├── .gitignore ├── LICENSE ├── README.md ├── analyze.txt ├── grab_huaban_board.py ├── gui_batchdownload.py ├── logo.ico ├── up2picbed.py └── version_file.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 | env/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | downloads/ 16 | eggs/ 17 | .eggs/ 18 | lib/ 19 | lib64/ 20 | parts/ 21 | sdist/ 22 | var/ 23 | *.egg-info/ 24 | .installed.cfg 25 | *.egg 26 | 27 | # PyInstaller 28 | # Usually these files are written by a python script from a template 29 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 30 | *.manifest 31 | *.spec 32 | 33 | # Installer logs 34 | pip-log.txt 35 | pip-delete-this-directory.txt 36 | 37 | # Unit test / coverage reports 38 | htmlcov/ 39 | .tox/ 40 | .coverage 41 | .coverage.* 42 | .cache 43 | nosetests.xml 44 | coverage.xml 45 | *,cover 46 | .hypothesis/ 47 | 48 | # Translations 49 | *.mo 50 | *.pot 51 | 52 | # Django stuff: 53 | *.log 54 | local_settings.py 55 | 56 | # Flask stuff: 57 | instance/ 58 | .webassets-cache 59 | 60 | # Scrapy stuff: 61 | .scrapy 62 | 63 | # Sphinx documentation 64 | docs/_build/ 65 | 66 | # PyBuilder 67 | target/ 68 | 69 | # IPython Notebook 70 | .ipynb_checkpoints 71 | 72 | # pyenv 73 | .python-version 74 | 75 | # celery beat schedule file 76 | celerybeat-schedule 77 | 78 | # dotenv 79 | .env 80 | 81 | # virtualenv 82 | venv/ 83 | ENV/ 84 | 85 | # Spyder project settings 86 | .spyderproject 87 | 88 | # Rope project settings 89 | .ropeproject 90 | 91 | boards/ 92 | .up2picbed.dat 93 | .up2picbed.dat.db 94 | myAutoUpload.sh 95 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | BSD 3-Clause License 2 | 3 | Copyright (c) 2019, Mr.tao 4 | All rights reserved. 5 | 6 | Redistribution and use in source and binary forms, with or without 7 | modification, are permitted provided that the following conditions are met: 8 | 9 | * Redistributions of source code must retain the above copyright notice, this 10 | list of conditions and the following disclaimer. 11 | 12 | * Redistributions in binary form must reproduce the above copyright notice, 13 | this list of conditions and the following disclaimer in the documentation 14 | and/or other materials provided with the distribution. 15 | 16 | * Neither the name of the copyright holder nor the names of its 17 | contributors may be used to endorse or promote products derived from 18 | this software without specific prior written permission. 19 | 20 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" 21 | AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 22 | IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE 23 | DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE 24 | FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 25 | DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR 26 | SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 27 | CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, 28 | OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 29 | OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 30 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # grab_huaban_board 2 | 批量下载花瓣网画板、堆糖网专辑 3 | 4 | 5 | ## 解析 6 | 7 | * 查看analyze.txt 8 | 9 | 10 | ## 使用 11 | 12 | ``` 13 | git clone https://github.com/staugur/grab_huaban_board 14 | cd grab_huaban_board 15 | ``` 16 | 17 | ### for Python 18 | 19 | 基于python2.7（您需要python环境，不谙此道者建议使用JS版，只需要浏览器即可），测试性地支持py3 20 | 21 | 1. pip install requests 22 | 23 | 2. python grab_huaban_board.py --help 24 | ``` 25 | usage: grab_huaban_board.py [-h] [-a ACTION] [-u USER] [-p PASSWORD] [-v] 26 | [--board_id BOARD_ID] [--user_id USER_ID] 27 | [--debug] [--proxy] [--proxy_apiurl PROXY_APIURL] 28 | 29 | optional arguments: 30 | -h, --help show this help message and exit 31 | -a ACTION, --action ACTION 32 | 脚本动作 -> getBoard: 抓取单画板(默认); getUser: 抓取单用户 33 | -u USER, --user USER 花瓣网账号-手机/邮箱 34 | -p PASSWORD, --password PASSWORD 35 | 花瓣网账号对应密码 36 | -v, --version 查看版本号 37 | -bid BOARD_ID, --board_id BOARD_ID 花瓣网单个画板id, action=getBoard时使用 38 | -uid USER_ID, --user_id USER_ID 花瓣网单个用户id, action=getUser时使用 39 | --debug 开启debug输出 40 | --proxy 开启IP代理池 41 | --proxy_apiurl PROXY_APIURL 42 | IP代理池接口：开启IP代理池后，设置此选项使用非默认接口 43 | ``` 44 | 45 | * 温馨提示：开启IP代理池，需要您使用 `proxy_apiurl` 设置一个能输出ip的接口！ 46 | 47 | * 详细使用文档请参考: [https://blog.saintic.com/blog/204.html](https://blog.saintic.com/blog/204.html "https://blog.saintic.com/blog/204.html") 48 | 49 | 50 | ### for JavaScript(花瓣、堆糖) 51 | 52 | * 详细使用文档请参考：[https://blog.saintic.com/blog/256.html](https://blog.saintic.com/blog/256.html "https://blog.saintic.com/blog/256.html") 53 | 54 | * 花瓣网下载脚本主页及安装地址：[请点击我](https://greasyfork.org/zh-CN/scripts/368427-%E8%8A%B1%E7%93%A3%E7%BD%91%E4%B8%8B%E8%BD%BD "请点击我") 55 | 56 | * 堆糖网下载脚本主页及安装地址：[请点击我](https://greasyfork.org/zh-CN/scripts/369842-%E5%A0%86%E7%B3%96%E7%BD%91%E4%B8%8B%E8%BD%BD "请点击我") 57 | 58 | * 仓库地址：[GitHub](https://github.com/saintic/userscript) 59 | 60 | * 当前仓库下有一个`gui_batchdownload.py`脚本用于这两个油猴脚本文本方式的批量下载，用以一定程度上避免迅雷等下载工具。 