Merge pull request #2121 from iptv-org/patch-2023.07.2

Patch 2023.07.2

Jenkinsfile

@@ -1,63 +0,0 @@
-List target_sites = (env.TARGET_SITES == null) ? [] : env.TARGET_SITES.split(';')
-List exclude_sites = (env.EXCLUDE_SITES == null) ? [] : env.EXCLUDE_SITES.split(';')
-
-target_sites.removeAll { it in exclude_sites }
-
-Map matrix_axes = [
-  SITE: target_sites
-]
-
-@NonCPS
-List getMatrixAxes(Map matrix_axes) {
-  List axes = []
-  matrix_axes.each { axis, values ->
-    List axisList = []
-    values.each { value ->
-      axisList << [(axis): value]
-    }
-    axes << axisList
-  }
-  axes.combinations()*.sum()
-}
-
-List axes = getMatrixAxes(matrix_axes)
-
-Map tasks = [failFast: false]
-
-for(int i = 0; i < axes.size(); i++) {
-  Map axis = axes[i]
-  List axisEnv = axis.collect { k, v ->
-      "${k}=${v}"
-  }
-  tasks[axisEnv.join(', ')] = { ->
-    env.NODEJS_HOME = "${tool 'node'}"
-    env.PATH="${env.NODEJS_HOME}/bin:${env.PATH}"
-
-    node {
-      skipDefaultCheckout()
-      withEnv(axisEnv) {
-        try {
-          cleanWs()
-          checkout scm
-          sh 'npm install'
-          sh "npm run grab"
-        } finally {
-          archiveArtifacts artifacts: "guides/**/*.xml", onlyIfSuccessful: true
-          cleanWs(
-            cleanWhenNotBuilt: false,
-            deleteDirs: true,
-            disableDeferredWipeout: true,
-            notFailBuild: true,
-            patterns: [[pattern: '.gitignore', type: 'INCLUDE'],
-                       [pattern: '.propsfile', type: 'EXCLUDE']])
-        }
-      }
-    }
-  }
-}
-
-node {
-  stage('Load') {
-    parallel(tasks)
-  }
-}

README.md

@@ -42,19 +42,34 @@ npm install
 Now choose one of the sources (their complete list can be found in the [/sites](https://github.com/iptv-org/epg/tree/master/sites) folder) and start downloading the guide using the command:
 
 ```sh
-# Windows
-set SITE=example.com&& npm run grab
+npm run grab -- --site=example.com
+```
 
-# Linux/macOS
-SITE=example.com npm run grab
+To download a guide in a specific language pass its [ISO 639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) code to the `--lang` argument:
+
+```sh
+npm run grab -- --site=example.com --lang=fr
+```
+
+To also create a compressed version of the guide, add the `--gzip` flag:
+
+```sh
+npm run grab -- --site=example.com --gzip
 ```
 
 After the download is completed in the current directory will appear a new folder `guides`, which will store all XML files:
 
 ```sh
 guides
-└── en
+└── fr
     └── example.com.xml
+    └── example.com.xml.gz
+```
+
+If you want to download the guide automatically on a schedule, you need to pass a valid [cron expression](https://crontab.guru/) to the script using the `--cron` attribute:
+
+```sh
+npm run grab -- --site=example.com --cron="0 0 * * *"
 ```
 
 Also you can make these guides available via URL by running your own server:
@@ -66,13 +81,13 @@ npm run serve
 After that all the downloaded guides will be available at a link like this:
 
 ```
-http://localhost:3000/guides/en/example.com.xml
+http://localhost:3000/guides/fr/example.com.xml
 ```
 
 In addition, they will be available on your local network at:
 
 ```
-http://<your_local_ip_address>:3000/guides/en/example.com.xml
+http://<your_local_ip_address>:3000/guides/fr/example.com.xml
 ```
 
