Algolia Crawler竟然申请过了，在vuepress配置Algolia搜索插件-THsInk

昨天搭建完文档网站，用的是内置搜索插件，但占用较高，睡觉前申请了Algolia Crawler，自认为申请条件不是完全符合，早上起来发现通过了?

直接配置爬虫

new Crawler({
  appId: "YOUR_APP_ID",
  apiKey: "YOUR_API_KEY",
  rateLimit: 8,
  startUrls: [
    // 这是 Algolia 开始抓取网站的初始地址
    // 如果你的网站被分为数个独立部分，你可能需要在此设置多个入口链接
    "https://YOUR_WEBSITE_URL/",
  ],
  sitemaps: [
    // 如果你在使用 Sitemap 插件 (如: vuepress-plugin-sitemap2)，你可以提供 Sitemap 链接
    "https://YOUR_WEBSITE_URL/sitemap.xml",
  ],
  ignoreCanonicalTo: false,
  exclusionPatterns: [
    // 你可以通过它阻止 Algolia 抓取某些 URL
  ],
  discoveryPatterns: [
    // 这是 Algolia 抓取 URL 的范围
    "https://YOUR_WEBSITE_URL/**",
  ],
  // 爬虫执行的计划时间，可根据文档更新频率设置
  schedule: "at 02:00 every 1 day",
  actions: [
    // 你可以拥有多个 action，特别是你在一个域名下部署多个文档时
    {
      // 使用适当的名称为索引命名
      indexName: "YOUR_INDEX_NAME",
      // 索引生效的路径
      pathsToMatch: ["https://YOUR_WEBSITE_URL/**"],
      // 控制 Algolia 如何抓取你的站点
      recordExtractor: ({ $, helpers }) => {
        // 以下是适用于 vuepress-theme-hope 的默认选项选项
        // vuepress-theme-hope 默认的容器类名为 theme-hope-content
        return helpers.docsearch({
          recordProps: {
            lvl0: {
              selectors: ".sidebar-heading.active",
              defaultValue: "Documentation",
            },
            lvl1: ".theme-hope-content h1",
            lvl2: ".theme-hope-content h2",
            lvl3: ".theme-hope-content h3",
            lvl4: ".theme-hope-content h4",
            lvl5: ".theme-hope-content h5",
            lvl6: ".theme-hope-content h6",
            content: ".theme-hope-content p, .theme-hope-content li",
          },
          indexHeadings: true,
        });
      },
    },
  ],
  initialIndexSettings: {
    // 控制索引如何被初始化，这仅当索引尚未生成时有效
    // 你可能需要在修改后手动删除并重新生成新的索引
    YOUR_INDEX_NAME: {
      attributesForFaceting: ["type", "lang"],
      attributesToRetrieve: ["hierarchy", "content", "anchor", "url"],
      attributesToHighlight: ["hierarchy", "hierarchy_camel", "content"],
      attributesToSnippet: ["content:10"],
      camelCaseAttributes: ["hierarchy", "hierarchy_radio", "content"],
      searchableAttributes: [
        "unordered(hierarchy_radio_camel.lvl0)",
        "unordered(hierarchy_radio.lvl0)",
        "unordered(hierarchy_radio_camel.lvl1)",
        "unordered(hierarchy_radio.lvl1)",
        "unordered(hierarchy_radio_camel.lvl2)",
        "unordered(hierarchy_radio.lvl2)",
        "unordered(hierarchy_radio_camel.lvl3)",
        "unordered(hierarchy_radio.lvl3)",
        "unordered(hierarchy_radio_camel.lvl4)",
        "unordered(hierarchy_radio.lvl4)",
        "unordered(hierarchy_radio_camel.lvl5)",
        "unordered(hierarchy_radio.lvl5)",
        "unordered(hierarchy_radio_camel.lvl6)",
        "unordered(hierarchy_radio.lvl6)",
        "unordered(hierarchy_camel.lvl0)",
        "unordered(hierarchy.lvl0)",
        "unordered(hierarchy_camel.lvl1)",
        "unordered(hierarchy.lvl1)",
        "unordered(hierarchy_camel.lvl2)",
        "unordered(hierarchy.lvl2)",
        "unordered(hierarchy_camel.lvl3)",
        "unordered(hierarchy.lvl3)",
        "unordered(hierarchy_camel.lvl4)",
        "unordered(hierarchy.lvl4)",
        "unordered(hierarchy_camel.lvl5)",
        "unordered(hierarchy.lvl5)",
        "unordered(hierarchy_camel.lvl6)",
        "unordered(hierarchy.lvl6)",
        "content",
      ],
      distinct: true,
      attributeForDistinct: "url",
      customRanking: [
        "desc(weight.pageRank)",
        "desc(weight.level)",
        "asc(weight.position)",
      ],
      ranking: [
        "words",
        "filters",
        "typo",
        "attribute",
        "proximity",
        "exact",
        "custom",
      ],
      highlightPreTag:
        '<span class="algolia-docsearch-suggestion--highlight">',
      highlightPostTag: "</span>",
      minWordSizefor1Typo: 3,
      minWordSizefor2Typos: 7,
      allowTyposOnNumericTokens: false,
      minProximity: 1,
      ignorePlurals: true,
      advancedSyntax: true,
      attributeCriteriaComputedByMinProximity: true,
      removeWordsIfNoResults: "allOptional",
    },
  },
});