61 | 62 | - 环境： Windows，Py2.7 63 | 64 | - 依赖： `pip install pyinstaller pywin32` 65 | 66 | - 打包： `pyinstaller.exe -F gui_batchdownload.py -i logo.ico -w --version-file version_file.txt` 67 | 68 | ## up2picbed 69 | 70 | 这是一个将花瓣网画板图片上传到[picbed](https://github.com/staugur/picbed)的脚本。 71 | 72 | 你需要用`grab_huaban_board.py`下载画板或用户，使用`up2picbed.py`上传画板或 73 | 用户所有画板，这个脚本会增量上传（即自动跳过已经上传的文件，但此功能基于 74 | 本地存储文件.up2picbed.dat且文件索引严格，如果删除dat文件则重传，如果文件名 75 | 改变则重传）。 76 | 77 | ``` 78 | $ python ./up2picbed.py -h 79 | usage: up2picbed.py [-h] [-b] [-u] [--picbed-url PICBED_URL] 80 | [--picbed-token PICBED_TOKEN] 81 | board_or_user 82 | 83 | positional arguments: 84 | board_or_user 画板ID或用户名 85 | 86 | optional arguments: 87 | -h, --help show this help message and exit 88 | -b, --board 上传画板，允许逗号选择多个，默认此项 89 | -u, --user 上传单个用户下所有画板 90 | --picbed-url PICBED_URL 91 | picbed的根域名 92 | --picbed-token PICBED_TOKEN 93 | picbed的用户token 94 | ``` 95 | 96 | 示例： 97 | 98 | 1. 上传画板: `./up2picbed.py --picbed-url https://picbed.saintic.com --picbed-token Token 画板ID` 99 | 100 | 2. 上传用户: `./up2picbed.py --picbed-url https://picbed.saintic.com --picbed-token Token -u 用户名` 101 | 102 | ## TODO 103 | 104 | 1. --board_ids 多画板 105 | 2. --user_ids 多用户 106 | 3. --igonre 指定忽略画板 107 | 4. ~~ip代理池~~ 108 | 109 | But，以上todo暂无计划，py版目前只针对bug 110 | 111 | 112 | ## 友情链接 113 | 1. [MacOS GUI 备份程序](https://github.com/ZhuPeng/grab_huaban_board "MacOS GUI 备份程序") 114 | -------------------------------------------------------------------------------- /analyze.txt: -------------------------------------------------------------------------------- 1 |  2 | 一、对于python 3 | 4 | 模仿ajax请求(header) 5 | s=requests.Session() 6 | s.headers.update({'X-Request': 'JSON', 'X-Requested-With': 'XMLHttpRequest', 'Referer': 'https://huaban.com', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36', 'Accept':'application/json'}) 7 | 8 | 9 | #### 以下针对画板 10 | 1. post 11 | https://huaban.com/auth/ 12 | r1=s.post(url1, headers=headers) 13 | data = dict(email="", password='') 14 | headers["Content-type"] = "application/x-www-form-urlencoded; charset=UTF-8" 15 | 错误密码时返回(JSON)： {"err":403,"msg":"用户密码错误"} 16 | 正确时返回(JSON)： 17 | {u'redirect': u'http://huaban.com/', u'user': {u'username': u'\u5c81\u6708\u5982\u5200\u65a9\u5929\u9a84', u'rating': 8191, u'user_id': 9880671, u'following_count': 43, u'roles': u'', u'location': u'\u5317\u4eac', u'status': {u'newbietask': 0, u'default_board': 13582018, u'past_shiji_guide': 1, u'featuretask': 6, u'share': u'0', u'lr': 1457690110, u'emailvalid': False, u'invites': 0}, u'boards_like_count': 15, u'like_count': 22, u'profile': {}, u'avatar': {u'farm': u'farm1', u'bucket': u'hbimg', u'height': u'700', u'width': u'541', u'key': u'18796173a3f91fcba4b767d0df743cdb041897ec73a4c-XlcHNT', u'frames': u'1', u'type': u'image/png', u'id': 131352797}, u'creations_count': 0, u'follower_count': 78, u'urlname': u'staugur', u'bindings': {u'weibo': u'weibo-3271188341'}, u'commodity_count': 0, u'pin_count': 1207, u'board_count': 2}} 18 | 19 | 2. get 20 | https://huaban.com/boards/32956845/ 21 | r2=s.get(url2,headers=headers) 22 | 返回json['board': ''] 23 | 24 | 3.ajax 25 | max=data['board']['pins'][-1]['pin_id'] 26 | url3 = 'https://huaban.com/boards/32956845/?max=max&limit=100&wfl=1' 27 | #Content-Type: application/json; charset=utf-8 28 | r3=s.get(url3, headers=headers) 29 | len(data3['board']['pins']) 30 | 100 31 | data3['board']['pins'][0]['pin_id'] 32 | 1131315846 33 | 34 | data3['board']['pins'][-1]['pin_id'] 35 | 973346258 36 | 37 | 38 | ######以下针对user 39 | 1. https://huaban.com/staugur 40 | get 返回 json ['user'] 41 | 42 | board_count = data['board_count'] 43 | board_ids = [ board['board_id'] for board in data['boards'] ] 44 | 45 | 46 | 2. ajax 47 | last_board_id=data['boards'][-1]['board_id'] 48 | https://huaban.com/staugur?jhhft3as&max=last_board_id&limit=10&wfl=1 49 | get 返回 json ['user'] 50 | 数据同1中 51 | 52 | 53 | 二、对于js 54 | 直接获取url中board_id，使用ajax访问首页及加载后续页即可获取所有json数据，拼接imgUrl通过不同下载方式保存图片即可。 55 | 56 | 57 | 三、堆糖网 58 | 利用ajax获取其接口数据，主要参数album_id,limit,start。 59 | -------------------------------------------------------------------------------- /grab_huaban_board.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf8 -*- 3 | 4 | __version__ = "5.0.4" 5 | __author__ = "staugur" 6 | __doc__ = "https://blog.saintic.com/blog/204.html" 7 | 8 | import os 9 | import logging 10 | import requests 11 | from random import choice 12 | from time import sleep 13 | from multiprocessing.dummy import Pool as ThreadPool 14 | from multiprocessing import Pool as ProcessPool 15 | 16 | # 花瓣网域名，目前应该设置为huaban.com，可使用http或https协议。 