Dhalang 0.6.6 → 0.7.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +18 -18
- data/README.md +16 -10
- data/lib/Dhalang/configuration.rb +87 -0
- data/lib/Dhalang/node_script_invoker.rb +29 -0
- data/lib/Dhalang/version.rb +1 -1
- data/lib/Dhalang.rb +3 -1
- data/lib/PDF.rb +4 -3
- data/lib/Scraper.rb +26 -0
- data/lib/Screenshot.rb +4 -3
- data/lib/js/html-scraper.js +26 -0
- data/package-lock.json +2 -2
- data/package.json +1 -1
- metadata +11 -8
- data/lib/Dhalang/puppeteer.rb +0 -97
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 7392a94eca6e888d2a81b779cde341fd7a9be0bbddd2d254e708e93aa18b7fe3
|
|
4
|
+
data.tar.gz: dc520a25fcaf30ad5584820bb45b9bcf72b35531024676e77d9ce0f54291f91f
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 3b75659edee50ba18a726be62a32d39336d5cb8ce6ac94625e529a75015ba7dee45fb396bc292a34604c602369ebba39842c127753d537fc882665a48aacf249
|
|
7
|
+
data.tar.gz: 965cbdae8bc88057c4d7a7a366940a5bb8deedf367893fab5d2c7c437bf96dc9530caf96a138ae7b19ef87ce190c9e8740d83f36cf2a411ec745c3c18b5d208b
|
data/Gemfile.lock
CHANGED
|
@@ -1,15 +1,16 @@
|
|
|
1
1
|
PATH
|
|
2
2
|
remote: .
|
|
3
3
|
specs:
|
|
4
|
-
Dhalang (0.
|
|
4
|
+
Dhalang (0.7.0)
|
|
5
5
|
|
|
6
6
|
GEM
|
|
7
7
|
remote: https://rubygems.org/
|
|
8
8
|
specs:
|
|
9
9
|
Ascii85 (1.1.0)
|
|
10
10
|
afm (0.2.2)
|
|
11
|
-
|
|
12
|
-
|
|
11
|
+
bigdecimal (3.1.7)
|
|
12
|
+
diff-lcs (1.5.1)
|
|
13
|
+
fastimage (2.2.7)
|
|
13
14
|
hashery (2.1.2)
|
|
14
15
|
pdf-reader (2.9.2)
|
|
15
16
|
Ascii85 (~> 1.0)
|
|
@@ -18,26 +19,25 @@ GEM
|
|
|
18
19
|
ruby-rc4
|
|
19
20
|
ttfunk
|
|
20
21
|
rake (13.0.6)
|
|
21
|
-
rspec (3.
|
|
22
|
-
rspec-core (~> 3.
|
|
23
|
-
rspec-expectations (~> 3.
|
|
24
|
-
rspec-mocks (~> 3.
|
|
25
|
-
rspec-core (3.
|
|
26
|
-
rspec-support (~> 3.
|
|
27
|
-
rspec-expectations (3.
|
|
22
|
+
rspec (3.13.0)
|
|
23
|
+
rspec-core (~> 3.13.0)
|
|
24
|
+
rspec-expectations (~> 3.13.0)
|
|
25
|
+
rspec-mocks (~> 3.13.0)
|
|
26
|
+
rspec-core (3.13.0)
|
|
27
|
+
rspec-support (~> 3.13.0)
|
|
28
|
+
rspec-expectations (3.13.0)
|
|
28
29
|
diff-lcs (>= 1.2.0, < 2.0)
|
|
29
|
-
rspec-support (~> 3.
|
|
30
|
-
rspec-mocks (3.
|
|
30
|
+
rspec-support (~> 3.13.0)
|
|
31
|
+
rspec-mocks (3.13.0)
|
|
31
32
|
diff-lcs (>= 1.2.0, < 2.0)
|
|
32
|
-
rspec-support (~> 3.
|
|
33
|
-
rspec-support (3.
|
|
33
|
+
rspec-support (~> 3.13.0)
|
|
34
|
+
rspec-support (3.13.1)
|
|
34
35
|
ruby-rc4 (0.1.5)
|
|
35
|
-
ttfunk (1.