 ## Playlists

package.json

@@ -11,7 +11,7 @@
     "test:commands": "npx jest --runInBand -- commands",
     "test:sites": "TZ=Pacific/Nauru npx jest --runInBand -- sites",
     "check": "npm run api:load && npm run channels:lint sites/**/*.js && npm run channels:validate sites/**/*.xml",
-    "grab": "cross-var epg-grabber --config=sites/$SITE/$SITE.config.js --channels=sites/$SITE/$SITE.channels.xml --output=guides/{lang}/{site}.xml",
+    "grab": "node scripts/commands/epg/grab.js",
     "serve": "npx serve"
   },
   "private": true,
@@ -33,10 +33,12 @@
     "chalk": "^4.1.2",
     "cheerio": "^1.0.0-rc.10",
     "commander": "^8.2.0",
+    "consola": "^3.2.3",
+    "cron": "^2.3.1",
     "cross-var": "^1.1.0",
     "csv-parser": "^3.0.0",
     "dayjs": "^1.11.7",
-    "epg-grabber": "^0.31.0",
+    "epg-grabber": "^0.32.0",
     "epg-parser": "^0.2.0",
     "form-data": "^4.0.0",
     "fs-extra": "^10.0.1",

scripts/commands/channels/lint.js

@@ -57,10 +57,10 @@ async function main() {
     }
 
     if (localErrors.length) {
-      logger.info(`\n${chalk.underline(filepath)}`)
+      console.log(`\n${chalk.underline(filepath)}`)
       localErrors.forEach(error => {
         const position = `${error.line}:${error.column}`
-        logger.error(` ${chalk.gray(position.padEnd(4, ' '))} ${error.message.trim()}`)
+        console.log(` ${chalk.gray(position.padEnd(4, ' '))} ${error.message.trim()}`)
       })
 
       errors = errors.concat(localErrors)
@@ -68,7 +68,7 @@ async function main() {
   }
 
   if (errors.length) {
-    logger.error(chalk.red(`\n${errors.length} error(s)`))
+    console.log(chalk.red(`\n${errors.length} error(s)`))
     process.exit(1)
   }
 }

scripts/commands/channels/validate.js

@@ -52,7 +52,7 @@ async function main() {
     }
 
     if (errors.length) {
-      logger.info(chalk.underline(filepath))
+      console.log(chalk.underline(filepath))
       console.table(errors, ['type', 'lang', 'xmltv_id', 'site_id', 'name'])
       console.log()
       stats.files++
@@ -60,7 +60,7 @@ async function main() {
   }
 
   if (stats.errors > 0) {
-    logger.error(chalk.red(`${stats.errors} error(s) in ${stats.files} file(s)`))
+    console.log(chalk.red(`${stats.errors} error(s) in ${stats.files} file(s)`))
     process.exit(1)
   }
 }

