├── README.md ├── LICENSE ├── .gitignore └── flomo-export.py /README.md: -------------------------------------------------------------------------------- 1 | # data-export 2 | flomo export to markdown for obsidian/logseq; 3 | 4 | ## 用法 5 | - step1，使用 `python 3.6+` 6 | - step2, 安装需要的包，`pip install beautifulsoup4` 7 | - step3，运行命令 `python flomo-export.py` 8 | - 参数： 9 | - `--input` ， 从 flomo 中导出的 html文件位置，放到和flomo 同目录可忽略 10 | - `--out` ，最终生成的 markdown 路径。 11 | 12 | 13 | 更多内容可见：[让 flomo 更好用](https://bbruceyuan.com/post/make-flomo-better.html/) 14 | 15 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2023 Chaofa Yuan 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /.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 | -------------------------------------------------------------------------------- /flomo-export.py: -------------------------------------------------------------------------------- 1 | """ 2 | Author: bbruceyuan 3 | Time: 2023/2/8 4 | 5 | 导出 flomo 的数据, 6 | 把从官网导出的 flomo 数据，导出成数据，共其他的 app 使用，比如 obsidian, typora, logseq, 7 | """ 8 | import argparse 9 | import pathlib 10 | import re 11 | from dataclasses import dataclass 12 | from typing import List, Optional, Tuple, Any 13 | 14 | import bs4 15 | from bs4 import BeautifulSoup 16 | 17 | 18 | @dataclass 19 | class Memo: 20 | """ memo 规则 21 | content: 正文内容 22 | - 普通的 p 标签 23 | - 加粗标签； 需要替换成 ****， 现在 parser 之前就 替换了；还有 B 标签 24 | - 有序列表 25 | - 无序列表； 26 | 目前暂时不支持嵌套 （因为 flomo 不支持） 27 | """ 28 | create_time: str 29 | content: str = "" 30 | file_list: Optional[List[str]] = None 31 | tag_list: Optional[List[str]] = None 32 | 33 | def __lt__(self, other): 34 | return self.create_time < other.create_time 35 | 36 | 37 | def parse_file(file_path: pathlib.Path) -> List[Memo]: 38 | """ 39 | html 格式： 40 | 所有的日志放在
中 41 | 每一条日志是一个
42 | 43 | example: 44 |
45 |
2021-03-29 18:07:06
46 |
47 |

test

这东西还是挺有意思的

48 |
49 |
50 |
51 | 52 | """ 53 | with open(file_path, 'r', encoding='utf-8') as f: 54 | file_content = f.read() 55 | # 提前替换 b 标签 56 | file_content = re.sub(r"(.+?)", 57 | __bold_to_md_type, file_content, re.DOTALL) 58 | file_content = re.sub(r"(.+?)", 59 | __bold_to_md_type, file_content, re.DOTALL) 60 | # todo: 除了

标签之外，还有 li/ui 标签需要考虑如何嵌套；这里也是建议 先用 markdown 语法替换； 61 | # 如果是导入到 标准的 markdown 中，比如 obsidian, 还可以把 li 之类的东西加上。 62 | 63 | tree = BeautifulSoup(file_content, 'html.parser') 64 | 65 | one_file_memos = [] 66 | for item in tree.find_all("div", class_="memo"): 67 | # 把文件中的 所有 memo 都 parse 了； 68 | one_memo = _parse_one_memo(item) 69 | one_file_memos.append(one_memo) 70 | 71 | return one_file_memos 72 | 73 | 74 | def __bold_to_md_type(match_obj): 75 | return "**{}**".format(match_obj.group(1)) 76 | 77 | 78 | def _parse_one_memo(item) -> Memo: 79 | ret = {} 80 | time_item = item.find("div", class_="time") 81 | # 所有的 content 都在这一步 82 | content_parent = item.find("div", class_="content") 83 | 84 | raw_contents: List[bs4.element.NavigableString] = content_parent.contents 85 | # 得到 content 和 tag_list 86 | clearn_markdown_content, tag_list = _memo_content_clean(raw_contents) 87 | ret.update({ 88 | "content": clearn_markdown_content, 89 | "tag_list": tag_list 90 | }) 91 | 92 | # todo: 这里仅仅是找到 image list, 可能有人需要支持语音，因为我没有图片，所以我实际上也没有导出图片 93 | file_items = item.find_all("img") 94 | if len(file_items) != 0: 95 | image_srcs_list = [ 96 | file_item["src"] for file_item in file_items 97 | ] 98 | ret.update({ 99 | "file_list": image_srcs_list 100 | }) 101 | 102 | ret.update({ 103 | "create_time": time_item.getText() 104 | }) 105 | memo = Memo(**ret) 106 | return memo 107 | 108 | 109 | def _memo_content_clean(content_elements: List[bs4.element.NavigableString]) -> Tuple[str, List[str]]: 110 | """ 111 | 如果是无序列表，那么等就是把 ol 换成 ul 112 |

