[contains(text(),"识别码:")]/../span[2]/text()')).strip(" ['']") 49 | return result1 50 | def getYear(release): 51 | try: 52 | result = str(re.search('\d{4}',release).group()) 53 | return result 54 | except: 55 | return release 56 | def getRelease(a): 57 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 58 | result1 = str(html.xpath('//span[contains(text(),"发行时间:")]/../text()')).strip(" ['']") 59 | return result1 60 | def getCover(htmlcode): 61 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 62 | result = str(html.xpath('/html/body/div[2]/div[1]/div[1]/a/img/@src')).strip(" ['']") 63 | return result 64 | def getCover_small(htmlcode): 65 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 66 | result = str(html.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']") 67 | return result 68 | def getTag(a): # 获取演员 69 | soup = BeautifulSoup(a, 'lxml') 70 | a = soup.find_all(attrs={'class': 'genre'}) 71 | d = [] 72 | for i in a: 73 | d.append(i.get_text()) 74 | return d 75 | 76 | def main(number): 77 | a = get_html('https://avsox.host/cn/search/' + number) 78 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 79 | result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']") 80 | if result1 == '' or result1 == 'null' or result1 == 'None': 81 | a = get_html('https://avsox.host/cn/search/' + number.replace('-', '_')) 82 | print(a) 83 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 84 | result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']") 85 | if result1 == '' or result1 == 'null' or result1 == 'None': 86 | a = get_html('https://avsox.host/cn/search/' + number.replace('_', '')) 87 | print(a) 88 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 89 | result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']") 90 | web = get_html(result1) 91 | soup = BeautifulSoup(web, 'lxml') 92 | info = str(soup.find(attrs={'class': 'row movie'})) 93 | dic = { 94 | 'actor': getActor(web), 95 | 'title': getTitle(web).strip(getNum(web)), 96 | 'studio': getStudio(info), 97 | 'outline': '',# 98 | 'runtime': getRuntime(info), 99 | 'director': '', # 100 | 'release': getRelease(info), 101 | 'number': getNum(info), 102 | 'cover': getCover(web), 103 | 'cover_small': getCover_small(a), 104 | 'imagecut': 3, 105 | 'tag': getTag(web), 106 | 'label': getLabel(info), 107 | 'year': getYear(getRelease(info)), # str(re.search('\d{4}',getRelease(a)).group()), 108 | 'actor_photo': getActorPhoto(web), 109 | 'website': result1, 110 | 'source': 'avsox.py', 111 | } 112 | js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') 113 | return js 114 | 115 | #print(main('012717_472')) -------------------------------------------------------------------------------- /config.ini: -------------------------------------------------------------------------------- 1 | [common] 2 | main_mode=11 3 | input_file=115s.txt 4 | failed_output_file=115failed.txt 5 | success_output_folder=AV_output 6 | soft_link=0 7 | 8 | [proxy] 9 | proxy=socks5://127.0.0.1:10808 10 | timeout=5 11 | retry=2 12 | 13 | [Name_Rule] 14 | location_rule= year+'/'+studio 15 | naming_rule=number+' '+actor+' '+title 16 | 17 | [update] 18 | update_check=0 19 | 20 | [escape] 21 | literals=\()/ 22 | folders=AV_output 23 | 24 | [debug_mode] 25 | switch=0 26 | -------------------------------------------------------------------------------- /fanza.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/python3 2 | # -*- coding: utf-8 -*- 3 | import json 4 | import re 5 | 6 | from lxml import etree 7 | 8 | from ADC_function import * 9 | 10 | # import sys 11 | # import io 12 | # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True) 13 | 14 | 15 | def getTitle(text): 16 | html = etree.fromstring(text, etree.HTMLParser()) 17 | result = html.xpath('//*[@id="title"]/text()')[0] 18 | return result 19 | 20 | 21 | def getActor(text): 22 | # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text() 23 | html = etree.fromstring(text, etree.HTMLParser()) 24 | result = ( 25 | str( 26 | html.xpath( 27 | "//td[contains(text(),'出演者')]/following-sibling::td/span/a/text()" 28 | ) 29 | ) 30 | .strip(" ['']") 31 | .replace("', '", ",") 32 | ) 33 | return result 34 | 35 | 36 | def getStudio(text): 37 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 38 | try: 39 | result = html.xpath( 40 | "//td[contains(text(),'メーカー')]/following-sibling::td/a/text()" 41 | )[0] 42 | except: 43 | result = html.xpath( 44 | "//td[contains(text(),'メーカー')]/following-sibling::td/text()" 45 | )[0] 46 | return result 47 | 48 | 49 | def getRuntime(text): 50 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 51 | result = html.xpath("//td[contains(text(),'収録時間')]/following-sibling::td/text()")[0] 52 | return re.search(r"\d+", str(result)).group() 53 | 54 | 55 | def getLabel(text): 56 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 57 | try: 58 | result = html.xpath( 59 | "//td[contains(text(),'シリーズ：')]/following-sibling::td/a/text()" 