scripts/commands/epg/grab.js

@@ -0,0 +1,218 @@
+const { program } = require('commander')
+const _ = require('lodash')
+const { EPGGrabber, generateXMLTV, Channel, Program } = require('epg-grabber')
+const { db, logger, date, timer, file, parser, api, zip } = require('../../core')
+const path = require('path')
+const dayjs = require('dayjs')
+const utc = require('dayjs/plugin/utc')
+const CronJob = require('cron').CronJob
+
+dayjs.extend(utc)
+
+const BASE_DIR = process.env.BASE_DIR || '.'
+const CURR_DATE = process.env.CURR_DATE || new Date()
+
+program
+  .requiredOption('-s, --site <name>', 'Name of the site to parse')
+  .option('-l, --lang <code>', 'Filter channels by language (ISO 639-2 code)')
+  .option('-o, --output <path>', 'Path to output file')
+  .option('--cron <expression>', 'Schedule a script run')
+  .option('--gzip', 'Create a compressed version of the guide as well', false)
+  .parse(process.argv)
+
+const options = program.opts()
+
+options.output = options.output || file.resolve(`${BASE_DIR}/guides/{lang}/{site}.xml`)
+options.config = file.resolve(`${BASE_DIR}/sites/${options.site}/${options.site}.config.js`)
+options.channels = file.resolve(`${BASE_DIR}/sites/${options.site}/${options.site}*.channels.xml`)
+
+let channels = []
+let programs = []
+let runIndex = 0
+
+async function main() {
+  logger.start('staring...')
+
+  logger.info('settings:')
+  for (let prop in options) {
+    logger.info(`  ${prop}: ${options[prop]}`)
+  }
+
+  const config = await loadConfig(options.config)
+  const queue = await createQueue(options.channels, config)
+  const outputPath = options.output
+
+  if (options.cron) {
+    const job = new CronJob(options.cron, function () {
+      runJob(config, queue, outputPath)
+    })
+    job.start()
+  } else {
+    await runJob(config, queue, outputPath)
+  }
+}
+
+async function loadConfig(configPath) {
+  let config = require(file.resolve(configPath))
+  config = _.merge(config, {})
+  config.days = config.days || 1
+
+  logger.info('config:')
+  logConfig(config)
+
+  return config
+}
+
+function logConfig(config, level = 1) {
+  let padLeft = '  '.repeat(level)
+  for (let prop in config) {
+    if (typeof config[prop] === 'string' || typeof config[prop] === 'number') {
+      logger.info(`${padLeft}${prop}: ${config[prop]}`)
+    } else if (typeof config[prop] === 'object') {
+      level++
+      logger.info(`${padLeft}${prop}:`)
+      logConfig(config[prop], level)
+    }
+  }
+}
+
+async function runJob(config, queue, outputPath) {
+  runIndex++
+  logger.info(`run #${runIndex}:`)
+
+  timer.start()
+
+  await grab(queue, config)
+
+  await save(outputPath, channels, programs)
+
+  logger.success(`  done in ${timer.format('HH[h] mm[m] ss[s]')}`)
+}
+
+async function grab(queue, config) {
+  const grabber = new EPGGrabber(config)
+  const total = queue.length
+
+  let i = 1
+  for (const item of queue) {
+    let channel = item.channel
+    let date = item.date
+    channels.push(item.channel)
+    await grabber
+      .grab(channel, date, (data, err) => {
+        logger.info(
+          `  [${i}/${total}] ${channel.site} (${channel.lang}) - ${channel.xmltv_id} - ${dayjs
+            .utc(data.date)
+            .format('MMM D, YYYY')} (${data.programs.length} programs)`
+        )
+        if (i < total) i++
+
+        if (err) {
+          logger.info(`    ERR: ${err.message}`)
+        }
+      })
+      .then(results => {
+        programs = programs.concat(results)
+      })
+  }
+}
+
+async function createQueue(channelsPath, config) {
+  logger.info('creating queue...')
+  let queue = {}
+  await api.channels.load().catch(logger.error)
+  const files = await file.list(channelsPath).catch(logger.error)
+  const utcDate = date.getUTC(CURR_DATE)
+  for (const filepath of files) {
+    logger.info(`  loading "${filepath}"...`)
+    try {
+      const dir = file.dirname(filepath)
+      const { channels } = await parser.parseChannels(filepath)
+      const filename = file.basename(filepath)
+      const dates = Array.from({ length: config.days }, (_, i) => utcDate.add(i, 'd'))
+      for (const channel of channels) {
+        if (!channel.site || !channel.xmltv_id) continue
+        if (options.lang && channel.lang !== options.lang) continue
+        const found = api.channels.find({ id: channel.xmltv_id })
+        if (found) {
+          channel.logo = found.logo
+        }
+        for (const d of dates) {
+          const dateString = d.toJSON()
+          const key = `${channel.site}:${channel.lang}:${channel.xmltv_id}:${dateString}`
+          if (!queue[key]) {
+            queue[key] = {
+              channel,
+              date: dateString,
+              config,
+              error: null
+            }
+          }
+        }
+      }
+    } catch (err) {
+      logger.error(err)
+      continue
+    }
+  }
+
+  queue = Object.values(queue)
+
+  logger.info(`  added ${queue.length} items`)
+
+  return queue
+}
+
+async function save(template, parsedChannels, programs = []) {
+  const variables = file.templateVariables(template)
+
+  const groups = _.groupBy(parsedChannels, channel => {
+    let groupId = ''
+    for (let key in channel) {
+      if (variables.includes(key)) {
+        groupId += channel[key]
+      }
+    }
+
+    return groupId
+  })
+
+  for (let groupId in groups) {
+    const channels = groups[groupId]
+
+    let output = {
+      channels,
+      programs: [],
+      date: CURR_DATE
+    }
+
+    for (let program of programs) {
+      let programLang = program.titles[0].lang
+      let channel = channels.find(c => c.xmltv_id === program.channel && c.lang === programLang)
+      if (!channel) continue
+
+      output.programs.push(new Program(program, channel))
+    }
+
+    output.channels = _.sortBy(output.channels, 'id')
+    output.channels = _.uniqBy(output.channels, 'id')
+
+    output.programs = _.sortBy(output.programs, ['channel', 'start'])
+    output.programs = _.uniqBy(output.programs, p => p.channel + p.start)
+
+    const outputPath = file.templateFormat(template, output.channels[0])
+    const xmlFilepath = outputPath
+    const xmltv = generateXMLTV(output)
+    logger.info(`  saving to "${xmlFilepath}"...`)
+    await file.create(xmlFilepath, xmltv)
+
+    if (options.gzip) {
+      const gzFilepath = `${outputPath}.gz`
+      const compressed = await zip.compress(xmltv)
+      logger.info(`  saving to "${gzFilepath}"...`)
+      await file.create(gzFilepath, compressed)
+    }
+  }
+}
+
+main()