    113 |
  1. 114 |

    数据增强的方式，同义词替换。同标签词替换？需要考虑

    115 |
    2. 116 |
  2. 117 |

    context representation 的表示。

    118 |
    3. 119 |
120 | 121 | """ 122 | tag_list = [] 123 | markdown_ret = [] 124 | for item in content_elements: 125 | tag_list_tmp, markdown_without_tag = _extract_tag_from_content(item) 126 | tag_list.extend(tag_list_tmp) 127 | if markdown_without_tag: 128 | markdown_ret.append(markdown_without_tag) 129 | 130 | return "\n\n".join(markdown_ret), tag_list 131 | 132 | 133 | def _extract_tag_from_content(content_: Any) -> Tuple[List[str], str]: 134 | def _extract_tag_from_str(content: str) -> Tuple[List[str], str]: 135 | # TAG 在 logseq 和 obsidian 是不一样的。 136 | if not content: 137 | return [], content 138 | else: 139 | tag_list = re.findall(r'(#.+?\s+?)', content, re.DOTALL) 140 | tag_list = list(map(lambda x: x.strip(), tag_list)) 141 | 142 | content = re.sub(r'(#.+?\s+?)', "", content, re.DOTALL).strip() 143 | 144 | # 特殊的 TAG, 假设这一行只有 TAG, 那么上面的规则不可靠 145 | match_obj = re.match(r"^(#.+?)$", content.strip()) 146 | if match_obj and not re.search(r"\s", content): 147 | tag_list.append(match_obj.group(1)) 148 | content = re.sub(r"^(#.+?)$", "", content, re.DOTALL).strip() 149 | 150 | return list(set(tag_list)), content 151 | # _extract_tag_from_str() function end 152 | 153 | ret_tag_list = [] 154 | ret_content = [] 155 | for one_item_element in content_.stripped_strings: 156 | ret_tag_list_tmp, ret_tmp = _extract_tag_from_str(one_item_element) 157 | ret_tag_list.extend(ret_tag_list_tmp) 158 | ret_content.append(ret_tmp) 159 | return list(set(ret_tag_list)), "\n".join(ret_content) 160 | 161 | 162 | def write_memo_as_md(memos: List[Memo], file_path: Optional[pathlib.Path] = None) -> None: 163 | def _memo_to_md(one_memo: Memo) -> str: 164 | ret = "- {}".format(one_memo.create_time) 165 | if one_memo.tag_list: 166 | ret += " , {}".format(" ".join(one_memo.tag_list)) 167 | ret += "\n\n" 168 | contents = one_memo.content.split("\n") 169 | for one_line in contents: 170 | if one_line: 171 | ret += "\t" + one_line + '\n\n' 172 | 173 | if one_memo.file_list: 174 | print(one_memo.file_list) 175 | for file in one_memo.file_list: 176 | ret += "\n\n" 177 | ret += f"![{file}]({file})" 178 | 179 | # 如果是导入到 logseq 中，使用下面的三行 180 | # ret += "\t- " + one_memo.content 181 | ret += "\n\n" 182 | return ret 183 | 184 | memos = sorted(memos) 185 | with file_path.open('w', encoding='utf-8') as f: 186 | for memo in memos: 187 | tmp = _memo_to_md(memo) 188 | f.write(tmp) 189 | 190 | 191 | def get_args(): 192 | parser = argparse.ArgumentParser() 193 | parser.add_argument("--out", default="flomo_export.md", 194 | help="输出路径") 195 | parser.add_argument("--input", default=".", 196 | help="输入的文件位置，默认是当前路径") 197 | args = parser.parse_args() 198 | return args 199 | 200 | 201 | def main(): 202 | args = get_args() 203 | cur_path = pathlib.Path(args.input) 204 | html_files = cur_path.glob("**/*.html") 205 | memos = [] 206 | for file in html_files: 207 | memos.extend(parse_file(file)) 208 | write_memo_as_md(memos, pathlib.Path(args.out)) 209 | 210 | 211 | if __name__ == '__main__': 212 | main() 213 | --------------------------------------------------------------------------------