17 | BASE_URL = 'https://huaban.com' 18 | # 设置下载短暂停止时间，单位：秒 19 | SLEEP_TIME = 1 20 | # 开启ip代理池 21 | WITH_IP_POOL = False 22 | IP_POOL_API = "https://open.saintic.com/proxy/get/" 23 | # 调试输出 24 | DEBUG = False 25 | 26 | logging.basicConfig( 27 | level=logging.INFO, 28 | format='[ %(levelname)s ] %(asctime)s %(filename)s:%(threadName)s:%(process)d:%(lineno)d %(message)s', 29 | datefmt='%Y-%m-%d %H:%M:%S', 30 | filename='huaban.log', 31 | filemode='a' 32 | ) 33 | 34 | request = requests.Session() 35 | request.verify = True 36 | request.headers.update({ 37 | 'X-Request': 'JSON', 'X-Requested-With': 'XMLHttpRequest', 'Referer': BASE_URL, 38 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36' 39 | }) 40 | user_agent_list = [ 41 | "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36", 42 | "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36", 43 | "Mozilla/5.0 (Windows NT 10.0; …) Gecko/20100101 Firefox/61.0", 44 | "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36", 45 | "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36", 46 | "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36", 47 | "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)", 48 | "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15", 49 | ] 50 | 51 | 52 | def get_proxy(): 53 | resp = dict() 54 | if WITH_IP_POOL is True: 55 | try: 56 | _ip_proxy = request.get(IP_POOL_API, timeout=5).text 57 | except requests.exceptions.RequestException as e: 58 | logging.warn(e, exc_info=True) 59 | else: 60 | if not (_ip_proxy.startswith("http://") or _ip_proxy.startswith("https://")): 61 | _ip_proxy = "http://%s" % _ip_proxy 62 | resp = {"http": _ip_proxy, "https": _ip_proxy} 63 | logging.info("Start ip_proxy_pool, get result: %s" % resp) 64 | return resp 65 | 66 | 67 | def printcolor(msg, color=None): 68 | if color == "green": 69 | print('\033[92m%s\033[0m' % msg) 70 | elif color == "blue": 71 | print('\033[94m%s\033[0m' % msg) 72 | elif color == "yellow": 73 | print('\033[93m%s\033[0m' % msg) 74 | elif color == "red": 75 | print('\033[91m%s\033[0m' % msg) 76 | else: 77 | print(msg) 78 | 79 | 80 | def makedir(d): 81 | if not os.path.exists(d): 82 | os.makedirs(d) 83 | if os.path.exists(d): 84 | return True 85 | else: 86 | return False 87 | 88 | 89 | def _post_login(email, password): 90 | """登录函数""" 91 | res = dict(success=False) 92 | url = BASE_URL + "/auth/" 93 | try: 94 | resp = request.post(url, data=dict(email=email, password=password), headers={ 95 | 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'}).json() 96 | except Exception as e: 97 | logging.error(e, exc_info=True) 98 | else: 99 | if "user" in resp: 100 | # 登录成功 101 | res.update(success=True, data=resp["user"]) 102 | else: 103 | res.update(resp) 104 | return res 105 | 106 | 107 | def _download_img(pin, retry=True): 108 | """ 下载单个原图 109 | @param pin dict: pin的数据，要求： {'pin_id': xx, 'suffix': u'png|jpg|jpeg...', 'key': u'xxx-xx', 'board_id': xx} 110 | @param retry bool: 是否失败重试 111 | """ 112 | if pin and isinstance(pin, dict) and "pin_id" in pin and "suffix" in pin and "key" in pin and "board_id" in pin: 113 | imgurl = "https://hbimg.huabanimg.com/{}".format(pin["key"]) 114 | imgdir = pin['board_id'] 115 | imgname = os.path.join(imgdir, '{}.{}'.format( 116 | pin["pin_id"], pin["suffix"])) 117 | if os.path.isfile(imgname): 118 | if DEBUG: 119 | printcolor("Skip downloaded images: %s" % imgname) 120 | return 121 | try: 122 | makedir(imgdir) 123 | req = request.get(imgurl) 124 | with open(imgname, 'wb') as fp: 125 | fp.write(req.content) 126 | except Exception as e: 127 | logging.warn(e, exc_info=True) 128 | if retry is True: 129 | _download_img(pin, False) 130 | else: 131 | printcolor("Failed download for {}".format(imgurl), "yellow") 132 | else: 133 | if DEBUG: 134 | printcolor("Successful download for {}, save as {}".format( 135 | pin["pin_id"], imgname), "blue") 136 | 137 | 138 | def _crawl_board(board_id): 139 | """ 获取画板下所有pin """ 140 | if not board_id: 141 | return 142 | limit = 100 143 | board_url = BASE_URL + '/boards/{}/'.format(board_id) 144 | try: 145 | # get first pin data 146 | r = request.get(board_url).json() 147 | except requests.ConnectionError: 148 | request.headers.update({"User-Agent": choice(user_agent_list)}) 149 | r = request.get(board_url).json() 150 | except Exception as e: 151 | printcolor("Crawl first page error, board_id: {}".format( 152 | board_id), "yellow") 153 | logging.error(e, exc_info=True) 154 | else: 155 | if "board" in r: 156 | board_data = r["board"] 157 | else: 158 | printcolor(r.get("msg")) 159 | return 160 | pin_number = board_data["pin_count"] 161 | retry = 2 * pin_number / limit 162 | board_pins = board_data["pins"] 163 | printcolor("Current board <{}> pins number is {}, first pins number is {}".format( 164 | board_id, pin_number, len(board_pins)), 'red') 165 | if len(board_pins) < pin_number: 166 | last_pin = board_pins[-1]['pin_id'] 167 | while 