Initial Commit

sites/rtb.gov.bn/rtb.gov.bn.channels.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<site site="rtb.gov.bn">
+  <channels>
+    <channel lang="ms" xmltv_id="RTBAneka.bn" site_id="Aneka">RTB Aneka</channel>
+    <channel lang="ms" xmltv_id="RTBPerdana.bn" site_id="Perdana">RTB Perdana</channel>
+    <channel lang="ms" xmltv_id="RTBSukmaindera.bn" site_id="Sukmaindera">RTB Sukmaindera</channel>
+  </channels>
+</site>

sites/rtb.gov.bn/rtb.gov.bn.config.js

@@ -0,0 +1,71 @@
+const pdf = require('pdf-parse')
+const dayjs = require('dayjs')
+const utc = require('dayjs/plugin/utc')
+const timezone = require('dayjs/plugin/timezone')
+const customParseFormat = require('dayjs/plugin/customParseFormat')
+
+dayjs.extend(utc)
+dayjs.extend(timezone)
+dayjs.extend(customParseFormat)
+
+module.exports = {
+  skip: true, // INFO: guide is not available on the site
+  site: 'rtb.gov.bn',
+  days: 2,
+  url: function ({ channel, date }) {
+    const [position] = channel.site_id.split('#')
+
+    return encodeURI(
+      `http://www.rtb.gov.bn/PublishingImages/SitePages/Programme Guide/${
+        channel.site_id
+      } ${date.format('DD MMMM YYYY')}.pdf`
+    )
+  },
+  parser: async function ({ buffer, date }) {
+    let programs = []
+    const items = await parseItems(buffer)
+    items.forEach(item => {
+      const prev = programs[programs.length - 1]
+      let start = parseStart(item, date)
+      if (prev) {
+        if (start.isBefore(prev.start)) {
+          start = start.add(1, 'd')
+          date = date.add(1, 'd')
+        }
+        prev.stop = start
+      }
+      const stop = start.add(1, 'h')
+      programs.push({
+        title: item.title,
+        start,
+        stop
+      })
+    })
+
+    return programs
+  }
+}
+
+function parseStart(item, date) {
+  const dateString = `${date.format('YYYY-MM-DD')} ${item.time}`
+
+  return dayjs.tz(dateString, 'YYYY-MM-DD HH:mm', 'Asia/Brunei')
+}
+
+async function parseItems(buffer) {
+  const data = await pdf(buffer).catch(err => null)
+  if (!data) return []
+
+  return data.text
+    .split('\n')
+    .filter(s => {
+      const string = s.trim()
+
+      return string && /^\d{2}:\d{2}/.test(string)
+    })
+    .map(s => {
+      const [_, time, title] = s.trim().match(/^(\d{2}:\d{2}) (.*)/) || [null, null, null]
+
+      return { time, title }
+    })
+}

sites/rtb.gov.bn/rtb.gov.bn.test.js

@@ -0,0 +1,96 @@
+// npx epg-grabber --config=sites/rtb.gov.bn/rtb.gov.bn.config.js --channels=sites/rtb.gov.bn/rtb.gov.bn.channels.xml --output=guide.xml --days=2
+
+const { parser, url } = require('./rtb.gov.bn.config.js')
+const path = require('path')
+const fs = require('fs')
+const dayjs = require('dayjs')
+const utc = require('dayjs/plugin/utc')
+const customParseFormat = require('dayjs/plugin/customParseFormat')
+dayjs.extend(customParseFormat)
+dayjs.extend(utc)
+
+const date = dayjs.utc('2021-11-11', 'YYYY-MM-DD').startOf('d')
+const channel = {
+  site_id: 'Sukmaindera',
+  xmltv_id: 'RTBSukmaindera.bn'
+}
+
+it('can generate valid url', () => {
+  expect(url({ channel, date })).toBe(
+    'http://www.rtb.gov.bn/PublishingImages/SitePages/Programme%20Guide/Sukmaindera%2011%20November%202021.pdf'
+  )
+})
+
+it('can parse Sukmaindera 11 November 2021.pdf', done => {
+  const buffer = fs.readFileSync(
+    path.resolve(__dirname, '__data__/Sukmaindera 11 November 2021.pdf'),
+    {
+      charset: 'utf8'
+    }
+  )
+  parser({ buffer, date })
+    .then(results => {
+      results = results.map(p => {
+        p.start = p.start.toJSON()
+        p.stop = p.stop.toJSON()
+        return p
+      })
+      expect(results.length).toBe(47)
+      expect(results[0]).toMatchObject({
+        start: '2021-11-10T22:00:00.000Z',
+        stop: '2021-11-10T22:05:00.000Z',
+        title: 'NATIONAL ANTHEM'
+      })
+      expect(results[46]).toMatchObject({
+        start: '2021-11-11T21:30:00.000Z',
+        stop: '2021-11-11T22:30:00.000Z',
+        title: 'BACAAN SURAH YASSIN'
+      })
+      done()
+    })
+    .catch(error => {
+      done(error)
+    })
+})
+
+it('can parse Aneka 11 November 2021.pdf', done => {
+  const buffer = fs.readFileSync(path.resolve(__dirname, '__data__/Aneka 11 November 2021.pdf'), {
+    charset: 'utf8'
+  })
+  parser({ buffer, date })
+    .then(results => {
+      results = results.map(p => {
+        p.start = p.start.toJSON()
+        p.stop = p.stop.toJSON()
+        return p
+      })
+      expect(results.length).toBe(26)
+      expect(results[4]).toMatchObject({
+        start: '2021-11-11T03:00:00.000Z',
+        stop: '2021-11-11T04:05:00.000Z',
+        title: 'DRAMA TURKI:'
+      })
+      done()
+    })
+    .catch(error => {
+      done(error)
+    })
+})
+
+it('can handle empty guide', done => {
+  parser({
+    date,
+    channel,
+    content: `<html><head><title>Object moved</title></head><body>
+<h2>Object moved to <a href="/en/_layouts/OGP/ErrorPage.aspx">here</a>.</h2>
+</body></html>
+`
+  })
+    .then(result => {
+      expect(result).toMatchObject([])
+      done()
+    })
+    .catch(error => {
+      done(error)
+    })
+})