基于Cloudflare Workers 免费加速GitHub文件下载

laiczhang
laiczhang
laiczhang
106
文章
0
评论
2020年4月1日14:35:49 评论 88 6227字阅读20分45秒

对于Cloudflare Workers,不了解的同学可以参考基于Cloudflare Workers 免费搭建维基百科镜像

这次我们使用cf来加速GitHub文件的下载,提速不会太多(当然比不上导入gitee再下载的速度),但是胜在方便。

演示站

https://gh.api.99988866.xyz/
https://gh2.laic.workers.dev/
https://shrill-pond-3e81.hunsh.workers.dev/

创建workers

登录账号后,创建workers

复制 index.js 或 index2.js 到左侧代码框,Save and deploy。如果正常,右侧应显示首页。

index.js的clone走github.com.cnpmjs.org,index2.js的clone走你的cf worker,请自行选择

index.js

'use strict'

/**
 * static files (404.html, sw.js, conf.js)
 */
const ASSET_URL = 'https://hunshcn.github.io/gh-proxy'

/** @type {RequestInit} */
const PREFLIGHT_INIT = {
    status: 204,
    headers: new Headers({
        'access-control-allow-origin': '*',
        'access-control-allow-methods': 'GET,POST,PUT,PATCH,TRACE,DELETE,HEAD,OPTIONS',
        'access-control-max-age': '1728000',
    }),
}

/**
 * @param {any} body
 * @param {number} status
 * @param {Object<string, string>} headers
 */
function makeRes(body, status = 200, headers = {}) {
    headers['access-control-allow-origin'] = '*'
    return new Response(body, {status, headers})
}


/**
 * @param {string} urlStr
 */
function newUrl(urlStr) {
    try {
        return new URL(urlStr)
    } catch (err) {
        return null
    }
}


addEventListener('fetch', e => {
    const ret = fetchHandler(e)
        .catch(err => makeRes('cfworker error:\n' + err.stack, 502))
    e.respondWith(ret)
})


/**
 * @param {FetchEvent} e
 */
async function fetchHandler(e) {
    const req = e.request
    const urlStr = req.url
    const urlObj = new URL(urlStr)
    let path = urlObj.searchParams.get('q')
    if(path)
    {
        return Response.redirect('https://' + urlObj.host + '/' + path, 301)
    }
    // cfworker 会把路径中的 `//` 合并成 `/`
    path = urlObj.href.substr(urlObj.origin.length + 1).replace(/^https?:\/+/, 'https://')
    const exp = /^(?:https?:\/\/)?github\.com\/.+?\/.+?\/(?:releases|archive)\/.*$/
    const exp2 = /^(?:https?:\/\/)?github\.com\/.+?\/.+?\/(?:blob)\/.*$/
    const exp3 = /^(?:https?:\/\/)?github\.com\/.+?\/.+?\/(?:info|git-upload-pack).*$/
    if (path.search(exp)===0) {
        return httpHandler(req, path)
    }else if(path.search(exp2)===0) {
        const newUrl = path.replace('/blob/', '@').replace(/^(?:https?:\/\/)?github\.com/, 'https://cdn.jsdelivr.net/gh')
        return Response.redirect(newUrl, 302)
    }else if (path.search(exp3)===0){
        const newUrl = path.replace(/^(?:https?:\/\/)?github\.com/, 'https://github.com.cnpmjs.org')
        return Response.redirect(newUrl, 302)
    } else {
        return fetch(ASSET_URL + path)
    }
}


/**
 * @param {Request} req
 * @param {string} pathname
 */
function httpHandler(req, pathname) {
    const reqHdrRaw = req.headers

    // preflight
    if (req.method === 'OPTIONS' &&
        reqHdrRaw.has('access-control-request-headers')
    ) {
        return new Response(null, PREFLIGHT_INIT)
    }

    let rawLen = ''

    const reqHdrNew = new Headers(reqHdrRaw)

    const refer = reqHdrNew.get('referer')

    let urlStr = pathname
    if (urlStr.startsWith('github')) {
        urlStr = 'https://' + urlStr
    }
    const urlObj = newUrl(urlStr)

    /** @type {RequestInit} */
    const reqInit = {
        method: req.method,
        headers: reqHdrNew,
        redirect: 'follow',
        body: req.body
    }
    return proxy(urlObj, reqInit, rawLen, 0)
}


/**
 *
 * @param {URL} urlObj
 * @param {RequestInit} reqInit
 */
async function proxy(urlObj, reqInit, rawLen) {
    const res = await fetch(urlObj.href, reqInit)
    const resHdrOld = res.headers
    const resHdrNew = new Headers(resHdrOld)