1 <= retry: 168 | # get ajax pin data 169 | board_next_url = BASE_URL + \ 170 | "/boards/{}/?max={}&limit={}&wfl=1".format( 171 | board_id, last_pin, limit) 172 | try: 173 | board_next_data = request.get( 174 | board_next_url).json()["board"] 175 | except Exception as e: 176 | logging.error(e, exc_info=True) 177 | continue 178 | else: 179 | board_pins += board_next_data["pins"] 180 | printcolor("ajax load board with pin_id {}, get pins number is {}, merged".format( 181 | last_pin, len(board_next_data["pins"])), "blue") 182 | if len(board_next_data["pins"]) == 0: 183 | break 184 | last_pin = board_next_data["pins"][-1]["pin_id"] 185 | retry -= 1 186 | # 减轻访问频率 187 | sleep(SLEEP_TIME) 188 | #map(lambda pin: dict(pin_id=pin['pin_id'], suffix=pin['file']['type'].split('/')[-1], key=pin['file']['key'], board_id=board_id), board_pins) 189 | board_pins = [dict(pin_id=pin['pin_id'], suffix=pin['file'].get('type', "").split( 190 | '/')[-1] or "png", key=pin['file']['key'], board_id=board_id) for pin in board_pins] 191 | pool = ThreadPool() 192 | pool.map(_download_img, board_pins) 193 | pool.close() 194 | pool.join() 195 | printcolor("Current board {}, download over".format(board_id), "green") 196 | 197 | 198 | def _crawl_user(user_id): 199 | """ 查询user的画板 """ 200 | if not user_id: 201 | return 202 | user_url = BASE_URL + "/{}".format(user_id) 203 | limit = 5 204 | try: 205 | # get first board data 206 | r = request.get(user_url).json() 207 | except requests.ConnectionError: 208 | request.headers.update({"User-Agent": choice(user_agent_list)}) 209 | r = request.get(user_url).json() 210 | except Exception as e: 211 | printcolor("Crawl first page error, user_id: {}".format( 212 | user_id), "yellow") 213 | logging.error(e, exc_info=True) 214 | else: 215 | if "user" in r: 216 | user_data = r["user"] 217 | else: 218 | printcolor(r.get("msg")) 219 | return 220 | board_number = int(user_data['board_count']) 221 | retry = 2 * board_number / limit 222 | board_ids = user_data['boards'] 223 | printcolor("Current user <{}> boards number is {}, first boards number is {}".format( 224 | user_id, board_number, len(board_ids)), 'red') 225 | if len(board_ids) < board_number: 226 | last_board = user_data['boards'][-1]['board_id'] 227 | while 1 <= retry: 228 | # get ajax pin data 229 | user_next_url = BASE_URL + \ 230 | "/{}?jhhft3as&max={}&limit={}&wfl=1".format( 231 | user_id, last_board, limit) 232 | try: 233 | user_next_data = request.get(user_next_url).json()["user"] 234 | except Exception as e: 235 | logging.error(e, exc_info=True) 236 | continue 237 | else: 238 | board_ids += user_next_data["boards"] 239 | printcolor("ajax load user with board_id {}, get boards number is {}, merged".format( 240 | last_board, len(user_next_data["boards"])), "blue") 241 | if len(user_next_data["boards"]) == 0: 242 | break 243 | last_board = user_next_data["boards"][-1]["board_id"] 244 | retry -= 1 245 | # 减轻访问频率 246 | sleep(SLEEP_TIME) 247 | board_ids = map(str, [board['board_id'] for board in board_ids]) 248 | pool = ProcessPool() # 创建进程池 249 | # board_ids：要处理的数据列表； _crawl_board：处理列表中数据的函数 250 | pool.map(_crawl_board, board_ids) 251 | pool.close() # 关闭进程池，不再接受新的进程 252 | pool.join() # 主进程阻塞等待子进程的退出 253 | printcolor("Current user {}, download over".format(user_id), "green") 254 | 255 | 256 | def main(parser): 257 | global WITH_IP_POOL, IP_POOL_API, request, DEBUG 258 | args = parser.parse_args() 259 | if not args.action: 260 | parser.print_help() 261 | return 262 | action = args.action 263 | user = args.user 264 | password = args.password 265 | version = args.version 266 | board_id = args.board_id 267 | user_id = args.user_id 268 | if args.debug is True: 269 | DEBUG = True 270 | if args.proxy is True: 271 | WITH_IP_POOL = args.proxy 272 | IP_POOL_API = args.proxy_apiurl or IP_POOL_API 273 | request.proxies.update(get_proxy()) 274 | if version: 275 | printcolor( 276 | "https://github.com/staugur/grab_huaban_board, v{}".format(__version__)) 277 | return 278 | # 用户登录 279 | if user and password: 280 | auth = _post_login(user, password) 281 | if not auth["success"]: 282 | printcolor(auth["msg"], "yellow") 283 | return 284 | else: 285 | printcolor("您未设置账号密码，将处于未登录状态，抓取的图片可能有限；设置账号密码后，图片抓取率大部分可达100%！") 