scripts/core/file.js

@@ -4,6 +4,23 @@ const fs = require('fs-extra')
 
 const file = {}
 
+file.templateVariables = function (template) {
+  const match = template.match(/{[^}]+}/g)
+
+  return Array.isArray(match) ? match.map(s => s.substring(1, s.length - 1)) : []
+}
+
+file.templateFormat = function (template, obj) {
+  let output = template
+  for (let key in obj) {
+    const regex = new RegExp(`{${key}}`, 'g')
+    const value = obj[key] || undefined
+    output = output.replace(regex, value)
+  }
+
+  return output
+}
+
 file.list = function (pattern) {
   return new Promise(resolve => {
     glob(pattern, function (err, files) {

scripts/core/logger.js

@@ -1,19 +1,3 @@
-const { Signale } = require('signale')
+const { consola } = require('consola')
 
-const options = {}
-
-const logger = new Signale(options)
-
-logger.config({
-  displayLabel: false,
-  displayScope: false,
-  displayBadge: false
-})
-
-logger.memoryUsage = function () {
-  const used = process.memoryUsage().heapUsed / 1024 / 1024
-
-  logger.info(`memory: ${Math.round(used * 100) / 100} MB`)
-}
-
-module.exports = logger
+module.exports = consola

tests/__data__/expected/guides/da/allente.se.xml

@@ -1,4 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?><tv date="20221020">
-<channel id="6eren.dk"><display-name>6&apos;eren</display-name><icon src="https://upload.wikimedia.org/wikipedia/commons/6/64/6%27eren_2015.png"/><url>https://allente.se</url></channel>
-<programme start="20221024040000 +0000" stop="20221024042500 +0000" channel="6eren.dk"><title lang="da">Diners, Drive-Ins and Dives</title><desc lang="da">Underholdning</desc><category lang="da">series</category><icon src="https://viasatps.api.comspace.se/PS/channeldate/image/viasat.ps/487/2022-10-24/se.cs.6eren.event.B_0254194276971024040000.jpg?size=2560x1440"/><episode-num system="xmltv_ns">23.5.0/1</episode-num><episode-num system="onscreen">S24E06</episode-num></programme>
-</tv>

tests/__data__/expected/guides/en/directv.com.xml

@@ -1,3 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?><tv date="20221020">
-<channel id="BravoEast.us"><display-name>Bravo East</display-name><icon src="https://www.directv.com/images/logos/channels/dark/large/579.png"/><url>https://directv.com</url></channel>
-</tv>

tests/__data__/expected/guides/en/example.com.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8" ?><tv date="20221020">
+<channel id="Channel1.us"><display-name>Channel 1</display-name><url>https://example.com</url></channel>
+<programme start="20220306043000 +0000" stop="20220306071000 +0000" channel="Channel1.us"><title lang="en">Program1</title></programme>
+</tv>

tests/__data__/expected/guides/en/sky.com.xml

@@ -1,4 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?><tv date="20221020">
-<channel id="BBCNews.uk"><display-name>BBC News</display-name><icon src="https://i.imgur.com/rPzH88J.png"/><url>https://sky.com</url></channel>
-<programme start="20221027120000 +0000" stop="20221027123000 +0000" channel="BBCNews.uk"><title lang="en">BBC News at One</title><desc lang="en">The latest national and international news from the BBC. [S,SL]</desc><icon src="http://epgstatic.sky.com/epgdata/1.0/paimage/46/1/lisa/5.2.2/linear/channel/ca247bc8-6be0-48f9-88d1-865f87f7680e/2011"/></programme>
-</tv>