    // verify
    if (rawLen) {
        const newLen = resHdrOld.get('content-length') || ''
        const badLen = (rawLen !== newLen)

        if (badLen) {
            return makeRes(res.body, 400, {
                '--error': `bad len: ${newLen}, except: ${rawLen}`,
                'access-control-expose-headers': '--error',
            })
        }
    }
    const status = res.status
    resHdrNew.set('access-control-expose-headers', '*')
    resHdrNew.set('access-control-allow-origin', '*')

    resHdrNew.delete('content-security-policy')
    resHdrNew.delete('content-security-policy-report-only')
    resHdrNew.delete('clear-site-data')

    return new Response(res.body, {
        status,
        headers: resHdrNew,
    })
}

index2.js

'use strict'

/**
 * static files (404.html, sw.js, conf.js)
 */
const ASSET_URL = 'https://hunshcn.github.io/gh-proxy'

/** @type {RequestInit} */
const PREFLIGHT_INIT = {
    status: 204,
    headers: new Headers({
        'access-control-allow-origin': '*',
        'access-control-allow-methods': 'GET,POST,PUT,PATCH,TRACE,DELETE,HEAD,OPTIONS',
        'access-control-max-age': '1728000',
    }),
}

/**
 * @param {any} body
 * @param {number} status
 * @param {Object<string, string>} headers
 */
function makeRes(body, status = 200, headers = {}) {
    headers['access-control-allow-origin'] = '*'
    return new Response(body, {status, headers})
}


/**
 * @param {string} urlStr
 */
function newUrl(urlStr) {
    try {
        return new URL(urlStr)
    } catch (err) {
        return null
    }
}


addEventListener('fetch', e => {
    const ret = fetchHandler(e)
        .catch(err => makeRes('cfworker error:\n' + err.stack, 502))
    e.respondWith(ret)
})


/**
 * @param {FetchEvent} e
 */
async function fetchHandler(e) {
    const req = e.request
    const urlStr = req.url
    const urlObj = new URL(urlStr)
    let path = urlObj.searchParams.get('q')
    if(path)
    {
        return Response.redirect('https://' + urlObj.host + '/' + path, 301)
    }
    // cfworker 会把路径中的 `//` 合并成 `/`
    path = urlObj.href.substr(urlObj.origin.length + 1).replace(/^https?:\/+/, 'https://')
    const exp = /^(?:https?:\/\/)?github\.com\/.+?\/.+?\/(?:releases|archive|info|git-upload-pack).*$/
    const exp2 = /^(?:https?:\/\/)?github\.com\/.+?\/.+?\/(?:blob)\/.*$/
    if (path.search(exp)===0) {
        return httpHandler(req, path)
    }else if(path.search(exp2)===0){
        const newUrl = path.replace('/blob/', '@').replace(/^(?:https?:\/\/)?github\.com/, 'https://cdn.jsdelivr.net/gh')
        return Response.redirect(newUrl, 302)
    } else {
        return fetch(ASSET_URL + path)
    }
}


/**
 * @param {Request} req
 * @param {string} pathname
 */
function httpHandler(req, pathname) {
    const reqHdrRaw = req.headers

    // preflight
    if (req.method === 'OPTIONS' &&
        reqHdrRaw.has('access-control-request-headers')
    ) {
        return new Response(null, PREFLIGHT_INIT)
    }

    let rawLen = ''

    const reqHdrNew = new Headers(reqHdrRaw)

    const refer = reqHdrNew.get('referer')

    let urlStr = pathname
    if (urlStr.startsWith('github')) {
        urlStr = 'https://' + urlStr
    }
    const urlObj = newUrl(urlStr)

    /** @type {RequestInit} */
    const reqInit = {
        method: req.method,
        headers: reqHdrNew,
        redirect: 'follow',
        body: req.body
    }
    return proxy(urlObj, reqInit, rawLen, 0)
}


/**
 *
 * @param {URL} urlObj
 * @param {RequestInit} reqInit
 */
async function proxy(urlObj, reqInit, rawLen) {
    const res = await fetch(urlObj.href, reqInit)
    const resHdrOld = res.headers
    const resHdrNew = new Headers(resHdrOld)

    // verify
    if (rawLen) {
        const newLen = resHdrOld.get('content-length') || ''
        const badLen = (rawLen !== newLen)

        if (badLen) {
            return makeRes(res.body, 400, {
                '--error': `bad len: ${newLen}, except: ${rawLen}`,
                'access-control-expose-headers': '--error',
            })
        }
    }
    const status = res.status
    resHdrNew.set('access-control-expose-headers', '*')
    resHdrNew.set('access-control-allow-origin', '*')

    resHdrNew.delete('content-security-policy')
    resHdrNew.delete('content-security-policy-report-only')
    resHdrNew.delete('clear-site-data')

    return new Response(res.body, {
        status,
        headers: resHdrNew,
    })
}

参考

https://hunsh.net/archives/23/

继续阅读
laiczhang
国内加速访问GitHub的几种方法 技术杂谈

国内加速访问GitHub的几种方法

众所周知,由于某些原因,国内访问Github会异常缓慢,在clone仓库时甚至只有10k以下的速度,下载半天有时还会失败需要从头再来,甚是让人恼火。 本文总结几种加速访问GitHub的方法。 1. 修...