├── .gitignore ├── LICENSE ├── README.md ├── onenote.py └── requirements.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 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # WizNote-to-OneNote 2 | 一个从为知笔记导入数据到 OneNote 的脚本 3 | 4 | ## 已知问题 5 | 1. OneNote 本身的限制。比如不支持自定义 CSS，文件大小等。（具体请看 [OneNote API](https://dev.onenote.com/docs)） 6 | 2. 不支持加密文档（请先在为知客户端手动解密） 7 | 3. 不支持附件（请在导入完后手动添加） 8 | 4. 不支持断点续传，且从微软获取的 token 有效期为 1 个小时。（意味着超过 1 小时会上传失败。如此巨量文档建议您还是不要轻易迁移知识库了。） 9 | 5. 仅在 Linux 环境测试通过 10 | 11 | ## 操作步骤 12 | 首先下载脚本并安装依赖 13 | 14 | 1. 登陆为知客户端，等待全部文件完成同步之后退出客户端 15 | 2. 执行脚本，根据提示输入账户名或文件夹路径（Windows 上路径为 `我的文档\My Knowledge\Data\{account}\`） 16 | 3. 打开提供的登录链接进行授权，然后复制并输入跳转后的空白页链接 17 | 4. 选择目标笔记本名称（请输入新的名字以避免冲突） 18 | 5. 开始导入，等待导入完成后确认内容正确，并根据需要手动上传附件。 19 | -------------------------------------------------------------------------------- /onenote.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | 3 | import mimetypes 4 | import os 5 | import re 6 | import sqlite3 7 | from collections import namedtuple, OrderedDict 8 | from datetime import datetime, timedelta, timezone 9 | from sys import platform 10 | from urllib.parse import urlencode, parse_qs 11 | from zipfile import ZipFile 12 | 13 | import requests 14 | from bs4 import BeautifulSoup 15 | from requests import HTTPError 16 | from requests.auth import AuthBase 17 | 18 | CLIENT_ID = 'ddbd41a5-c46d-44f2-85b2-d73bbd7bee7d' 19 | CLIENT_SECRET = 'qqgu6ApNZyUmvYgna2WBwK5' 20 | REDIRECT_URI = 'https://login.live.com/oauth20_desktop.srf' 21 | 22 | LINUX_DATA_PATH = os.path.expanduser('~/.wiznote/{}/data') 23 | API_BASE = 'https://www.onenote.com/api/v1.0/me/notes' 24 | AUTH_URL = 'https://login.live.com/oauth20_authorize.srf?' + urlencode({ 25 | 'response_type': 'code', 26 | 'client_id': CLIENT_ID, 27 | 'redirect_uri': REDIRECT_URI, 28 | 'scope': 'wl.signin office.onenote_create' 29 | }) 30 | OAUTH_URL = 'https://login.live.com/oauth20_token.srf' 31 | 32 | Document = namedtuple('Document', ['guid', 'title', 'location', 'name', 'url', 'created']) 33 | 34 | 35 | class BearerAuth(AuthBase): 36 | def __init__(self, token): 37 | self.token = token 38 | 39 | def __call__(self, r): 40 | r.headers['Authorization'] = 'Bearer ' + self.token 41 | return r 42 | 43 | 44 | def get_data_dir(): 45 | while True: 46 | if platform == 'linux': 47 | account = input('Input WizNote account: ') 48 | data_path = LINUX_DATA_PATH.format(account) 49 | elif platform == 'win32' or platform == 'darwin': 50 | data_path = input('Input WizNote dir path of "index.db": ') 51 | else: 52 | raise Exception('Unsupported platform') 53 | 54 | index_path = os.path.join(data_path, 'index.db') 55 | if not os.path.isfile(index_path): 56 | print('Account data not found!') 57 | continue 58 | 59 | break 60 | 61 | return data_path, index_path 62 | 63 | 64 | def get_doc_path(data_path, doc): 65 | if platform == 'linux' or platform == 'darwin': 66 | return os.path.join(data_path, 'notes', '{%s}' % doc.guid) 67 | 68 | if platform == 'win32': 69 | return os.path.join(data_path, doc.location.strip('/'), doc.name) 70 | 71 | raise Exception('Unsupported platform') 72 | 73 | 74 | def get_token(session): 75 | print('Sign in via: ') 76 | print(AUTH_URL) 77 | print('Copy the url of blank page after signed in,\n' 78 | f'url should starts with "{REDIRECT_URI}"') 79 | 80 | while True: 81 | url = input('URL: ') 82 | 83 | if not url.startswith(REDIRECT_URI): 84 | print('Invalid URL!') 85 | continue 86 | 87 | code = parse_qs(url[url.index('?')+1:])['code'][0] 88 | break 89 | 90 | resp = session.post(OAUTH_URL, data={ 91 | 'grant_type': 'authorization_code', 92 | 'client_id': CLIENT_ID, 93 | 'client_secret': '', 94 | 'code': code, 95 | 'redirect_uri': REDIRECT_URI, 96 | }).json() 97 | 98 | print('Token result:', resp) 99 | 100 | return resp['access_token'] 101 | 102 | 103 | def create_notebook(session): 104 | name = input('Pleas input new notebook name(such as WizNote, can\'t be empty).