tests/__data__/expected/guides/en/virginmedia.com.xml

@@ -1,4 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?><tv date="20221020">
-<channel id="BBCNews.uk"><display-name>BBC News</display-name><icon src="https://i.imgur.com/rPzH88J.png"/><url>https://virginmedia.com</url></channel>
-<programme start="20221027120000 +0000" stop="20221027123000 +0000" channel="BBCNews.uk"><title lang="en">BBC News at One</title><desc lang="en">The latest national and international news, followed by weather.</desc><category lang="en">News</category><episode-num system="xmltv_ns">96839999.145799123.0/1</episode-num><episode-num system="onscreen">S96840000E145799124</episode-num></programme>
-</tv>

tests/__data__/expected/guides/fr/example.com.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8" ?><tv date="20221020">
+<channel id="Channel1.us"><display-name>Channel 1</display-name><url>https://example.com</url></channel>
+<programme start="20220306043000 +0000" stop="20220306071000 +0000" channel="Channel1.us"><title lang="fr">Program1</title></programme>
+</tv>

tests/__data__/expected/guides/fr/sky.com.xml

@@ -1,6 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?><tv date="20221020">
-<channel id="BBCNews.uk"><display-name>BBC News</display-name><icon src="https://i.imgur.com/rPzH88J.png"/><url>https://sky.com</url></channel>
-<channel id="CNN.us"><display-name>CNN</display-name><icon src="https://www.directv.com/images/logos/channels/dark/large/579.png"/><url>https://sky.com</url></channel>
-<programme start="20221027120000 +0000" stop="20221027123000 +0000" channel="BBCNews.uk"><title lang="fr">BBC News at One</title><desc lang="fr">Les dernières nouvelles nationales et internationales de la BBC. [S,SL]</desc><icon src="http://epgstatic.sky.com/epgdata/1.0/paimage/46/1/lisa/5.2.2/linear/channel/ca247bc8-6be0-48f9-88d1-865f87f7680e/2011"/></programme>
-<programme start="20221027120000 +0000" stop="20221027123000 +0000" channel="CNN.us"><title lang="fr">French title</title></programme>
-</tv>

tests/__data__/input/sites/epg-grab/epg-grab.channels.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<site site="example.com">
+  <channels>
+    <channel lang="en" xmltv_id="Channel1.us" site_id="140">Channel 1</channel>
+    <channel lang="fr" xmltv_id="Channel1.us" site_id="140">Channel 1</channel>
+  </channels>
+</site>

tests/__data__/input/sites/epg-grab/epg-grab.config.js

@@ -0,0 +1,16 @@
+module.exports = {
+  site: 'example.com',
+  days: 2,
+  url() {
+    return `https://example.com`
+  },
+  parser() {
+    return [
+      {
+        title: 'Program1',
+        start: '2022-03-06T04:30:00.000Z',
+        stop: '2022-03-06T07:10:00.000Z'
+      }
+    ]
+  }
+}

tests/commands/epg/grab.test.js

@@ -0,0 +1,39 @@
+const { execSync } = require('child_process')
+const fs = require('fs-extra')
+const path = require('path')
+
+beforeEach(() => {
+  fs.emptyDirSync('tests/__data__/output')
+})
+
+it('can grab epg', () => {
+  const stdout = execSync(
+    'BASE_DIR=tests/__data__/input CURR_DATE=2022-10-20 DATA_DIR=tests/__data__/input/tmp/data npm run grab -- --site=epg-grab --output=tests/__data__/output/{lang}/{site}.xml',
+    { encoding: 'utf8' }
+  )
+
+  expect(content('tests/__data__/output/en/example.com.xml')).toEqual(
+    content('tests/__data__/expected/guides/en/example.com.xml')
+  )
+
+  expect(content('tests/__data__/output/fr/example.com.xml')).toEqual(
+    content('tests/__data__/expected/guides/fr/example.com.xml')
+  )
+})
+
+it('can grab epg with language filter enabled', () => {
+  const stdout = execSync(
+    'BASE_DIR=tests/__data__/input CURR_DATE=2022-10-20 DATA_DIR=tests/__data__/input/tmp/data npm run grab -- --site=epg-grab --lang=fr --output=tests/__data__/output/fr/guide.xml',
+    { encoding: 'utf8' }
+  )
+
+  expect(content('tests/__data__/output/fr/guide.xml')).toEqual(
+    content('tests/__data__/expected/guides/fr/example.com.xml')
+  )
+})
+
+function content(filepath) {
+  return fs.readFileSync(path.resolve(filepath), {
+    encoding: 'utf8'
+  })
+}