286 | # 主要动作-功能 287 | if action == "getBoard": 288 | # 抓取单画板 289 | if not board_id: 290 | printcolor("请设置board_id参数", "yellow") 291 | return 292 | makedir("boards") 293 | os.chdir("boards") 294 | _crawl_board(board_id) 295 | elif action == "getUser": 296 | # 抓取单用户 297 | if not user_id: 298 | printcolor("请设置user_id参数", "yellow") 299 | return 300 | makedir(user_id) 301 | os.chdir(user_id) 302 | _crawl_user(user_id) 303 | else: 304 | parser.print_help() 305 | 306 | 307 | if __name__ == "__main__": 308 | import argparse 309 | parser = argparse.ArgumentParser() 310 | parser.add_argument("-a", "--action", default="getBoard", 311 | help=u"脚本动作 -> getBoard: 抓取单画板(默认); getUser: 抓取单用户") 312 | parser.add_argument("-u", "--user", help=u"花瓣网账号-手机/邮箱") 313 | parser.add_argument("-p", "--password", help=u"花瓣网账号对应密码") 314 | parser.add_argument("-v", "--version", help=u"查看版本号", action='store_true') 315 | parser.add_argument("-bid", "--board_id", 316 | help=u"花瓣网单个画板id, action=getBoard时使用") 317 | parser.add_argument("-uid", "--user_id", 318 | help=u"花瓣网单个用户id, action=getUser时使用") 319 | parser.add_argument("--debug", help=u"开启debug输出", action='store_true') 320 | parser.add_argument("--proxy", help=u"开启IP代理池", action='store_true') 321 | parser.add_argument( 322 | "--proxy_apiurl", help=u"IP代理池接口：开启IP代理池后，设置此选项使用非默认接口") 323 | main(parser) 324 | -------------------------------------------------------------------------------- /gui_batchdownload.py: -------------------------------------------------------------------------------- 1 | #! /usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | # 4 | # 依赖： pip install pyinstaller pywin32 5 | # 打包： pyinstaller.exe -F gui_batchdownload.py -i logo.ico -w --version-file version_file.txt 6 | # 如需压缩，请到此https://github.com/upx/upx/releases下载对应的包（比如v3.95，win64）解压，打包时带上--upx .\upx-3.95-win64 7 | # 8 | 9 | import os 10 | from base64 import b64decode 11 | import Tkinter as tk 12 | from tkFileDialog import askdirectory 13 | from threading import Timer, Thread 14 | from tempfile import NamedTemporaryFile 15 | import tkMessageBox 16 | from sys import version_info 17 | 18 | PY2 = version_info[0] == 2 19 | if PY2: 20 | from urllib2 import build_opener 21 | else: 22 | from urllib.request import build_opener 23 | 24 | ListEqualSplit = lambda l,n=100: [ l[i:i+n] for i in range(0,len(l), n) ] 25 | logo_base64 = '''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''' 26 | with NamedTemporaryFile(mode='w+b', prefix='grab-huaban-duitang-', suffix=".ico", delete=False) as fp: 27 | fp.write(b64decode(logo_base64)) 28 | logo_file = fp.name 29 | 30 | def _makedir(d): 31 | if not os.path.exists(d): 32 | os.makedirs(d) 33 | if os.path.exists(d): 34 | return True 35 | else: 36 | return False 37 | 38 | def _get_url(url, site=None): 39 | """发起原生get请求""" 40 | class DO(dict): 41 | def __getattr__(self, name): 42 | try: 43 | return self[name] 44 | except KeyError: 45 | raise AttributeError(name) 46 | opener = build_opener() 47 | agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36' 48 | referer = 'https://huaban.com' if site == "huaban" else 'https://www.duitang.com' 49 | opener.addheaders = [('User-Agent', agent), ('Referer', referer)] 50 | response = opener.open(url) 51 | resp = dict(status=response.code, msg=response.msg, type=response.headers.type, maintype=response.headers.maintype, subtype=response.headers.subtype, headers=response.headers.dict, content=response.read()) 52 | response.close() 53 | return DO(resp) 54 | 55 | def _check_download_type(img_url): 56 | """根据img_url分析是花瓣网图片还是堆糖网图片，特征： 57 | #: 花瓣 58 | https://hbimg.b0.upaiyun.com/ec4433d815c45742a4ec1d5b6810c4ce9fe2f4d86e636-SoEBVh 59 | #: 堆糖 60 | https://b-ssl.duitang.com/uploads/item/201904/26/20190426115802_dUaAA.jpeg 61 | """ 62 | if img_url: 63 | if img_url.startswith("https://hbimg.") or img_url.startswith("http://hbimg."): 64 | return "huaban" 65 | elif "duitang.com" in img_url: 66 | return "duitang" 67 | return "unknown" 68 | 69 | class DownloadImage(Thread): 70 | 71 | def __init__(self, img_data, index=0, length=None): 72 | Thread.__init__(self) 73 | self.img_data = img_data 74 | self.index = index 75 | self.length = length - 1 76 | 77 | def run(self): 78 | """ 下载单个原图 79 | @param img_data dict: 图片所需数据，要求： {'img_url': xx, 'img_dir': xx} 80 | @param retry bool: 是否失败重试 81 | """ 82 | imgurl = self.img_data["img_url"] 83 | site = _check_download_type(imgurl) 84 | name = imgurl.split("/")[-1] 85 | imgdir = os.path.join(self.img_data["img_dir"], site) 86 | support_showmessage(u"下载: NO.%s -> %s" %(self.index, name)) 87 | try: 88 | if _makedir(imgdir) is True: 89 | response = _get_url(imgurl, site) 90 | if site in ("huaban", "unknown"): 91 | imgname = os.path.join(imgdir, '%s.%s' %(name, response.subtype or "png")) 92 | else: 93 | imgname = os.path.join(imgdir, name) 94 | if not os.path.isfile(imgname): 95 | with open(imgname, 'wb') as fp: 96 | fp.write(response.content) 97 | except: 98 | pass 99 | finally: 100 | if self.index == self.length: 101 | support_showmessage(u"下载完成", True) 102 | 103 | #: 主窗口辅助模块 104 | def support_showmessage(text, renew=False): 105 | """向message部分输出信息""" 106 | w.Label1.configure(text=text) 107 | if renew: 108 | #: 清空text 109 | w.Text1.delete('1.0', tk.END) 110 | #: 重新启用按钮 111 | w.Button1.configure(state="active") 112 | 113 | def support_start_thread(data): 114 | for p in data: 115 | p.setDaemon(True) 116 | p.start() 117 | 118 | def support_download_timer(text_list): 119 | if text_list and isinstance(text_list, list): 120 | tkMessageBox.showinfo(u"温馨提示", u"点击确定提交下载，期间请不要关闭主窗口，并关注窗口底部消息输出。") 