60 | )[0] 61 | except: 62 | result = html.xpath( 63 | "//td[contains(text(),'シリーズ：')]/following-sibling::td/text()" 64 | )[0] 65 | return result 66 | 67 | 68 | def getNum(text): 69 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 70 | try: 71 | result = html.xpath( 72 | "//td[contains(text(),'品番：')]/following-sibling::td/a/text()" 73 | )[0] 74 | except: 75 | result = html.xpath( 76 | "//td[contains(text(),'品番：')]/following-sibling::td/text()" 77 | )[0] 78 | return result 79 | 80 | 81 | def getYear(getRelease): 82 | try: 83 | result = str(re.search(r"\d{4}", getRelease).group()) 84 | return result 85 | except: 86 | return getRelease 87 | 88 | 89 | def getRelease(text): 90 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 91 | try: 92 | result = html.xpath( 93 | "//td[contains(text(),'発売日：')]/following-sibling::td/a/text()" 94 | )[0].lstrip("\n") 95 | except: 96 | result = html.xpath( 97 | "//td[contains(text(),'発売日：')]/following-sibling::td/text()" 98 | )[0].lstrip("\n") 99 | return result 100 | 101 | 102 | def getTag(text): 103 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 104 | try: 105 | result = html.xpath( 106 | "//td[contains(text(),'ジャンル：')]/following-sibling::td/a/text()" 107 | ) 108 | except: 109 | result = html.xpath( 110 | "//td[contains(text(),'ジャンル：')]/following-sibling::td/text()" 111 | ) 112 | return result 113 | 114 | 115 | def getCover(text, number): 116 | html = etree.fromstring(text, etree.HTMLParser()) 117 | cover_number = number 118 | try: 119 | result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0] 120 | except: 121 | # sometimes fanza modify _ to \u0005f for image id 122 | if "_" in cover_number: 123 | cover_number = cover_number.replace("_", r"\u005f") 124 | try: 125 | result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0] 126 | except: 127 | # (TODO) handle more edge case 128 | # print(html) 129 | # raise exception here, same behavior as before 130 | # people's major requirement is fetching the picture 131 | raise ValueError("can not find image") 132 | return result 133 | 134 | 135 | def getDirector(text): 136 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 137 | try: 138 | result = html.xpath( 139 | "//td[contains(text(),'監督：')]/following-sibling::td/a/text()" 140 | )[0] 141 | except: 142 | result = html.xpath( 143 | "//td[contains(text(),'監督：')]/following-sibling::td/text()" 144 | )[0] 145 | return result 146 | 147 | 148 | def getOutline(text): 149 | html = etree.fromstring(text, etree.HTMLParser()) 150 | try: 151 | result = str(html.xpath("//div[@class='mg-b20 lh4']/text()")[0]).replace( 152 | "\n", "" 153 | ) 154 | if result == "": 155 | result = str(html.xpath("//div[@class='mg-b20 lh4']//p/text()")[0]).replace( 156 | "\n", "" 157 | ) 158 | except: 159 | # (TODO) handle more edge case 160 | # print(html) 161 | return "" 162 | return result 163 | 164 | 165 | def main(number): 166 | # fanza allow letter + number + underscore, normalize the input here 167 | # @note: I only find the usage of underscore as h_test123456789 168 | fanza_search_number = number 169 | # AV_Data_Capture.py.getNumber() over format the input, restore the h_ prefix 170 | if fanza_search_number.startswith("h-"): 171 | fanza_search_number = fanza_search_number.replace("h-", "h_") 172 | 173 | fanza_search_number = re.sub(r"[^0-9a-zA-Z_]", "", fanza_search_number).lower() 174 | 175 | fanza_urls = [ 176 | "https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=", 177 | "https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=", 178 | "https://www.dmm.co.jp/digital/anime/-/detail/=/cid=", 179 | "https://www.dmm.co.jp/mono/anime/-/detail/=/cid=", 180 | "https://www.dmm.co.jp/digital/videoc/-/detail/=/cid=", 181 | "https://www.dmm.co.jp/digital/nikkatsu/-/detail/=/cid=", 182 | ] 183 | chosen_url = "" 184 | for url in fanza_urls: 185 | chosen_url = url + fanza_search_number 186 | htmlcode = get_html(chosen_url) 187 | if "404 Not Found" not in htmlcode: 188 | break 189 | if "404 Not Found" in htmlcode: 190 | return json.dumps({"title": "",}) 191 | try: 192 | # for some old page, the input number does not match the page 193 | # for example, the url will be cid=test012 194 | # but the hinban on the page is test00012 195 | # so get the hinban first, and then pass it to following functions 196 | fanza_hinban = getNum(htmlcode) 197 | data = { 198 | "title": getTitle(htmlcode).strip(getActor(htmlcode)), 199 | "studio": getStudio(htmlcode), 200 | "outline": getOutline(htmlcode), 201 | "runtime": getRuntime(htmlcode), 202 | "director": getDirector(htmlcode) if "anime" not in chosen_url else "", 203 | "actor": getActor(htmlcode) if "anime" not in chosen_url else "", 204 | "release": getRelease(htmlcode), 205 | "number": fanza_hinban, 206 | "cover": getCover(htmlcode, fanza_hinban), 207 | "imagecut": 1, 208 | "tag": getTag(htmlcode), 209 | "label": getLabel(htmlcode), 210 | "year": getYear( 211 | getRelease(htmlcode) 212 | ), # str(re.search('\d{4}',getRelease(a)).group()), 213 | "actor_photo": "", 214 | "website": chosen_url, 215 | "source": "fanza.py", 216 | } 217 | except: 218 | data = { 219 | "title": "", 220 | } 221 | js = json.dumps( 222 | data, ensure_ascii=False, sort_keys=True, indent=4, separators=(",", ":") 223 | ) # .encode('UTF-8') 224 | return js 225 | 226 | 227 | if __name__ == "__main__": 228 | # print(main("DV-1562")) 229 | # input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看和错误信息。") 