1+ /**
2+ * Copyright 2018 Google Inc. All rights reserved.
3+ *
4+ * Licensed under the Apache License, Version 2.0 (the "License");
5+ * you may not use this file except in compliance with the License.
6+ * You may obtain a copy of the License at
7+ *
8+ * http://www.apache.org/licenses/LICENSE-2.0
9+ *
10+ * Unless required by applicable law or agreed to in writing, software
11+ * distributed under the License is distributed on an "AS IS" BASIS,
12+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13+ * See the License for the specific language governing permissions and
14+ * limitations under the License.
15+ *
16+ * @author ebidel@ (Eric Bidelman)
17+ */
18+
19+ /**
20+ * Shows how to click a file download link and verify that that file gets
21+ * downloaded to the local filesystem in the expected location.
22+ * Note: this approach only works in headful Chrome.
23+ *
24+ * Install:
25+ * npm i puppeteer
26+ * Run:
27+ * node verify_download.js
28+ */
29+
30+ const puppeteer = require ( 'puppeteer' ) ;
31+ const fs = require ( 'fs' ) ;
32+ const path = require ( 'path' ) ;
33+ const os = require ( 'os' ) ;
34+
35+ const DOWNLOADS_FOLDER = `${ os . homedir ( ) } ;
36+
37+ /**
38+ * From @xprudhomme.
39+ * Check if file exists, watching containing directory meanwhile.
40+ * Resolve if the file exists, or if the file is created before the timeout
41+ * occurs.
42+ * @param {string } filePath
43+ * @param {integer } timeout
44+ */
45+ function checkFileExists ( filePath , timeout = 15000 ) {
46+ return new Promise ( ( resolve , reject ) => {
47+ const dir = path . dirname ( filePath ) ;
48+ const basename = path . basename ( filePath ) ;
49+
50+ const watcher = fs . watch ( dir , ( eventType , filename ) => {
51+ if ( eventType === 'rename' && filename === basename ) {
52+ clearTimeout ( timer ) ;
53+ watcher . close ( ) ;
54+ resolve ( basename ) ;
55+ }
56+ } ) ;
57+
58+ const timer = setTimeout ( ( ) => {
59+ watcher . close ( ) ;
60+ reject ( new Error ( ' [checkFileExists] File does not exist, and was not created during the timeout delay.' ) ) ;
61+ } , timeout ) ;
62+
63+ fs . access ( filePath , fs . constants . R_OK , err => {
64+ if ( ! err ) {
65+ clearTimeout ( timer ) ;
66+ watcher . close ( ) ;
67+ resolve ( basename ) ;
68+ }
69+ } ) ;
70+ } ) ;
71+ }
72+
73+ /**
74+ * @param {!Browser } browser
75+ * @param {string } url The URL of the download file to wait for.
76+ * @returns {!Promise<!Object> } Metadata about the latest file in Download Manager.
77+ */
78+ async function waitForFileToDownload ( browser , url ) {
79+ const downloadPage = await browser . newPage ( ) ;
80+ // Note: navigating to this page only works in headful chrome.
81+ await downloadPage . goto ( 'chrome://downloads/' ) ;
82+
83+ // Wait for our download to show up in the list by matching on its url.
84+ const jsHandle = await downloadPage . waitForFunction ( downloadUrl => {
85+ const manager = document . querySelector ( 'downloads-manager' ) ;
86+ const downloads = manager . items_ . length ;
87+ const lastDownload = manager . items_ [ 0 ] ;
88+ if ( downloads && lastDownload . url === downloadUrl &&
89+ lastDownload . state === 'COMPLETE' ) {
90+ return manager . items_ [ 0 ] ;
91+ }
92+ } , { polling : 100 } , url ) ;
93+
94+ const fileMeta = await jsHandle . jsonValue ( ) ;
95+
96+ await downloadPage . close ( ) ;
97+
98+ return fileMeta ;
99+ }
100+
101+ /**
102+ * @param {!Browser } browser
103+ * @param {string } url The url of the page to navigate to.
104+ * @param {string } text The link with this text to find and click on the page.
105+ * @returns {!Promise<?string> } The download resource's url.
106+ */
107+ async function clickDownloadLink ( browser , url , text ) {
108+ const page = await browser . newPage ( ) ;
109+ await page . goto ( url , { waitUntil : 'networkidle2' } ) ;
110+
111+ const downloadUrl = await page . evaluate ( ( text ) => {
112+ const link = document . evaluate ( `//a[text()="${ text } , document ,
113+ null , XPathResult . FIRST_ORDERED_NODE_TYPE , null ) . singleNodeValue ;
114+ if ( link ) {
115+ link . click ( ) ;
116+ return link . href ;
117+ }
118+ return null ;
119+ } , text ) ;
120+
121+ await page . close ( ) ;
122+
123+ return downloadUrl ;
124+ }
125+
126+ ( async ( ) => {
127+
128+ const browser = await puppeteer . launch ( {
129+ headless : false ,
130+ // dumpio: true,
131+ } ) ;
132+
133+ // TODO: setDownloadBehavior would be a good approach, as we could check
134+ // that the file shows up in the location specified by downloadPath. Howeverm
135+ // that arg doesn't currently work.
136+ // const client = await page.target().createCDPSession();
137+ // await client.send('Page.setDownloadBehavior', {
138+ // behavior: 'allow',
139+ // downloadPath: path.resolve(__dirname, 'downloads'),
140+ // });
141+
142+ // await client.detach();
143+
144+ // 1. navigate to a page with a bunch links to download.
145+ // 2. click the "Short Selling (csv)" link on the page. The browser force downloads the file.
146+ const url = 'https://www.nseindia.com/products/content/equities/equities/homepage_eq.htm' ;
147+ const downloadUrl = await clickDownloadLink ( browser , url , 'Short Selling (csv)' ) ;
148+
149+ if ( ! downloadUrl ) {
150+ console . error ( 'Did not find download link!' ) ;
151+ return ;
152+ }
153+
154+ // 3. Open chrome:downloads and wait for the file to be downloaded.
155+ const fileMeta = await waitForFileToDownload ( browser , downloadUrl ) ;
156+
157+ console . log ( `"${ fileMeta . file_name } ) ;
158+
159+ // 4. Optionally check that the file really ends up in the expected location
160+ // on the filesystem.
161+ const exists = await checkFileExists ( `${ DOWNLOADS_FOLDER } ${ fileMeta . file_name } ) ;
162+ console . assert ( exists , `${ fileMeta . file_name } ) ;
163+
164+ await browser . close ( ) ;
165+
166+ } ) ( ) ;
0 commit comments