如何定制化展示arxiv的论文

西西嘛呦

发布于 2022-12-25 10:51:47

3930

发布于 2022-12-25 10:51:47

文章被收录于专栏：数据分析与挖掘

进入到网址代码仓库：https://github.com/MLNLP-World/MyArxiv

新建完成后进入到自己创建的仓库。修改config.toml：

site_title = "MyArxiv"
limit_days = 7
cache_url = "https://taishan1994.github.io/MyArxiv/cache.json" # taishan1994为自己的名称 
[[sources]]
limit = 150  # 显示的文章数
category = "cs.CL"  # 这里是arxiv上的类别，还可以添加其它类，我这里主要针对自然语言处理
title = "Computation and Language"

[scripts]
highlight_title = "scripts/highlight_title.rhai"
highlight_author = "scripts/highlight_author.rhai"
highlight_conference = "scripts/highlight_conference.rhai"

修改scripts/config.rhai，这里面主要是一些高亮显示。

let titles_type = ["Dataset", "Survey", "Review", "Overview"];
let titles_model = ["BERT", "GPT", "Transformer","chinese","entity","relation"];  # 这里我加了实体、关系、中文
let titles_method = ["Pre-train", "Pretrain", "Prompt", "Self-Supervised"];
let titles =  titles_model + titles_method + titles_type;
let authors_array = ["Yann LeCun", "Geoffrey Hinton", "Yoshua Bengio"];

let conferences = [
    // AI
    "AAAI", "AAMAS", "ACM MM", "AISTATS", "ALT", "CEC", "ECAI", "FUZZ IEEE", "GECCO", "ICANN", "ICAPS", "ICCBR", "ICONIP", "ICRA", "ICTAI", "IJCAI", "IJCNN", "IROS", "KR", "KSEM", "SIGGRAPH", "STOC", "UAI", "PPSN", "PRICAI", "TAAI",
    // CV
    "3DV", "ACCV", "ACM MM", "BMVC", "CVPR", "ECCV", "ICCV", "ICDAR", "ICIP", "ICME", "ICPR", "IEEE VIS", "MICCAI", "SIGGRAPH", "WACV",
    // DM
    "AKBC", "APWeb", "CIKM", "DASFAA", "ECML-PKDD", "ICDE", "ICDM", "ICDT", "KDD", "LREC", "MDM", "PAKDD", "PODS", "RecSys", "SDM", "SIGMOD", "VLDB", "WSDM", "WWW", "EDBT", "CIDR",
    // IR
    "ECIR", "ESWC", "ICMR", "ICTIR", "ISWC", "SIGIR",
    // ML
    "ACML", "AISTATS", "ECML", "ICLR", "ICML", "ML4H", "NeurIPS", "NIPS", "UAI",
    // NLP
    "AACL", "ACL", "CCL", "COLING", "COLT", "CoNLL", "EACL", "EMNLP", "ICASSP", "ICDAR", "ICONIP", "INTERSPEECH", "LREC", "NAACL", "NLPCC", "RepL4NLP", "SIGDIAL", "SemEval", "WANLP", "WASSA", "WOAH",
    // Arch
    "ASPLOS", "ATC", "DATE", "EuroSys", "FAST", "HPCA", "ISCA", "MICRO", "PPoPP", "SC", "SoCC",
    // System
    "FSE/ESEC", "ICSE", "ISSTA", "OSDI", "SOSP",
    // Security
    "ACSA", "AsiaCCS", "CCS", "DSN", "ESORICS", "EuroS&P", "ICICS", "NDSS", "RAID", "SP", "USENIX Security"
];

let start = conferences.shift();
let conferences_rg = conferences.reduce(|sum, v| sum + "|" + v, start);
let conferences_rg = "(" + conferences_rg + ")([\\s'-]*\\d+)?";

let start = titles.shift();
let title_rg = titles.reduce(|sum, v| sum + "|" + v, start);

let start = authors_array.shift();
let authors_rg = authors_array.reduce(|sum, v| sum + "|" + v, start);

export title_rg;
export authors_rg;
export conferences_rg;