230 | # print(main("ipx292")) 231 | pass 232 | -------------------------------------------------------------------------------- /fc2fans_club.py: -------------------------------------------------------------------------------- 1 | import re 2 | from lxml import etree#need install 3 | import json 4 | import ADC_function 5 | # import sys 6 | # import io 7 | # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True) 8 | 9 | def getTitle(htmlcode): #获取厂商 10 | #print(htmlcode) 11 | html = etree.fromstring(htmlcode,etree.HTMLParser()) 12 | result = str(html.xpath('/html/body/div[2]/div/div[1]/h3/text()')).strip(" ['']") 13 | result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1) 14 | #print(result2) 15 | return result2 16 | def getActor(htmlcode): 17 | try: 18 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 19 | result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[5]/a/text()')).strip(" ['']") 20 | return result 21 | except: 22 | return '' 23 | def getStudio(htmlcode): #获取厂商 24 | html = etree.fromstring(htmlcode,etree.HTMLParser()) 25 | result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[3]/a[1]/text()')).strip(" ['']") 26 | return result 27 | def getNum(htmlcode): #获取番号 28 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 29 | result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']") 30 | #print(result) 31 | return result 32 | def getRelease(htmlcode2): # 33 | #a=ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php') 34 | html=etree.fromstring(htmlcode2,etree.HTMLParser()) 35 | result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']") 36 | return result 37 | def getCover(htmlcode,number,htmlcode2): #获取厂商 # 38 | #a = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id=' + str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-") + '&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php') 39 | html = etree.fromstring(htmlcode2, etree.HTMLParser()) 40 | result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[1]/a/img/@src')).strip(" ['']") 41 | if result == '': 42 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 43 | result2 = str(html.xpath('//*[@id="slider"]/ul[1]/li[1]/img/@src')).strip(" ['']") 44 | return 'https://fc2club.com' + result2 45 | return 'http:' + result 46 | def getOutline(htmlcode2): #获取番号 # 47 | html = etree.fromstring(htmlcode2, etree.HTMLParser()) 48 | result = str(html.xpath('/html/body/div[1]/div[2]/div[2]/div[1]/div/article/section[4]/p/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',') 49 | return result 50 | def getTag(htmlcode): #获取番号 51 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 52 | result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[4]/a/text()')) 53 | return result.strip(" ['']").replace("'",'').replace(' ','') 54 | def getYear(release): 55 | try: 56 | result = re.search('\d{4}',release).group() 57 | return result 58 | except: 59 | return '' 60 | 61 | def getTitle_fc2com(htmlcode): #获取厂商 62 | html = etree.fromstring(htmlcode,etree.HTMLParser()) 63 | result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/h3/text()')[0] 64 | return result 65 | def getActor_fc2com(htmlcode): 66 | try: 67 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 68 | result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')[0] 69 | return result 70 | except: 71 | return '' 72 | def getStudio_fc2com(htmlcode): #获取厂商 73 | try: 74 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 75 | result = str(html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')).strip(" ['']") 76 | return result 77 | except: 78 | return '' 79 | def getNum_fc2com(htmlcode): #获取番号 80 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 81 | result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']") 82 | return result 83 | def getRelease_fc2com(htmlcode2): # 84 | html=etree.fromstring(htmlcode2,etree.HTMLParser()) 85 | result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']") 86 | return result 87 | def getCover_fc2com(htmlcode2): #获取厂商 # 88 | html = etree.fromstring(htmlcode2, etree.HTMLParser()) 89 | result = str(html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[1]/span/img/@src')).strip(" ['']") 90 | return 'http:' + result 91 | def getOutline_fc2com(htmlcode2): #获取番号 # 92 | html = etree.fromstring(htmlcode2, etree.HTMLParser()) 93 | result = str(html.xpath('/html/body/div/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip(' ').replace('。