{"id":13644379,"url":"https://github.com/jesselau76/ebook-gpt-translator","last_synced_at":"2025-05-15T18:11:32.935Z","repository":{"id":133612922,"uuid":"611622512","full_name":"jesselau76/ebook-GPT-translator","owner":"jesselau76","description":"Enjoy reading with your favorite style.","archived":false,"fork":false,"pushed_at":"2024-01-19T08:18:54.000Z","size":653,"stargazers_count":1666,"open_issues_count":45,"forks_count":210,"subscribers_count":11,"default_branch":"main","last_synced_at":"2025-03-31T22:21:43.420Z","etag":null,"topics":["docx","epub","mobi","pdf","python","translation","translator"],"latest_commit_sha":null,"homepage":"https://jesselau.com","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jesselau76.png","metadata":{"files":{"readme":"README-zh.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2023-03-09T07:51:06.000Z","updated_at":"2025-03-25T15:02:15.000Z","dependencies_parsed_at":null,"dependency_job_id":"21c3a6b2-d340-48f1-aea8-98b5ba1fcfcb","html_url":"https://github.com/jesselau76/ebook-GPT-translator","commit_stats":null,"previous_names":["jesselau76/pdf-epub-gpt-translator"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jesselau76%2Febook-GPT-translator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jesselau76%2Febook-GPT-translator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jesselau76%2Febook-GPT-translator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jesselau76%2Febook-GPT-translator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jesselau76","download_url":"https://codeload.github.com/jesselau76/ebook-GPT-translator/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247744335,"owners_count":20988783,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["docx","epub","mobi","pdf","python","translation","translator"],"created_at":"2024-08-02T01:02:02.225Z","updated_at":"2025-04-07T23:10:42.855Z","avatar_url":"https://github.com/jesselau76.png","language":"Python","funding_links":[],"categories":["NLP"],"sub_categories":[],"readme":"# ebook-GPT-Translator: : Enjoy reading with your favorite style.\n\n[En](https://github.com/jesselau76/ebook-GPT-translator/blob/main/README.md) | [中文说明](https://github.com/jesselau76/ebook-GPT-translator/blob/main/README-zh.md)\n\n该工具旨在帮助用户将文本从一种格式转换为另一种格式，以及使用 OpenAI API (model=`gpt-3.5-turbo`) 将其翻译成另一种语言。 目前支持PDF、DOCX、MOBI和EPUB文件格式转换翻译成EPUB文件及文本文件，可以将文字翻译成多种语言。\n\n注：\n- PDF、DOCX及MOBI文件只处理其中文本部分，图形部分不会出现在结果文件中。\n- EPUB文件的图形部分全部放在每章之初，因EPUB文件为HTML语言格式，若保持原有格式需要大量拆分文字，以多段文字一并翻译保持翻译水准为原则，故图形部分不保持在原有位置，而全部放在每章最初。\n- 初始页面、最终页面设置仅支持PDF文件。因EPUB、DOCX、MOBI及TXT文件等因字体大小，页面大小会有不同，无法处理页码。\n\n\n你需要申请OpenAI API KEY,[申请地址](https://platform.openai.com/)，现有免费使用额度，3个月有效。\n\n## 安装\n\n要使用此工具，您需要在系统上安装 Python 3 以及以下软件包：\n\n- pdfminer\n- openai\n- tqdm\n- ebooklib\n- bs4\n- docx\n- mobi\n\n您可以通过运行以下命令来安装这些软件包：\n```\npip install -r requirements.txt\n```\n\ngit clone本git\n\n```\ngit clone https://github.com/jesselau76/ebook-GPT-translator.git\n```\n升级到新版\n```\ncd ebook-GPT-translator\ngit pull\npip install -r requirements.txt\n```\n## 用法\n\n使用前将settings.cfg.example改名为settings.cfg并用任何一款编辑器编辑.