修改includes/index.hbs：

<!DOCTYPE html>
<html lang="en">

<head>
    <title>{{site_title}}</title>
    <meta charset="utf-8"/>
    <meta http-equiv="X-UA-Compatible" content="IE=edge"/>
    <meta name="robots" content="noindex, nofollow"/>
    <meta name="viewport" content="width=device-width, initial-scale=1"/>
    <link rel="shortcut icon" type="image/x-icon" href="favicon.ico"/>
    <link href="index.css" rel="stylesheet"/>
    <link href="https://cdn.jsdelivr.net/npm/remixicon@2.5.0/fonts/remixicon.css" rel="stylesheet">
    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.15.1/dist/katex.min.css"
          integrity="sha384-R4558gYOUz8mP9YWpZJjofhk+zx0AS11p36HnD2ZKj/6JR5z27gSSULCNHIRReVs" crossorigin="anonymous">
    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.15.1/dist/katex.min.css"
          integrity="sha384-R4558gYOUz8mP9YWpZJjofhk+zx0AS11p36HnD2ZKj/6JR5z27gSSULCNHIRReVs" crossorigin="anonymous">
    <script defer src="https://cdn.jsdelivr.net/npm/katex@0.15.1/dist/katex.min.js"
            integrity="sha384-z1fJDqw8ZApjGO3/unPWUPsIymfsJmyrDVWC8Tv/a1HeOtGmkwNd/7xUS0Xcnvsx"
            crossorigin="anonymous"></script>
    <script defer src="https://cdn.jsdelivr.net/npm/katex@0.15.1/dist/contrib/auto-render.min.js"
            integrity="sha384-+XBljXPPiv+OzfbB3cVmLHf4hdUFHlWNZN5spNQ7rmHTXpd7WvJum6fIACpNNfIR"
            crossorigin="anonymous"></script>
    <script>
        document.addEventListener("DOMContentLoaded", function () {
            renderMathInElement(document.body, {
                // customised options
                // • auto-render specific keys, e.g.:
                delimiters: [
                    {left: '$$', right: '$$', display: true},
                    {left: '$', right: '$', display: false},
                    {left: '\\(', right: '\\)', display: false},
                    {left: '\\[', right: '\\]', display: true},
                    {left: "\\begin{equation}", right: "\\end{equation}", display: true},
                    {left: "\\begin{align}", right: "\\end{align}", display: true},
                    {left: "\\begin{alignat}", right: "\\end{alignat}", display: true},
                    {left: "\\begin{gather}", right: "\\end{gather}", display: true},
                    {left: "\\begin{CD}", right: "\\end{CD}", display: true},
                ],
                // • rendering keys, e.g.:
                throwOnError: false
            });
        });
    </script>
</head>

<body>
<section class="header-container">
    <div style="display:flex; justify-content:space-between; align-items:flex-end;">
        <div>
            {{!-- <a href="https://github.com/MLNLP-World/MyArxiv" style="text-decoration: none;">
                <div class="header-title">
                    <span class="header-title-preffix">MLNLP</span>//MyArxiv
                </div>
            </a> --}}
            <div class="header-title">
                xiximayou-arxiv //我主要修改了这里，自定义名称
            </div>
        </div>

        <div class=icons>
            <label class="theme-switch" for="checkbox">
                <input type="checkbox" id="checkbox"/>
                <i id="theme-icon" class="ri-moon-line" style="font-size: 32px" rel="noopener noreferrer"></i>
            </label>
        </div>
    </div>
</section>

{{#each days}}
    <section class="day-container">
        <div class="date">
            <time datetime="{{datetime}}">{{time_format datetime "%F"}}</time>
        </div>
        {{#each subjects}}
            <article>
                <details>
                    <Summary>
                        {{ subject }}
                    </Summary>
                    <div class="details-content">
                        {{#each papers}}
                            <article>
                                <details class="article-expander">
                                    <summary class="article-expander-title">
                                        {{#if (ne updated published)}}♻{{/if}} {{highlight_title title authors}} {{highlight_conference comment}}
                                    </summary>
                                    <div class="article-authors">
                                        <a href="{{id}}">
                                            <i class="ri-links-line"></i>
                                        </a>
                                        <a href="{{pdf_url}}">
                                            <i class="ri-file-paper-2-line"></i>
                                        </a>
                                        {{highlight_author authors}}
                                    </div>
                                    <div class="article-summary-box-inner">
                                        <span>{{summary}}</span>
                                    </div>
                                    {{#if comment}}
                                        <div class="article-summary-box-inner">
                                            <span class="chip">comment</span>: <span>{{comment}}</span>
                                        </div>
                                    {{/if}}
                                </details>
                            </article>
                        {{/each}}
                    </div>
                </details>
            </article>
        {{/each}}
    </section>
{{/each}}

</body>

<footer>
    <div>
        <time id="build-timestamp" datetime="{{build_time}}">
            {{!-- <a href="https://github.com/MLNLP-World/MyArxiv/actions">
                <img id="build-timestamp-badge"
                     src="https://img.shields.io/github/workflow/status/mlnlp-world/myarxiv/Update?label={{time_format
                    build_time "%F %T %Z"}}&style=for-the-badge"
                alt="{{time_format build_time "%F %T %Z"}}">
            </a> --}}
            {{time_format build_time "%F %T %Z"}}
        </time>
    </div>
</footer>
<script src="index.js"></script>
</html>

可以选择修改workflows/update-feed.yml里面的定时，什么时候更新。