再安装@vuepress/plugin-docsearch

pnmp

yarn

npm

pnpm add -D @vuepress/plugin-docsearch@next

yarn add -D @vuepress/plugin-docsearch@next

npm i -D @vuepress/plugin-docsearch@next

配置

// .vuepress/config.ts
import { docsearchPlugin } from "@vuepress/plugin-docsearch";
import { defineUserConfig } from "vuepress";

export default defineUserConfig({
  plugins: [
    docsearchPlugin({
      // 你的选项
      // appId, apiKey 和 indexName 是必填的，其中apikey区别于爬虫apikey，是发到邮件里的那个
    }),
  ],
});

汉化配置

// .vuepress/config.ts
import { defineUserConfig } from "vuepress";
import { docsearchPlugin } from "@vuepress/plugin-docsearch";

export default defineUserConfig({
  plugins: [
    docsearchPlugin({
      // ...

      locales: {
        "/zh/": {
          placeholder: "搜索文档",
          translations: {
            button: {
              buttonText: "搜索文档",
              buttonAriaLabel: "搜索文档",
            },
            modal: {
              searchBox: {
                resetButtonTitle: "清除查询条件",
                resetButtonAriaLabel: "清除查询条件",
                cancelButtonText: "取消",
                cancelButtonAriaLabel: "取消",
              },
              startScreen: {
                recentSearchesTitle: "搜索历史",
                noRecentSearchesText: "没有搜索历史",
                saveRecentSearchButtonTitle: "保存至搜索历史",
                removeRecentSearchButtonTitle: "从搜索历史中移除",
                favoriteSearchesTitle: "收藏",
                removeFavoriteSearchButtonTitle: "从收藏中移除",
              },
              errorScreen: {
                titleText: "无法获取结果",
                helpText: "你可能需要检查你的网络连接",
              },
              footer: {
                selectText: "选择",
                navigateText: "切换",
                closeText: "关闭",
                searchByText: "搜索提供者",
              },
              noResultsScreen: {
                noResultsText: "无法找到相关结果",
                suggestedQueryText: "你可以尝试查询",
                reportMissingResultsText: "你认为该查询应该有结果？",
                reportMissingResultsLinkText: "点击反馈",
              },
            },
          },
        },
      },
    }),
  ],
});

配置Algolia搜索插件本身没什么难度，记录踩过的两个坑：

1. 配置文件(.vuepress/config.ts)中的apikey区别于爬虫配置apikey，是发到邮件里的那个。填错会返回403错误。

2. 爬取页面有问题都可以看日志或提示解决。我的cdn拦截了Algolia爬虫，可以给爬虫ip加白 34.66.202.43

参考链接https://www.algolia.com/doc/tools/crawler/troubleshooting/faq/

–

ps. 至此我的文档网站搭建也彻底结束了?只是明天去云南玩一周，来不及好好休息两天了…

文章版权归作者所有，未经允许请勿转载。

THE END