,',',') 94 | return result 95 | def getTag_fc2com(number): #获取番号 96 | htmlcode = str(bytes(ADC_function.get_html('http://adult.contents.fc2.com/api/v4/article/'+number+'/tag?'),'utf-8').decode('unicode-escape')) 97 | result = re.findall('"tag":"(.*?)"', htmlcode) 98 | return result 99 | def getYear_fc2com(release): 100 | try: 101 | result = re.search('\d{4}',release).group() 102 | return result 103 | except: 104 | return '' 105 | 106 | def main(number): 107 | try: 108 | number = number.replace('FC2-', '').replace('fc2-', '') 109 | htmlcode2 = ADC_function.get_html('https://adult.contents.fc2.com/article/'+number+'/') 110 | htmlcode = ADC_function.get_html('https://fc2club.com//html/FC2-' + number + '.html') 111 | actor = getActor(htmlcode) 112 | if getActor(htmlcode) == '': 113 | actor = 'FC2系列' 114 | dic = { 115 | 'title': getTitle(htmlcode), 116 | 'studio': getStudio(htmlcode), 117 | 'year': '',#str(re.search('\d{4}',getRelease(number)).group()), 118 | 'outline': '',#getOutline(htmlcode2), 119 | 'runtime': getYear(getRelease(htmlcode)), 120 | 'director': getStudio(htmlcode), 121 | 'actor': actor, 122 | 'release': getRelease(number), 123 | 'number': 'FC2-'+number, 124 | 'label': '', 125 | 'cover': getCover(htmlcode,number,htmlcode2), 126 | 'imagecut': 0, 127 | 'tag': getTag(htmlcode), 128 | 'actor_photo':'', 129 | 'website': 'https://fc2club.com//html/FC2-' + number + '.html', 130 | 'source':'https://fc2club.com//html/FC2-' + number + '.html', 131 | } 132 | if dic['title'] == '': 133 | htmlcode2 = ADC_function.get_html('https://adult.contents.fc2.com/article/' + number + '/',cookies={'wei6H':'1'}) 134 | actor = getActor(htmlcode) 135 | if getActor(htmlcode) == '': 136 | actor = 'FC2系列' 137 | dic = { 138 | 'title': getTitle_fc2com(htmlcode2), 139 | 'studio': getStudio_fc2com(htmlcode2), 140 | 'year': '', # str(re.search('\d{4}',getRelease(number)).group()), 141 | 'outline': getOutline_fc2com(htmlcode2), 142 | 'runtime': getYear_fc2com(getRelease(htmlcode2)), 143 | 'director': getStudio_fc2com(htmlcode2), 144 | 'actor': actor, 145 | 'release': getRelease_fc2com(number), 146 | 'number': 'FC2-' + number, 147 | 'cover': getCover_fc2com(htmlcode2), 148 | 'imagecut': 0, 149 | 'tag': getTag_fc2com(number), 150 | 'label': '', 151 | 'actor_photo': '', 152 | 'website': 'http://adult.contents.fc2.com/article/' + number + '/', 153 | 'source': 'http://adult.contents.fc2.com/article/' + number + '/', 154 | } 155 | except Exception as e: 156 | # (TODO) better handle this 157 | # print(e) 158 | dic = {"title": ""} 159 | js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8') 160 | return js 161 | 162 | 163 | #print(main('1252953')) 164 | -------------------------------------------------------------------------------- /jav321.py: -------------------------------------------------------------------------------- 1 | import json 2 | from bs4 import BeautifulSoup 3 | from lxml import html 4 | from ADC_function import post_html 5 | 6 | 7 | def main(number: str) -> json: 8 | result = post_html(url="https://www.jav321.com/search", query={"sn": number}) 9 | soup = BeautifulSoup(result.text, "html.parser") 10 | lx = html.fromstring(str(soup)) 11 | 12 | if "/video/" in result.url: 13 | data = parse_info(soup) 14 | dic = { 15 | "title": get_title(lx), 16 | "studio": "", 17 | "year": get_year(data), 18 | "outline": get_outline(lx), 19 | "director": "", 20 | "cover": get_cover(lx), 21 | "imagecut": 1, 22 | "actor_photo": "", 23 | "website": result.url, 24 | "source": "jav321.py", 25 | **data, 26 | } 27 | else: 28 | dic = {} 29 | 30 | return json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':')) 31 | 32 | 33 | def get_title(lx: html.HtmlElement) -> str: 34 | return lx.xpath("/html/body/div[2]/div[1]/div[1]/div[1]/h3/text()")[0].strip() 35 | 36 | 37 | def parse_info(soup: BeautifulSoup) -> dict: 38 | data = soup.select_one("div.row > div.col-md-9") 39 | 40 | if data: 41 | dd = str(data).split("
") 42 | data_dic = {} 43 | for d in dd: 44 | data_dic[get_bold_text(h=d)] = d 45 | 46 | return { 47 | "actor": get_actor(data_dic), 48 | "label": get_label(data_dic), 49 | "tag": get_tag(data_dic), 50 | "number": get_number(data_dic), 51 | "release": get_release(data_dic), 52 | "runtime": get_runtime(data_dic), 53 | } 54 | else: 55 | return {} 56 | 57 | 58 | def get_bold_text(h: str) -> str: 59 | soup = BeautifulSoup(h, "html.parser") 60 | if soup.b: 61 | return soup.b.text 62 | else: 63 | return "UNKNOWN_TAG" 64 | 65 | 66 | def get_anchor_info(h: str) -> str: 67 | result = [] 68 | 69 | data = BeautifulSoup(h, "html.parser").find_all("a", href=True) 70 | for d in data: 71 | result.append(d.text) 72 | 73 | return ",".join(result) 74 | 75 | 76 | def get_text_info(h: str) -> str: 77 | return h.split(": ")[1] 78 | 79 | 80 | def get_cover(lx: html.HtmlElement) -> str: 81 | return lx.xpath("/html/body/div[2]/div[2]/div[1]/p/a/img/@src")[0] 82 | 83 | 