\n```\ncd ebook-GPT-translator\nmv settings.cfg.example settings.cfg\nnano settings.cfg\n```\n打开settings.cfg文件后\n```\nopenai-apikey = sk-xxxxxxx\n```\n\n将sk-xxxxxxx替换为你的OpenAI api key (或者是 sk-xxxxxxx,sk-xxxxxxx 配置多个key)\n修改其他选项，然后退出保存\n\n如果需要先测试prompt,可以加--test参数只翻译前三段短文字。\n运行命令：\n\n```\npython text_translation.py [-h] [--test] filename\n\npositional arguments:\n  filename    Name of the input file\n\noptions:\n  -h, --help  show this help message and exit\n  --test      Only translate the first 3 short texts\n  --tlist     Use the translated name table\n```\n\n运行`text_translation.py`脚本，将要翻译或转换的文件作为参数。 例如，要翻译名为`example.pdf`的 PDF 文件，您可以运行以下命令：\n\n```\npython text_translation.py example.pdf\n```\n或者要翻译名为 `example.epub` 的 epub 文件，您可以运行以下命令：\n```\npython text_translation.py example.epub\n```\n\n或者要翻译名为 `example.docx` 的 docx 文件，您可以运行以下命令：\n```\npython text_translation.py example.docx\n```\n\n或者要翻译名为 `example.mobi` 的 mobi 文件，您可以运行以下命令：\n\n```\npython text_translation.py example.mobi\n```\n或者要翻译名为 `example.txt` 的 text 文件，您可以运行以下命令：\n```\npython text_translation.py example.txt\n```\n默认情况下，脚本会尝试将文本翻译成在 `target-language` 选项下的 `settings.cfg` 文件中指定的语言。 您还可以通过将`bilingual-output`选项设置为`True`来选择输出文本的双语版本。\n\n## 特点\n- 代码从 settings.cfg 文件中读取 OpenAI API 密钥、目标语言和其他选项。\n- 该代码可以在配置文件中设置OpenAI API 代理。\n- 该代码分别使用 pdfminer 和 ebooklib 库将 PDF、DOCX 和 EPUB 文件转换为文本。\n- 该代码提供了一个选项来输出双语文本。\n- 代码提供了一个进度条来显示PDF/EPUB到文本转换和翻译的进度\n- 测试功能，只翻译前三页以节省API用量。\n- 译名表功能，如果有翻译的译名表，可在翻译前预先替换，让结果更为准确。\n## 配置\n\n`settings.cfg` 文件包含几个可用于配置脚本行为的选项：\n\n- `openai-apikey`：您的 OpenAI API 的API Key\n- `openai-proxy`：OpenAI API 代理，如 `https://api.openai-proxy.com`，你可以在 [OpenAI API 代理](https://www.openai-proxy.com/) 看到一些用法与说明，如果你担心自己的API Key安全问题，可以查看 [Ice-Hazymoon/openai-scf-proxy](https://github.com/Ice-Hazymoon/openai-scf-proxy) 等反向代理API的项目自行搭建。\n- `prompt`: 你可以更改缺省的Chinese到\"en\", \"zh-cn\", \"ja\", \"繁体中文\",\"文言文\", or \"红楼梦风格的半文言文\" etc，或用你常用的prompt定制。\n![文言文](https://user-images.githubusercontent.com/40444824/223943798-4faf91a0-05ec-4a4e-9731-ba80bc9845c2.png)\n\n- `bilingual-output`：是否输出文本的双语版本。\n- `langcode`：输出 epub 文件的语言代码（例如 `ja` 表示日语，`zh` 表示中文等）。\n- `startpage`: 从指定的起始页码开始翻译，且仅适用于PDF文件。\n- `endpage`: 翻译将持续到PDF文件中指定的页码。此功能仅支持PDF文件。如果输入等于-1，则翻译将继续到文件结束。\n- `transliteration-list`: 译名表文件路径，格式参考示例xlsx文件 `transliteration-list-example.xlsx`。![](https://raw.githubusercontent.com/kagangtuya-star/picgo1/88f82ade7323ad23106cacb8d6fac1a4fe2fe9c3/Snipaste_2023-04-23_17-53-18.png)\n- `case-matching`: 使用译名表替换时是否开启大小写匹配。\n\n## 输出\n\n\n脚本的输出将是一个与输入文件同名的 EPUB 文件，但在末尾附加了`_translated`。 例如，如果输入文件是`example.pdf`，输出文件将是`example_translated.epub` 与`example_translated.txt`。\n\n## 版权\n\n这个工具是在 MIT 许可证下发布的。\n\n## 免责声明：\n\n本项目仅适用于已进入公共领域的书籍和资料。它不适用于受版权保护的内容。在使用本项目之前，我们强烈建议用户仔细查阅版权信息，并遵守相关法律法规，以保护自己和他人的权益。\n\n对于因使用本项目而造成的任何损失或损害，本项目的作者和开发者概不负责。用户需承担与本项目使用相关的所有风险。在使用本项目之前，用户有责任确保已获得原版权持有者的许可，或使用开源 PDF、EPUB 或 MOBI 文件，以避免潜在的版权风险。\n\n如果您对本项目的使用有任何疑虑或建议，请通过问题（issues）部分与我们联系。\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjesselau76%2Febook-gpt-translator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjesselau76%2Febook-gpt-translator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjesselau76%2Febook-gpt-translator/lists"}