121 | ms = 0 122 | seq = 20 123 | length = len(text_list) 124 | thread_ids = [] 125 | for i,d in enumerate(text_list): 126 | p = DownloadImage(d, i, length) 127 | thread_ids.append(p) 128 | for data in ListEqualSplit(thread_ids, seq): 129 | root.update() 130 | root.after(ms, support_start_thread, data) 131 | ms += 2000 132 | 133 | def support_batchDownload(): 134 | """开始批量下载""" 135 | #: 禁用按钮 136 | w.Button1.configure(state="disabled") 137 | #: 获取要下载的url列表 138 | text = w.Text1.get(1.0, tk.END) 139 | text_list = [ i for i in text.split("\n") if i ] 140 | #: 下载存储的目录 141 | download_dir = w.Label2.cget("text") or os.getcwd() 142 | if text_list: 143 | #: 解析text，分出huaban、duitang和unknown站点 144 | huaban_list = [ i for i in text_list if _check_download_type(i) == "huaban" ] 145 | duitang_list = [ i for i in text_list if _check_download_type(i) == "duitang" ] 146 | unknown_list = [ i for i in text_list if _check_download_type(i) == "unknown" ] 147 | all_pins = [] 148 | if os.path.isdir(os.path.join(download_dir, "huaban")): 149 | all_pins += [ i.split('.')[0] for i in os.listdir(os.path.join(download_dir, "huaban")) ] 150 | if os.path.isdir(os.path.join(download_dir, "duitang")): 151 | all_pins += [ i for i in os.listdir(os.path.join(download_dir, "duitang")) ] 152 | if os.path.isdir(os.path.join(download_dir, "unknown")): 153 | all_pins += [ i for i in os.listdir(os.path.join(download_dir, "unknown")) ] 154 | data = [ {"img_url":i, "img_dir": download_dir} for i in text_list if i.split("/")[-1] not in all_pins ] 155 | if data: 156 | support_showmessage(u"本次批量下载概述：花瓣网 %s 条，堆糖网 %s 条，未知 %s 条，有效 %s 条！" %(len(huaban_list), len(duitang_list), len(unknown_list), len(data))) 157 | root.update() 158 | root.after(1000, support_download_timer, data) 159 | else: 160 | support_showmessage(u"您输入的已经全部下载完成", True) 161 | else: 162 | support_showmessage(u"请输入花瓣网下载或堆糖网下载中复制的文本！") 163 | w.Button1.configure(state="active") 164 | 165 | def support_init(top, gui, *args, **kwargs): 166 | global w, top_level, root, timer 167 | w = gui 168 | top_level = top 169 | root = top 170 | 171 | def support_destroy_window(): 172 | # Function which closes the window. 173 | global top_level 174 | top_level.destroy() 175 | top_level.update 176 | top_level = None 177 | os.remove(logo_file) 178 | 179 | #: 启动主窗口 180 | def vp_start_gui(): 181 | '''Starting point when module is the main routine.''' 182 | global w, root 183 | root = tk.Tk() 184 | top = Toplevel1 (root) 185 | support_init(root, top) 186 | root.protocol("WM_DELETE_WINDOW", support_destroy_window) 187 | root.mainloop() 188 | 189 | #: 主窗口类 190 | class Toplevel1: 191 | 192 | def __init__(self, top=None): 193 | '''This class configures and populates the toplevel window. 194 | top is the toplevel containing window.''' 195 | _bgcolor = '#d9d9d9' # X11 color: 'gray85' 196 | _fgcolor = '#000000' # X11 color: 'black' 197 | _compcolor = '#d9d9d9' # X11 color: 'gray85' 198 | _ana1color = '#d9d9d9' # X11 color: 'gray85' 199 | _ana2color = '#ececec' # Closest X11 color: 'gray92' 200 | 201 | top.geometry("600x450+590+251") 202 | top.title(u"花瓣网、堆糖网脚本--文本下载工具") 203 | top.iconbitmap(logo_file) 204 | top.configure(background="#d9d9d9") 205 | 206 | self.Button1 = tk.Button(top) 207 | self.Button1.place(relx=0.033, rely=0.022, height=28, width=137) 208 | self.Button1.configure(activebackground="#ececec") 209 | self.Button1.configure(activeforeground="#000000") 210 | self.Button1.configure(background="#d9d9d9") 211 | self.Button1.configure(command=support_batchDownload) 212 | self.Button1.configure(disabledforeground="#a3a3a3") 213 | self.Button1.configure(foreground="#000000") 214 | self.Button1.configure(highlightbackground="#d9d9d9") 215 | self.Button1.configure(highlightcolor="black") 216 | self.Button1.configure(pady="0") 217 | self.Button1.configure(text=u'开始批量下载') 218 | 219 | #选择路径 220 | self.Button2 = tk.Button(top) 221 | self.Button2.place(relx=0.3, rely=0.022, height=28, width=60) 222 | self.Button2.configure(activebackground="#ececec") 223 | self.Button2.configure(activeforeground="#000000") 224 | self.Button2.configure(background="#d9d9d9") 225 | self.Button2.configure(disabledforeground="#a3a3a3") 226 | self.Button2.configure(foreground="#000000") 227 | self.Button2.configure(highlightbackground="#d9d9d9") 228 | self.Button2.configure(highlightcolor="black") 229 | self.Button2.configure(pady="0") 230 | self.Button2.configure(text=u'选择目录') 231 | self.Button2.configure(command=self.selectPath) 232 | 233 | #显示选择后的路径 234 | self.Label2 = tk.Label(top) 235 | self.Label2.place(relx=0.4, rely=0.022, height=28) 236 | self.Label2.configure(background="#d9d9d9") 237 | self.Label2.configure(disabledforeground="#a3a3a3") 238 | self.Label2.configure(foreground="#000000") 