84 | def get_outline(lx: html.HtmlElement) -> str: 85 | return lx.xpath("/html/body/div[2]/div[1]/div[1]/div[2]/div[3]/div/text()")[0] 86 | 87 | 88 | def get_actor(data: hash) -> str: 89 | if "女优" in data: 90 | return get_anchor_info(data["女优"]) 91 | else: 92 | return "" 93 | 94 | 95 | def get_label(data: hash) -> str: 96 | if "片商" in data: 97 | return get_anchor_info(data["片商"]) 98 | else: 99 | return "" 100 | 101 | 102 | def get_tag(data: hash) -> str: 103 | if "标签" in data: 104 | return get_anchor_info(data["标签"]) 105 | else: 106 | return "" 107 | 108 | 109 | def get_number(data: hash) -> str: 110 | if "番号" in data: 111 | return get_text_info(data["番号"]) 112 | else: 113 | return "" 114 | 115 | 116 | def get_release(data: hash) -> str: 117 | if "发行日期" in data: 118 | return get_text_info(data["发行日期"]) 119 | else: 120 | return "" 121 | 122 | 123 | def get_runtime(data: hash) -> str: 124 | if "播放时长" in data: 125 | return get_text_info(data["播放时长"]) 126 | else: 127 | return "" 128 | 129 | 130 | def get_year(data: hash) -> str: 131 | if "release" in data: 132 | return data["release"][:4] 133 | else: 134 | return "" 135 | 136 | 137 | if __name__ == "__main__": 138 | print(main("wmc-002")) 139 | -------------------------------------------------------------------------------- /javbus.py: -------------------------------------------------------------------------------- 1 | import re 2 | from pyquery import PyQuery as pq#need install 3 | from lxml import etree#need install 4 | from bs4 import BeautifulSoup#need install 5 | import json 6 | from ADC_function import * 7 | 8 | def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img 9 | soup = BeautifulSoup(htmlcode, 'lxml') 10 | a = soup.find_all(attrs={'class': 'star-name'}) 11 | d={} 12 | for i in a: 13 | l=i.a['href'] 14 | t=i.get_text() 15 | html = etree.fromstring(get_html(l), etree.HTMLParser()) 16 | p=str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']") 17 | p2={t:p} 18 | d.update(p2) 19 | return d 20 | def getTitle(htmlcode): #获取标题 21 | doc = pq(htmlcode) 22 | title=str(doc('div.container h3').text()).replace(' ','-') 23 | try: 24 | title2 = re.sub('n\d+-','',title) 25 | return title2 26 | except: 27 | return title 28 | def getStudio(htmlcode): #获取厂商 29 | html = etree.fromstring(htmlcode,etree.HTMLParser()) 30 | result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']") 31 | return result 32 | def getYear(htmlcode): #获取年份 33 | html = etree.fromstring(htmlcode,etree.HTMLParser()) 34 | result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']") 35 | return result 36 | def getCover(htmlcode): #获取封面链接 37 | doc = pq(htmlcode) 38 | image = doc('a.bigImage') 39 | return image.attr('href') 40 | def getRelease(htmlcode): #获取出版日期 41 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 42 | result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']") 43 | return result 44 | def getRuntime(htmlcode): #获取分钟 45 | soup = BeautifulSoup(htmlcode, 'lxml') 46 | a = soup.find(text=re.compile('分鐘')) 47 | return a 48 | def getActor(htmlcode): #获取女优 49 | b=[] 50 | soup=BeautifulSoup(htmlcode,'lxml') 51 | a=soup.find_all(attrs={'class':'star-name'}) 52 | for i in a: 53 | b.append(i.get_text()) 54 | return b 55 | def getNum(htmlcode): #获取番号 56 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 57 | result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']") 58 | return result 59 | def getDirector(htmlcode): #获取导演 60 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 61 | result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']") 62 | return result 63 | def getOutline(htmlcode): #获取演员 64 | doc = pq(htmlcode) 65 | result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text()) 66 | return result 67 | def getSerise(htmlcode): 68 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 69 | result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/a/text()')).strip(" ['']") 70 | return result 71 | def getTag(htmlcode): # 获取演员 72 | tag = [] 73 | soup = BeautifulSoup(htmlcode, 'lxml') 74 | a = soup.find_all(attrs={'class': 'genre'}) 75 | for i in a: 76 | if 'onmouseout' in str(i): 77 | continue 78 | tag.append(i.get_text()) 79 | return tag 80 | 81 | 82 | def main(number): 83 | try: 84 | htmlcode = get_html('https://www.javbus.com/' + number) 85 | try: 86 | dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", '')) 87 | except: 88 | dww_htmlcode = '' 89 | dic = { 90 | 'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))), 91 | 'studio': getStudio(htmlcode), 92 | 'year': str(re.search('\d{4}', getYear(htmlcode)).group()), 93 | 'outline': getOutline(dww_htmlcode), 94 | 'runtime': getRuntime(htmlcode), 95 | 'director': getDirector(htmlcode), 96 | 'actor': getActor(htmlcode), 97 | 'release': getRelease(htmlcode), 98 | 'number': getNum(htmlcode), 99 | 'cover': getCover(htmlcode), 100 | 'imagecut': 1, 101 | 'tag': getTag(htmlcode), 102 | 'label': getSerise(htmlcode), 103 | 