|
|
36
|
+
ttfunk (1.8.0)
|
|
37
|
+
bigdecimal (~> 3.1)
|
|
36
38
|
|
|
37
39
|
PLATFORMS
|
|
38
40
|
arm64-darwin-21
|
|
39
|
-
x86-mingw32
|
|
40
|
-
x86_64-darwin-20
|
|
41
41
|
x86_64-linux
|
|
42
42
|
|
|
43
43
|
DEPENDENCIES
|
|
@@ -49,4 +49,4 @@ DEPENDENCIES
|
|
|
49
49
|
rspec (~> 3.0)
|
|
50
50
|
|
|
51
51
|
BUNDLED WITH
|
|
52
|
-
2.3.
|
|
52
|
+
2.3.7
|
data/README.md
CHANGED
|
@@ -5,9 +5,10 @@
|
|
|
5
5
|
|
|
6
6
|
|
|
7
7
|
## Features
|
|
8
|
-
* Generate PDFs from
|
|
9
|
-
* Generate PDFs from
|
|
10
|
-
* Capture
|
|
8
|
+
* Generate PDFs from webpages
|
|
9
|
+
* Generate PDFs from HTML ( external images/stylesheets supported )
|
|
10
|
+
* Capture screenshots from webpages
|
|
11
|
+
* Scrape HTML from webpages
|
|
11
12
|
|
|
12
13
|
|
|
13
14
|
|
|
@@ -26,37 +27,42 @@ Install puppeteer in your application's root directory:
|
|
|
26
27
|
|
|
27
28
|
<sub>Dhalang and Puppeteer require Node ≥ 18 and Puppeteer ≥ 22</sub>
|
|
28
29
|
## Usage
|
|
29
|
-
|
|
30
|
+
__PDF of a website url__
|
|
30
31
|
```ruby
|
|
31
32
|
Dhalang::PDF.get_from_url("https://www.google.com")
|
|
32
33
|
```
|
|
33
34
|
It is important to pass the complete url, leaving out https://, http:// or www. will result in an error.
|
|
34
35
|
|
|
35
|
-
|
|
36
|
+
__PDF of a HTML string__
|
|
36
37
|
```ruby
|
|
37
38
|
Dhalang::PDF.get_from_html("<html><head></head><body><h1>examplestring</h1></body></html>")
|
|
38
39
|
```
|
|
39
40
|
|
|
40
|
-
|
|
41
|
+
__PNG screenshot of a website__
|
|
41
42
|
```ruby
|
|
42
43
|
Dhalang::Screenshot.get_from_url("https://www.google.com", :png)
|
|
43
44
|
```
|
|
44
45
|
|
|
45
|
-
|
|
46
|
+
__JPEG screenshot of a website__
|
|
46
47
|
```ruby
|
|
47
48
|
Dhalang::Screenshot.get_from_url("https://www.google.com", :jpeg)
|
|
48
49
|
```
|
|
49
50
|
|
|
50
|
-
|
|
51
|
+
__WEBP screenshot of a website__
|
|
51
52
|
```ruby
|
|
52
53
|
Dhalang::Screenshot.get_from_url("https://www.google.com", :webp)
|
|
53
54
|
```
|
|
54
55
|
|
|
55
|
-
|
|
56
|
+
__HTML of a website__
|
|
57
|
+
```ruby
|
|
58
|
+
Dhalang::Scraper.html("https://www.google.com")
|
|
59
|
+
```
|
|
60
|
+
|
|
61
|
+
Above methods either return a string containing the PDF/JPEG/PNG/WEBP in binary or the scraped HTML.
|
|
56
62
|
|
|
57
63
|
|
|
58
64
|
|
|
59
|
-
## Custom
|
|
65
|
+
## Custom options
|
|
60
66
|
To override the default options that are set by Dhalang you can pass as last argument a hash with the custom options you want to set.
