├── LICENSE ├── README.md └── evernote_remove_duplicates.py /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 | # evernote_remove_duplicates 2 | 印象笔记去重 3 | >若经常保存公众号文章，较大可能会有重复 ———— 维特根斯坦 4 | ### 一、环境配置 5 | 1. 基于 python3 6 | 2. 访问以下网址安装 python3 的印象笔记 SDK 7 | https://github.com/evernote/evernote-sdk-python3 8 | 3. pip install pandas 9 | ### 二、主线 10 | 1. 访问以下网址获取 token，填入 py 文件的 token 处 11 | https://app.yinxiang.com/api/DeveloperToken.action 12 | 2. 运行 py 文件，完成去重 13 | #### 检验程序有效性 14 | 1. 将 check 改为你的一个笔记本名称，推荐新建一个笔记本同时加入一些重复笔记 15 | 2. 将 check 改为 None 16 | ### 三、注意事项 17 | ***务必仔细阅读以下注意事项，以防错删*** 18 | 1. 笔记本**不可重名** 19 | 2. 每个笔记本内的笔记**数目不得多于 250 个** 20 | 3. API 有调用频率限制，当抛出 EDAMSystemException 异常时，rateLimitDuration 表示离刷新计数的时间间隔（秒） 21 | ### 四、代码说明 22 | #### 方法 23 | ##### get_notebook_list 24 | @para API 25 | 调用 API，获得*笔记本数据集* 26 | ##### search_note 27 | @para 笔记本名称，笔记本数据集 28 | 接受笔记本名称，获得该笔记本下的*笔记数据集* 29 | ##### get_note_list 30 | @para 笔记本数据集，笔记本名（可选） 31 | 接受*笔记本数据集*，获得*笔记数据集* 32 | 可选参数用于检验程序是否正常运行 33 | ##### writer_to_excel 34 | @para 笔记数据集，excel 文件名 35 | 接受*笔记数据集*导出备查 excel 36 | #### 数据结构 37 | 皆为 pd.DataFrame 38 | ##### 笔记本数据集 39 | columns = ['tag', 'name', 'guid'] 40 | >tag 是个人使用印象笔记时的习惯 41 | >一般笔记本名会命名类似为：a.05 - 互联网 42 | >这时 a.05 便是 tag，互联网是 name 43 | >如有修改需求可修改代码第 15 行 44 | ##### 笔记数据集 45 | columns=['name', 'guid'] 46 | ### 五、参考文献 47 | 1. 印象笔记开发者文档 48 | https://dev.yinxiang.com/doc/ 49 | 2. 使用 Python 操作 Evernote - 简书 50 | https://www.jianshu.com/p/bda26798f3b3 51 | 3. Github / EvernoteController 52 | https://github.com/littlecodersh/EasierLife/tree/master/Programs/Evernote 53 | -------------------------------------------------------------------------------- /evernote_remove_duplicates.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | import getpass 4 | import pandas as pd 5 | import evernote.edam.notestore.NoteStore as NoteStore 6 | from evernote.api.client import EvernoteClient 7 | 8 | 9 | def get_notebook_list(_note_store): 10 | notebooks = _note_store.listNotebooks() 11 | notebook_list = {} 12 | for notebook in notebooks: 13 | try: 14 | notebook_list[notebook.name] = \ 15 | [notebook.name.split('-')[0].strip(), notebook.name.split('-')[1].strip(), notebook.guid] 16 | except IndexError: 17 | notebook_list[notebook.name] = \ 18 | ['', notebook.name, notebook.guid] 19 | notebook_list = pd.DataFrame(notebook_list).T 20 | notebook_list.columns = ['tag', 'name', 'guid'] 21 | notebook_list.index = range(1, len(notebook_list) + 1, 1) 22 | return notebook_list 23 | 24 | 25 | def search_note(notebook, notebook_list): 26 | notebookguid = [item for item in notebook_list[notebook_list['name'] == notebook]['guid']][0] 27 | f = NoteStore.NoteFilter(notebookGuid=notebookguid) 28 | note_list = [] 29 | result_spec = NoteStore.NotesMetadataResultSpec(includeTitle=True) 30 | for _note in noteStore.findNotesMetadata( 31 | token, f, 0, 999, result_spec).notes: 32 | note_list.append(_note) 33 | return note_list 34 | 35 | 36 | def get_note_list(notebook_list, para=None): 37 | note_dict = [] 38 | trans = notebook_list['name'] 39 | if para is not None: 40 | trans = [para] 41 | count = 1 42 | for item in trans: 43 | note = search_note(item, notebooklist) 44 | for item2 in note: 45 | note_dict.append([item2.title, item2.guid]) 46 | count += 1 47 | if count % 5 == 0: 48 | print('已统计 {} 个笔记本'.format(count)) 49 | note_dict = pd.DataFrame(note_dict, columns=['name', 'guid']) 50 | note_dict.sort_values(by='name', inplace=True) 51 | return note_dict 52 | 53 | 54 | def writer_to_excel(data, filename): 55 | write = pd.ExcelWriter(address + r'\{}.xlsx'.format(filename)) 56 | data.to_excel(write, sheet_name=filename) 57 | write.save() 58 | write.close() 59 | 60 | 61 | # 参数 62 | 63 | pd.set_option('display.max_columns', None) 64 | pd.set_option('display.max_rows', None) 65 | address = r'C:\Users\{}\Desktop'.format(getpass.getuser()) 66 | token = '填入你的 token' 67 | check = None 68 | 69 | # 连接印象笔记 70 | 71 | client = EvernoteClient(token=token, sandbox=False, china=True) 72 | userStore = client.get_user_store() 73 | noteStore = client.get_note_store() 74 | 75 | # 正文 76 | 77 | notebooklist = get_notebook_list(noteStore) 78 | notelist = get_note_list(notebooklist, para=check) 79 | writer_to_excel(notelist, '印象笔记') 80 | 81 | # 查找与删除重复项 82 | 83 | after = [] 84 | drop_list = [] 85 | for i, v in notelist.iterrows(): 86 | if notelist.loc[i]['name'] not in after: 87 | after.append(notelist.loc[i]['name']) 88 | else: 89 | print(v['name']) 90 | drop_list.append(v['guid']) 91 | for i in drop_list: 92 | noteStore.deleteNote(token, i) 93 | --------------------------------------------------------------------------------