239 | self.Label2.configure(text=u'') 240 | 241 | self.Text1 = tk.Text(top) 242 | self.Text1.place(relx=0.033, rely=0.089, relheight=0.827, relwidth=0.94) 243 | self.Text1.configure(background="white") 244 | self.Text1.configure(borderwidth="0") 245 | self.Text1.configure(font="TkTextFont") 246 | self.Text1.configure(foreground="black") 247 | self.Text1.configure(highlightbackground="#d9d9d9") 248 | self.Text1.configure(highlightcolor="black") 249 | self.Text1.configure(insertbackground="black") 250 | self.Text1.configure(selectbackground="#c4c4c4") 251 | self.Text1.configure(selectforeground="black") 252 | self.Text1.configure(width=564) 253 | self.Text1.configure(wrap="word") 254 | 255 | self.Label1 = tk.Label(top) 256 | self.Label1.place(relx=0.033, rely=0.933, height=23, width=500) 257 | self.Label1.configure(background="#d9d9d9") 258 | self.Label1.configure(disabledforeground="#a3a3a3") 259 | self.Label1.configure(foreground="#000000") 260 | self.Label1.configure(text=u'') 261 | 262 | def selectPath(self): 263 | path_ = askdirectory(title=u"请选择或新建一个目录以存储将要下载的图片") 264 | if path_: 265 | self.Label2.configure(text=path_) 266 | 267 | @staticmethod 268 | def popup1(event, *args, **kwargs): 269 | Popupmenu1 = tk.Menu(root, tearoff=0) 270 | Popupmenu1.configure(activebackground="#f9f9f9") 271 | Popupmenu1.configure(activeborderwidth="1") 272 | Popupmenu1.configure(activeforeground="black") 273 | Popupmenu1.configure(background="#d9d9d9") 274 | Popupmenu1.configure(borderwidth="1") 275 | Popupmenu1.configure(disabledforeground="#a3a3a3") 276 | Popupmenu1.configure(font="{Microsoft YaHei UI} 9") 277 | Popupmenu1.configure(foreground="black") 278 | Popupmenu1.post(event.x_root, event.y_root) 279 | 280 | @staticmethod 281 | def popup2(event, *args, **kwargs): 282 | Popupmenu2 = tk.Menu(root, tearoff=0) 283 | Popupmenu2.configure(activebackground="#f9f9f9") 284 | Popupmenu2.configure(activeborderwidth="1") 285 | Popupmenu2.configure(activeforeground="black") 286 | Popupmenu2.configure(background="#d9d9d9") 287 | Popupmenu2.configure(borderwidth="1") 288 | Popupmenu2.configure(disabledforeground="#a3a3a3") 289 | Popupmenu2.configure(font="{Microsoft YaHei UI} 9") 290 | Popupmenu2.configure(foreground="black") 291 | Popupmenu2.post(event.x_root, event.y_root) 292 | 293 | if __name__ == '__main__': 294 | vp_start_gui() 295 | -------------------------------------------------------------------------------- /logo.ico: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/staugur/grab_huaban_board/e0ad1120bdd431e4d8eb4667331d5b82df2688ef/logo.ico -------------------------------------------------------------------------------- /up2picbed.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf8 -*- 3 | 4 | __version__ = "0.1.0" 5 | __author__ = "staugur" 6 | __doc__ = "将图片上传到picbed" 7 | 8 | import shelve 9 | import requests 10 | from time import time 11 | from os import listdir, sep 12 | from os.path import isdir, join, abspath, dirname, isfile 13 | from sys import version_info 14 | from grab_huaban_board import request, printcolor, BASE_URL 15 | 16 | BASE_DIR = dirname(abspath(__file__)) 17 | PICBED_URL = None 18 | PICBED_TOKEN = None 19 | STORAGE_INDEX = ".up2picbed.dat" 20 | ALLOWED_SUFFIX = ("png", "jpg", "jpeg", "gif", "webp") 21 | 22 | PY2 = version_info[0] == 2 23 | 24 | if PY2: # pragma: nocover 25 | 26 | def iteritems(d): 27 | return d.iteritems() 28 | 29 | text_type = unicode 30 | string_types = (str, unicode) 31 | 32 | else: # pragma: nocover 33 | 34 | def iteritems(d): 35 | return iter(d.items()) 36 | 37 | text_type = str 38 | string_types = (str,) 39 | 40 | 41 | class LocalStorage(object): 42 | """Local file system storage based on the shelve module.""" 43 | 44 | def __init__(self): 45 | self.index = join(BASE_DIR, STORAGE_INDEX) 46 | 47 | def _open(self, flag="c"): 48 | return shelve.open( 49 | filename=abspath(self.index), 50 | flag=flag, 51 | protocol=2, 52 | writeback=False 53 | ) 54 | 55 | @property 56 | def list(self): 57 | """list all data 58 | 59 | :returns: dict 60 | """ 61 | db = None 62 | try: 63 | db = self._open("r") 64 | except: 65 | return {} 66 | else: 67 | return dict(db) 68 | finally: 69 | if db: 70 | db.close() 71 | 72 | def __ck(self, key): 73 | if PY2 and isinstance(key, text_type): 74 | key = key.encode("utf-8") 75 | if not PY2 and not isinstance(key, text_type): 76 | key = key.decode("utf-8") 77 | return key 78 | 79 | def set(self, key, value): 80 | """Set persistent data with shelve. 81 | 82 | :param key: str: Index key 83 | 84 | :param value: All supported data types in python 85 | """ 86 | db = self._open() 87 | try: 88 | db[self.__ck(key)] = value 89 | finally: 90 | db.close() 91 | 92 | def setmany(self, **mapping): 93 | if mapping and isinstance(mapping, dict): 94 | db = self._open() 95 | for k, v in iteritems(mapping): 96 | db[self.