|
|
61
67
|
|
|
62
68
|
For example to set custom margins for PDFs:
|
|
@@ -0,0 +1,87 @@
|
|
|
1
|
+
module Dhalang
|
|
2
|
+
# Groups Puppeteer and Dhalang configuration.
|
|
3
|
+
class Configuration
|
|
4
|
+
NODE_MODULES_PATH = Dir.pwd + '/node_modules/'.freeze
|
|
5
|
+
USER_OPTIONS = {
|
|
6
|
+
navigationTimeout: 10000,
|
|
7
|
+
printToPDFTimeout: 0, # unlimited
|
|
8
|
+
navigationWaitUntil: 'load',
|
|
9
|
+
navigationWaitForSelector: '',
|
|
10
|
+
navigationWaitForXPath: '',
|
|
11
|
+
userAgent: '',
|
|
12
|
+
isHeadless: true,
|
|
13
|
+
viewPort: '',
|
|
14
|
+
httpAuthenticationCredentials: '',
|
|
15
|
+
isAutoHeight: false,
|
|
16
|
+
chromeOptions: []
|
|
17
|
+
}.freeze
|
|
18
|
+
DEFAULT_PDF_OPTIONS = {
|
|
19
|
+
scale: 1,
|
|
20
|
+
displayHeaderFooter: false,
|
|
21
|
+
headerTemplate: '',
|
|
22
|
+
footerTemplate: '',
|
|
23
|
+
headerTemplateFile: '',
|
|
24
|
+
footerTemplateFile: '',
|
|
25
|
+
printBackground: true,
|
|
26
|
+
landscape: false,
|
|
27
|
+
pageRanges: '',
|
|
28
|
+
format: 'A4',
|
|
29
|
+
width: '',
|
|
30
|
+
height: '',
|
|
31
|
+
margin: { top: 36, right: 36, bottom: 20, left: 36 },
|
|
32
|
+
preferCSSPageSize: true,
|
|
33
|
+
omitBackground: false
|
|
34
|
+
}.freeze
|
|
35
|
+
DEFAULT_SCREENSHOT_OPTIONS = {
|
|
36
|
+
fullPage: true,
|
|
37
|
+
clip: nil,
|
|
38
|
+
omitBackground: false
|
|
39
|
+
}.freeze
|
|
40
|
+
DEFAULT_JPEG_OPTIONS = {
|
|
41
|
+
quality: 100
|
|
42
|
+
}.freeze
|
|
43
|
+
|
|
44
|
+
private_constant :NODE_MODULES_PATH
|
|
45
|
+
private_constant :USER_OPTIONS
|
|
46
|
+
private_constant :DEFAULT_PDF_OPTIONS
|
|
47
|
+
private_constant :DEFAULT_SCREENSHOT_OPTIONS
|
|
48
|
+
private_constant :DEFAULT_JPEG_OPTIONS
|
|
49
|
+
|
|
50
|
+
private attr_accessor :page_url
|
|
51
|
+
private attr_accessor :temp_file_path
|
|
52
|
+
private attr_accessor :temp_file_extension
|
|
53
|
+
private attr_accessor :user_options
|
|
54
|
+
private attr_accessor :pdf_options
|
|
55
|
+
private attr_accessor :screenshot_options
|
|
56
|
+
private attr_accessor :jpeg_options
|
|
57
|
+
|
|
58
|
+
# @param [Hash] custom_options Changes that override default.
|
|
59
|
+
# @param [String] page_url Url for Puppeteer to visit.
|
|
60
|
+
# @param [String] temp_file_path Absolute path of temp file to use for writing script results.
|
|
61
|
+
# Can be nil for scripts using stdout.
|
|
62
|
+
# @param [String] temp_file_extension Extension of temp file. Can be nil for scripts using stdout.
|
|
63
|
+
def initialize(custom_options, page_url, temp_file_path = nil, temp_file_extension = nil)
|
|
64
|
+
self.page_url = page_url
|
|
65
|
+
self.temp_file_path = temp_file_path
|
|
66
|
+
self.temp_file_extension = temp_file_extension
|
|
67
|
+
self.user_options = USER_OPTIONS.map { |key, default_value| [key, custom_options.fetch(key, default_value)] }
|
|
68
|
+
self.pdf_options = DEFAULT_PDF_OPTIONS.map { |key, default_value| [key, custom_options.fetch(key, default_value)] }
|
|
69
|
+
self.screenshot_options = DEFAULT_SCREENSHOT_OPTIONS.map { |key, default_value| [key, custom_options.fetch(key, default_value)] }
|
|
70
|
+
self.jpeg_options = DEFAULT_JPEG_OPTIONS.map { |key, default_value| [key, custom_options.fetch(key, default_value)] }