'actor_photo': getActorPhoto(htmlcode), 104 | 'website': 'https://www.javbus.com/' + number, 105 | 'source' : 'javbus.py', 106 | } 107 | js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') 108 | return js 109 | except: 110 | return main_uncensored(number) 111 | 112 | def main_uncensored(number): 113 | htmlcode = get_html('https://www.javbus.com/' + number) 114 | dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", '')) 115 | if getTitle(htmlcode) == '': 116 | htmlcode = get_html('https://www.javbus.com/' + number.replace('-','_')) 117 | dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", '')) 118 | dic = { 119 | 'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''), 120 | 'studio': getStudio(htmlcode), 121 | 'year': getYear(htmlcode), 122 | 'outline': getOutline(dww_htmlcode), 123 | 'runtime': getRuntime(htmlcode), 124 | 'director': getDirector(htmlcode), 125 | 'actor': getActor(htmlcode), 126 | 'release': getRelease(htmlcode), 127 | 'number': getNum(htmlcode), 128 | 'cover': getCover(htmlcode), 129 | 'tag': getTag(htmlcode), 130 | 'label': getSerise(htmlcode), 131 | 'imagecut': 0, 132 | 'actor_photo': '', 133 | 'website': 'https://www.javbus.com/' + number, 134 | 'source': 'javbus.py', 135 | } 136 | js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') 137 | return js 138 | 139 | -------------------------------------------------------------------------------- /javdb.py: -------------------------------------------------------------------------------- 1 | import re 2 | from lxml import etree 3 | import json 4 | from bs4 import BeautifulSoup 5 | from ADC_function import * 6 | # import sys 7 | # import io 8 | # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True) 9 | 10 | def getTitle(a): 11 | html = etree.fromstring(a, etree.HTMLParser()) 12 | result = html.xpath("/html/body/section/div/h2/strong/text()")[0] 13 | return result 14 | def getActor(a): # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text() 15 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 16 | result1 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/text()')).strip(" ['']") 17 | result2 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/a/text()')).strip(" ['']") 18 | return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',').replace(',', ', ') 19 | def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img 20 | a = actor.split(',') 21 | d={} 22 | for i in a: 23 | p={i:''} 24 | d.update(p) 25 | return d 26 | def getStudio(a): 27 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 28 | result1 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/text()')).strip(" ['']") 29 | result2 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/a/text()')).strip(" ['']") 30 | return str(result1 + result2).strip('+').replace("', '", '').replace('"', '') 31 | def getRuntime(a): 32 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 33 | result1 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/text()')).strip(" ['']") 34 | result2 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/a/text()')).strip(" ['']") 35 | return str(result1 + result2).strip('+').rstrip('mi') 36 | def getLabel(a): 37 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 38 | result1 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/text()')).strip(" ['']") 39 | result2 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/a/text()')).strip(" ['']") 40 | return str(result1 + result2).strip('+').replace("', '", '').replace('"', '') 41 | def getNum(a): 42 | html = etree.fromstring(a, etree.HTMLParser()) 43 | result1 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/text()')).strip(" ['']") 44 | result2 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/a/text()')).strip(" ['']") 45 | return str(result2 + result1).strip('+') 46 | def getYear(getRelease): 47 | try: 48 | result = str(re.search('\d{4}', getRelease).group()) 49 | return result 50 | except: 51 | return getRelease 52 | def getRelease(a): 53 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 54 | result1 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/text()')).strip(" ['']") 55 | result2 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/a/text()')).strip(" ['']") 56 | return str(result1 + result2).strip('+') 57 | def getTag(a): 58 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 59 | result1 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/text()')).strip(" ['']") 60 | result2 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/a/text()')).strip(" ['']") 61 | return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',') 62 | def getCover_small(a, index=0): 63 | # same issue mentioned below, 64 | # javdb sometime returns multiple results 65 | # DO NOT just get the firt one, get the one with correct index number 66 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 67 | result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index] 68 | if not 