__ck(k)] = v 97 | db.close() 98 | 99 | def get(self, key, default=None): 100 | """Get persistent data from shelve. 101 | 102 | :returns: data 103 | """ 104 | try: 105 | value = self.list[key] 106 | except KeyError: 107 | return default 108 | else: 109 | return value 110 | 111 | def remove(self, key): 112 | db = self._open() 113 | del db[key] 114 | 115 | def __len__(self): 116 | return len(self.list) 117 | 118 | def __str__(self): 119 | return "<%s object at %s, index is %s>" % ( 120 | self.__class__.__name__, hex(id(self)), self.index 121 | ) 122 | 123 | __repr__ = __str__ 124 | 125 | 126 | def board2piced(album, board_path): 127 | if isdir(board_path): 128 | apiurl = "%s/api/upload" % PICBED_URL.rstrip("/") 129 | headers = { 130 | "User-Agent": "grab_huaban_board/%s" % __version__, 131 | "Authorization": "Token %s" % PICBED_TOKEN 132 | } 133 | storage = LocalStorage() 134 | success = [] 135 | for filename in listdir(board_path): 136 | suffix = filename.split(".")[-1] 137 | filepath = join(board_path, filename) 138 | sindex = filepath.split(BASE_DIR)[-1] 139 | if storage.get(sindex): 140 | printcolor("%s 已上传，继续下一个" % filepath, "blue") 141 | continue 142 | if isfile(filepath) and suffix in ALLOWED_SUFFIX: 143 | files = { 144 | 'picbed': ( 145 | filename, open(filepath, 'rb'), 'image/%s' % suffix 146 | ) 147 | } 148 | try: 149 | r = requests.post( 150 | apiurl, 151 | files=files, 152 | headers=headers, 153 | data=dict(album=album), 154 | timeout=30 155 | ) 156 | except requests.exceptions.RequestException as e: 157 | printcolor( 158 | u"%s 上传错误：%s" % (filepath, e.message), 159 | "yellow" 160 | ) 161 | else: 162 | result = r.json() 163 | if result.get("code") == 0: 164 | success.append(sindex) 165 | printcolor(u"%s 上传成功" % filepath, "green") 166 | else: 167 | printcolor( 168 | u"%s 上传失败：%s" % (filepath, result["msg"]), 169 | "yellow" 170 | ) 171 | if success: 172 | storage.setmany(**{f: time() for f in success}) 173 | 174 | 175 | def main(parser): 176 | global PICBED_URL, PICBED_TOKEN 177 | args = parser.parse_args() 178 | is_board = args.board 179 | is_user = args.user 180 | if not is_board and not is_user: 181 | parser.print_help() 182 | return 183 | bou = args.board_or_user 184 | PICBED_URL = args.picbed_url 185 | PICBED_TOKEN = args.picbed_token 186 | if not PICBED_URL: 187 | printcolor("请输入picbed地址") 188 | return 189 | if is_user: 190 | if isdir(join(BASE_DIR, bou)): 191 | boards = [ 192 | join(BASE_DIR, bou, d) 193 | for d in listdir(bou) 194 | if isdir(join(BASE_DIR, bou, d)) 195 | ] 196 | else: 197 | printcolor("用户目录不存在", "red") 198 | else: 199 | boards = [ 200 | join(BASE_DIR, "boards", d) 201 | for d in bou.split(",") 202 | if isdir(join(BASE_DIR, "boards", d)) 203 | ] 204 | for board_path in boards: 205 | board_id = board_path.split(sep)[-1] 206 | album = board_id 207 | try: 208 | board_info = request.get( 209 | "%s/boards/%s" % (BASE_URL, board_id), 210 | timeout=5 211 | ).json() 212 | except requests.exceptions.RequestException: 213 | pass 214 | else: 215 | if isinstance(board_info, dict) and "board" in board_info: 216 | board_info = board_info["board"] 217 | album = board_info.get("title") or board_info["board_id"] 218 | board2piced(album, board_path) 219 | 220 | 221 | if __name__ == "__main__": 222 | import argparse 223 | parser = argparse.ArgumentParser() 224 | parser.add_argument("-b", "--board", action='store_true', default=True, 225 | help=u"上传画板，允许逗号选择多个，默认此项") 226 | parser.add_argument("-u", "--user", help=u"上传单个用户下所有画板", 227 | action='store_true') 228 | parser.add_argument("--picbed-url", help=u"picbed的根域名") 229 | parser.add_argument("--picbed-token", help=u"picbed的用户token") 230 | parser.add_argument("board_or_user", type=str, help=u"画板ID或用户名") 231 | main(parser) 232 | -------------------------------------------------------------------------------- /version_file.txt: -------------------------------------------------------------------------------- 1 | VSVersionInfo( 2 | ffi=FixedFileInfo( 3 | filevers=(0, 1, 0, 0), 4 | prodvers=(0, 1, 0, 0), 5 | mask=0x3f, 6 | flags=0x0, 7 | OS=0x40004, 8 | fileType=0x1, 9 | subtype=0x0, 10 | date=(0, 0) 11 | ), 12 | kids=[ 13 | StringFileInfo( 14 | [ 15 | StringTable( 16 | u'040904B0', 17 | [StringStruct(u'CompanyName', u'SaintIC'), 18 | StringStruct(u'FileDescription', u'花瓣、堆糖油猴脚本文本方式批量下载'), 19 | StringStruct(u'FileVersion', u'0.1.0.0'), 20 | StringStruct(u'InternalName', u'cmd'), 21 | StringStruct(u'LegalCopyright', u'\xa9 SaintIC. All rights reserved.'), 22 | StringStruct(u'OriginalFilename', u'gui_batchdownload.py'), 23 | StringStruct(u'ProductName', u'花瓣、堆糖油猴脚本文本方式批量下载'), 24 | StringStruct(u'ProductVersion', u'0.1.0.0')]) 25 | ]), 26 | VarFileInfo([VarStruct(u'Translation', [2052, 1200])]) 27 | ] 28 | ) --------------------------------------------------------------------------------