|
|
71
|
+
end
|
|
72
|
+
|
|
73
|
+
# Returns configuration as JSON string.
|
|
74
|
+
def json
|
|
75
|
+
return {
|
|
76
|
+
webPageUrl: page_url,
|
|
77
|
+
tempFilePath: temp_file_path,
|
|
78
|
+
puppeteerPath: NODE_MODULES_PATH,
|
|
79
|
+
imageType: temp_file_extension,
|
|
80
|
+
userOptions: user_options.to_h,
|
|
81
|
+
pdfOptions: pdf_options.to_h,
|
|
82
|
+
screenshotOptions: screenshot_options.to_h,
|
|
83
|
+
jpegOptions: jpeg_options.to_h
|
|
84
|
+
}.to_json
|
|
85
|
+
end
|
|
86
|
+
end
|
|
87
|
+
end
|
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
module Dhalang
|
|
2
|
+
class NodeScriptInvoker
|
|
3
|
+
|
|
4
|
+
# Executes JS script under given script_path by launching a new Node process.
|
|
5
|
+
#
|
|
6
|
+
# @param [String] script_path Absolute path of JS script to execute.
|
|
7
|
+
# @param [Configuration] configuration Configuration to use.
|
|
8
|
+
def self.execute_script(script_path, configuration)
|
|
9
|
+
command = create_node_command(script_path, configuration)
|
|
10
|
+
Open3.popen2e(command) do |_stdin, stdouterr, wait|
|
|
11
|
+
return nil if wait.value.success?
|
|
12
|
+
|
|
13
|
+
output = stdouterr.read.strip
|
|
14
|
+
output = nil if output == ''
|
|
15
|
+
message = output || "Exited with status #{wait.value.exitstatus}"
|
|
16
|
+
raise DhalangError, message
|
|
17
|
+
end
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
# Returns a [String] with node command that invokes the provided script with the configuration.
|
|
22
|
+
#
|
|
23
|
+
# @param [String] script_path Absolute path of JS script to invoke.
|
|
24
|
+
# @param [Configuration] configuration Configuration to use.
|
|
25
|
+
private_class_method def self.create_node_command(script_path, configuration)
|
|
26
|
+
"node #{script_path} #{Shellwords.escape(configuration.json)}"
|
|
27
|
+
end
|
|
28
|
+
end
|
|
29
|
+
end
|
data/lib/Dhalang/version.rb
CHANGED
data/lib/Dhalang.rb
CHANGED
|
@@ -1,11 +1,13 @@
|
|
|
1
1
|
module Dhalang
|
|
2
2
|
require_relative 'PDF'
|
|
3
3
|
require_relative 'Screenshot'
|
|
4
|
+
require_relative 'Scraper'
|
|
4
5
|
require_relative 'Dhalang/version'
|
|
5
6
|
require_relative 'Dhalang/url_utils'
|
|
6
7
|
require_relative 'Dhalang/file_utils'
|
|
7
8
|
require_relative 'Dhalang/error'
|
|
8
|
-
require_relative 'Dhalang/
|
|
9
|
+
require_relative 'Dhalang/configuration'
|
|
10
|
+
require_relative 'Dhalang/node_script_invoker'
|
|
9
11
|
require 'uri'
|
|
10
12
|
require 'tempfile'
|
|
11
13
|
require 'shellwords'
|
data/lib/PDF.rb
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
module Dhalang
|
|
2
2
|
# Allows consumers of this library to create PDFs with Puppeteer.
|
|
3
3
|
class PDF
|
|
4
|
-
|
|
5
|
-
private_constant :
|
|
4
|
+
SCRIPT_PATH = File.expand_path('../js/pdf-generator.js', __FILE__).freeze
|
|
5
|
+
private_constant :SCRIPT_PATH
|
|
6
6
|
|
|
7
7
|
# Captures the full webpage under the given url as PDF.
|
|
8
8
|
#
|
|
@@ -43,7 +43,8 @@ module Dhalang
|
|
|
43
43
|
private_class_method def self.get(url, options)
|
|
44
44
|
temp_file = FileUtils.create_temp_file("pdf")
|
|
45
45
|
begin
|
|
46
|
-
|
|
46
|
+
configuration = Configuration.new(options, url, temp_file.path, "pdf")
|
|
47
|
+
NodeScriptInvoker.execute_script(SCRIPT_PATH, configuration)
|
|
47
48
|
binary_pdf_content = FileUtils.read_binary(temp_file.path)
|
|
48
49
|
ensure
|
|
49
50
|
FileUtils.delete(temp_file)