'https' in result: 69 | result = 'https:' + result 70 | return result 71 | def getCover(htmlcode): 72 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 73 | result = str(html.xpath("//div[contains(@class, 'column-video-cover')]/a/img/@src")).strip(" ['']") 74 | return result 75 | def getDirector(a): 76 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 77 | result1 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/text()')).strip(" ['']") 78 | result2 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/a/text()')).strip(" ['']") 79 | return str(result1 + result2).strip('+').replace("', '", '').replace('"', '') 80 | def getOutline(htmlcode): 81 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 82 | result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']") 83 | return result 84 | def main(number): 85 | try: 86 | number = number.upper() 87 | query_result = get_html('https://javdb.com/search?q=' + number + '&f=all') 88 | html = etree.fromstring(query_result, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 89 | # javdb sometime returns multiple results, 90 | # and the first elememt maybe not the one we are looking for 91 | # iterate all candidates and find the match one 92 | urls = html.xpath('//*[@id="videos"]/div/div/a/@href') 93 | ids =html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()') 94 | correct_url = urls[ids.index(number)] 95 | detail_page = get_html('https://javdb.com' + correct_url) 96 | dic = { 97 | 'actor': getActor(detail_page), 98 | 'title': getTitle(detail_page), 99 | 'studio': getStudio(detail_page), 100 | 'outline': getOutline(detail_page), 101 | 'runtime': getRuntime(detail_page), 102 | 'director': getDirector(detail_page), 103 | 'release': getRelease(detail_page), 104 | 'number': getNum(detail_page), 105 | 'cover': getCover(detail_page), 106 | 'cover_small': getCover_small(query_result, index=ids.index(number)), 107 | 'imagecut': 3, 108 | 'tag': getTag(detail_page), 109 | 'label': getLabel(detail_page), 110 | 'year': getYear(getRelease(detail_page)), # str(re.search('\d{4}',getRelease(a)).group()), 111 | 'actor_photo': getActorPhoto(getActor(detail_page)), 112 | 'website': 'https://javdb.com' + correct_url, 113 | 'source': 'javdb.py', 114 | } 115 | except Exception as e: 116 | # print(e) 117 | dic = {"title": ""} 118 | js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') 119 | return js 120 | 121 | # main('DV-1562') 122 | # input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看和错误信息。") 123 | #print(main('ipx-292')) 124 | -------------------------------------------------------------------------------- /linux_make.py: -------------------------------------------------------------------------------- 1 | import os 2 | os.system("pyinstaller --onefile AV_Data_Capture.py --hidden-import ADC_function.py --hidden-import core.py") 3 | os.system("rm -rf ./build") 4 | os.system("rm -rf ./__pycache__") 5 | os.system("rm -rf AV_Data_Capture.spec") 6 | os.system("echo '[Make]Finish'") 7 | -------------------------------------------------------------------------------- /mgstage.py: -------------------------------------------------------------------------------- 1 | import re 2 | from lxml import etree 3 | import json 4 | from bs4 import BeautifulSoup 5 | from ADC_function import * 6 | # import sys 7 | # import io 8 | # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True) 9 | 10 | def getTitle(a): 11 | try: 12 | html = etree.fromstring(a, etree.HTMLParser()) 13 | result = str(html.xpath('//*[@id="center_column"]/div[1]/h1/text()')).strip(" ['']") 14 | return result.replace('/', ',') 15 | except: 16 | return '' 17 | def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text() 18 | html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text() 19 | result1=str(html.xpath('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n') 20 | result2=str(html.xpath('//th[contains(text(),"出演：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n') 21 | return str(result1+result2).strip('+').replace("', '",'').replace('"','').replace('/',',') 22 | def getStudio(a): 23 | html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text() 24 | result1=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n') 25 | result2=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n') 26 | return str(result1+result2).strip('+').replace("', '",'').replace('"','') 27 | def getRuntime(a): 28 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 29 | result1 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip('\\n') 30 | result2 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/text()')).strip(" ['']").strip('\\n ').strip('\\n') 31 | return str(result1 + result2).strip('+').rstrip('mi') 32 | def getLabel(a): 33 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 34 | result1 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip( 35 | '\\n') 36 | result2 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n ').strip( 37 | '\\n') 38 | return str(result1 + result2).strip('+').replace("', '",'').replace('"','') 39 | def getNum(a): 40 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 41 | result1 = str(html.xpath('//th[contains(text(),"品番：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip( 42 | '\\n') 43 | result2 = str(html.xpath('//th[contains(text(),"品番：")]/../td/text()')).strip(" ['']").strip('\\n ').strip( 44 | '\\n') 45 | return str(result1 + result2).strip('+') 46 | def getYear(getRelease): 47 | try: 48 | result = str(re.search('\d{4}',getRelease).group()) 49 | return result 50 | except: 51 | return getRelease 52 | def getRelease(a): 53 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 54 | result1 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip( 55 | '\\n') 56 | result2 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/text()')).strip(" ['']").strip('\\n ').strip( 57 | '\\n') 58 | return str(result1 + result2).strip('+') 59 | def getTag(a): 60 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 61 | result1 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip( 62 | '\\n') 63 | result2 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/text()')).strip(" ['']").strip('\\n ').strip( 64 | '\\n') 65 | return str(result1 + result2).strip('+').replace("', '\\n",",").replace("', '","").replace('"','') 66 | def getCover(htmlcode): 67 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 68 | result = str(html.xpath('//*[@id="center_column"]/div[1]/div[1]/div/div/h2/img/@src')).strip(" ['']") 69 | # /html/body/div[2]/article[2]/div[1]/div[1]/div/div/h2/img/@src 70 | return result 71 | def getDirector(a): 72 | html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 73 | result1 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/a/text()')).strip(" ['']").strip('\\n ').strip( 74 | '\\n') 75 | result2 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/text()')).strip(" ['']").strip('\\n ').strip( 76 | '\\n') 77 | return str(result1 + result2).strip('+').replace("', '",'').replace('"','') 78 | def getOutline(htmlcode): 79 | html = etree.fromstring(htmlcode, etree.HTMLParser()) 80 | result = str(html.xpath('//p/text()')).strip(" ['']") 81 | return result 82 | def main(number2): 83 | number=number2.upper() 84 | htmlcode=str(get_html('https://www.mgstage.com/product/product_detail/'+str(number)+'/',cookies={'adc':'1'})) 85 | soup = BeautifulSoup(htmlcode, 'lxml') 86 | a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','') 87 | b = str(soup.find(attrs={'id': 'introduction'})).replace('\n ','').replace(' ','').replace('\n ','').replace('\n ','') 88 | #print(b) 89 | dic = { 90 | 'title': getTitle(htmlcode).replace("\\n",'').replace(' ',''), 91 | 'studio': getStudio(a), 92 | 'outline': getOutline(b), 93 | 'runtime': getRuntime(a), 94 | 'director': getDirector(a), 95 | 'actor': getActor(a), 96 | 'release': getRelease(a), 97 | 'number': getNum(a), 98 | 'cover': getCover(htmlcode), 99 | 'imagecut': 0, 100 | 'tag': getTag(a), 101 | 'label':getLabel(a), 102 | 'year': getYear(getRelease(a)), # str(re.search('\d{4}',getRelease(a)).group()), 103 | 'actor_photo': '', 104 | 'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/', 105 | 'source': 'mgstage.py', 106 | } 107 | js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8') 108 | return js 109 | #print(htmlcode) 110 | 111 | #print(main('SIRO-3607')) 112 | -------------------------------------------------------------------------------- /py_to_exe.bat: -------------------------------------------------------------------------------- 1 | pyinstaller --onefile OOF_Rename.py --hidden-import ADC_function.py --hidden-import OOF_core.py 2 | rmdir /s/q build 3 | rmdir /s/q __pycache__ 4 | pause -------------------------------------------------------------------------------- /readme/1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LSD08KM/115_Code_Rename/221dd8199200719c55495b7da5956df131bfee6e/readme/1.png -------------------------------------------------------------------------------- /readme/2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LSD08KM/115_Code_Rename/221dd8199200719c55495b7da5956df131bfee6e/readme/2.png -------------------------------------------------------------------------------- /readme/This is readms.md's images folder: -------------------------------------------------------------------------------- 1 | 1 2 | -------------------------------------------------------------------------------- /readme/single.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LSD08KM/115_Code_Rename/221dd8199200719c55495b7da5956df131bfee6e/readme/single.gif -------------------------------------------------------------------------------- /ruquirments.txt: -------------------------------------------------------------------------------- 1 | lxml 2 | bs4 3 | pillow 4 | pyquery --------------------------------------------------------------------------------