\nName: ') 105 | print('Creating notebook: "%s"' % name) 106 | resp = session.post(API_BASE + '/notebooks', json={'name': name}) 107 | resp.raise_for_status() 108 | 109 | return resp.json()['id'] 110 | 111 | 112 | def create_section(session, notebook_id, name): 113 | print('Creating section: "%s"' % name) 114 | resp = session.post(API_BASE + '/notebooks/%s/sections' % notebook_id, json={'name': name}) 115 | resp.raise_for_status() 116 | 117 | return resp.json()['id'] 118 | 119 | 120 | def get_documents(): 121 | data_path, index_path = get_data_dir() 122 | 123 | result = OrderedDict() 124 | with sqlite3.connect(index_path) as conn: 125 | sql = """ 126 | SELECT DOCUMENT_GUID, DOCUMENT_TITLE, DOCUMENT_LOCATION, DOCUMENT_NAME, DOCUMENT_URL, DT_CREATED, 127 | DOCUMENT_PROTECT, DOCUMENT_ATTACHEMENT_COUNT 128 | FROM wiz_document 129 | ORDER BY DOCUMENT_LOCATION; 130 | """.strip() 131 | 132 | cur = conn.execute(sql) 133 | while True: 134 | row = cur.fetchone() 135 | if not row: 136 | break 137 | 138 | guid, title, location, name, url, created, protect, attachment_count = row 139 | 140 | if protect: 141 | print('Ignore protected document "%s"' % (location + title)) 142 | continue 143 | 144 | if attachment_count: 145 | print('Ignore %d attachment(s) in "%s"' % (attachment_count, location + title)) 146 | 147 | docs = result.get(location) 148 | if not docs: 149 | docs = [] 150 | result[location] = docs 151 | 152 | doc = Document(guid, title, location, name, url, created) 153 | docs.append(doc) 154 | 155 | return data_path, result 156 | 157 | 158 | def clean_html(data, doc): 159 | def parse_datetime(time_str): 160 | time = datetime.strptime(time_str, '%Y-%m-%d %H:%M:%S') 161 | return time.replace(tzinfo=timezone(timedelta(hours=-8))).isoformat() 162 | 163 | soup = BeautifulSoup(data, 'lxml') 164 | 165 | pattern = re.compile(r'^index_files/(.+?)$') 166 | imgs = soup.find_all('img', src=pattern) 167 | 168 | src_file_names = [] 169 | for img in imgs: 170 | src = img['src'] 171 | match = pattern.fullmatch(src) 172 | file_name = match.group(1) 173 | 174 | src_file_names.append(file_name) 175 | img['src'] = 'name:' + file_name 176 | 177 | head_tag = soup.head 178 | if not head_tag: 179 | head_tag = soup.new_tag('head') 180 | soup.html.insert(0, head_tag) 181 | 182 | title_tag = head_tag.title 183 | if not title_tag: 184 | title_tag = soup.new_tag('title') 185 | 186 | # to avoid 'Untitled' in title 187 | title_tag.string = doc.title 188 | head_tag.insert(0, title_tag) 189 | 190 | created_tag = soup.new_tag('meta', attrs={'name': 'created', 'content': parse_datetime(doc.created)}) 191 | head_tag.insert(1, created_tag) 192 | 193 | if doc.url: 194 | url_tag = soup.new_tag('p') 195 | url_tag.string = 'URL: ' + doc.url 196 | soup.body.insert(0, url_tag) 197 | 198 | return soup.encode('utf-8'), src_file_names 199 | 200 | 201 | def upload_doc(session, section_id, data_path, doc): 202 | doc_path = get_doc_path(data_path, doc) 203 | 204 | print('Processing %s%s (%s)' % (doc.location, doc.title, doc.guid)) 205 | 206 | with ZipFile(doc_path) as zip_file: 207 | html_content, src_file_names = clean_html(zip_file.read('index.html'), doc) 208 | 209 | if len(src_file_names) > 5: 210 | print('Upload may failed if images more than 5') 211 | 212 | data_send = { 213 | 'Presentation': (None, html_content, mimetypes.guess_type('index.html')[0]) 214 | } 215 | 216 | for name in src_file_names: 217 | data_send[name] = (None, zip_file.read('index_files/' + name), mimetypes.guess_type(name)[0]) 218 | 219 | resp = session.post(API_BASE + '/sections/%s/pages' % section_id, files=data_send) 220 | resp.raise_for_status() 221 | 222 | 223 | def main(): 224 | data_dir, docs = get_documents() 225 | 226 | with requests.session() as session: 227 | token = get_token(session) 228 | session.auth = BearerAuth(token) 229 | 230 | notebook_id = create_notebook(session) 231 | 232 | for location, docs in docs.items(): 233 | section_name = location.strip('/').replace('/', '-') 234 | section_id = create_section(session, notebook_id, section_name) 235 | 236 | for doc in docs: 237 | upload_doc(session, section_id, data_dir, doc) 238 | 239 | 240 | if __name__ == '__main__': 241 | try: 242 | main() 243 | except HTTPError as e: 244 | print(e.response.json()) 245 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | beautifulsoup4 2 | chardet 3 | lxml 4 | requests --------------------------------------------------------------------------------