|
data/lib/Scraper.rb
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
module Dhalang
|
|
2
|
+
# Provides functionality for scraping webpages.
|
|
3
|
+
class Scraper
|
|
4
|
+
SCRIPT_PATH = File.expand_path('../js/html-scraper.js', __FILE__).freeze
|
|
5
|
+
private_constant :SCRIPT_PATH
|
|
6
|
+
|
|
7
|
+
# Scrapes full HTML content under given url.
|
|
8
|
+
#
|
|
9
|
+
# @param [String] url Url to scrape.
|
|
10
|
+
# @param [Hash] options User configurable options.
|
|
11
|
+
#
|
|
12
|
+
# @return [String] Scraped HTML content.
|
|
13
|
+
def self.html(url, options = {})
|
|
14
|
+
UrlUtils.validate(url)
|
|
15
|
+
temp_file = FileUtils.create_temp_file("html")
|
|
16
|
+
begin
|
|
17
|
+
configuration = Configuration.new(options, url, temp_file.path, "html")
|
|
18
|
+
NodeScriptInvoker.execute_script(SCRIPT_PATH, configuration)
|
|
19
|
+
html = IO.read(temp_file.path)
|
|
20
|
+
ensure
|
|
21
|
+
FileUtils.delete(temp_file)
|
|
22
|
+
end
|
|
23
|
+
return html
|
|
24
|
+
end
|
|
25
|
+
end
|
|
26
|
+
end
|
data/lib/Screenshot.rb
CHANGED
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
module Dhalang
|
|
2
2
|
# Allows consumers of this library to take screenshots with Puppeteer.
|
|
3
3
|
class Screenshot
|
|
4
|
-
|
|
4
|
+
SCRIPT_PATH = File.expand_path('../js/screenshot-generator.js', __FILE__).freeze
|
|
5
5
|
IMAGE_TYPES = [:jpeg, :png, :webp].freeze
|
|
6
|
-
private_constant :
|
|
6
|
+
private_constant :SCRIPT_PATH
|
|
7
7
|
private_constant :IMAGE_TYPES
|
|
8
8
|
|
|
9
9
|
# <b>DEPRECATED:</b> Please use `get_from_url(url, :jpeg)` instead.
|
|
@@ -44,7 +44,8 @@ module Dhalang
|
|
|
44
44
|
|
|
45
45
|
temp_file = FileUtils.create_temp_file(image_type)
|
|
46
46
|
begin
|
|
47
|
-
|
|
47
|
+
configuration = Configuration.new(options, url, temp_file.path, image_type)
|
|
48
|
+
NodeScriptInvoker.execute_script(SCRIPT_PATH, configuration)
|
|
48
49
|
binary_image_content = FileUtils.read_binary(temp_file.path)
|
|
49
50
|
ensure
|
|
50
51
|
FileUtils.delete(temp_file)
|
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
'use strict';
|
|
2
|
+
const dhalang = require('./dhalang');
|
|
3
|
+
const fs = require('node:fs');
|
|
4
|
+
|
|
5
|
+
const scrapeHtml = async () => {
|
|
6
|
+
const configuration = dhalang.getConfiguration();
|
|
7
|
+
|
|
8
|
+
let browser;
|
|
9
|
+
try {
|
|
10
|
+
browser = await dhalang.launchPuppeteer(configuration);
|
|
11
|
+
const page = await browser.newPage();
|
|
12
|
+
await dhalang.configure(page, configuration.userOptions);
|
|
13
|
+
await dhalang.navigate(page, configuration);
|
|
14
|
+
const html = await page.content();
|
|
15
|
+
fs.writeFileSync(configuration.tempFilePath, html);
|
|
16
|
+
} catch (error) {
|
|
17
|
+
console.error(error.message);
|
|
18
|
+
process.exit(1);
|
|
19
|
+
} finally {
|
|
20
|
+
if (browser) {
|
|
21
|
+
browser.close();
|
|
22
|
+
}
|
|
23
|
+
process.exit(0);
|
|
24
|
+
}
|
|
25
|
+
};
|
|
26
|
+
scrapeHtml();
|
data/package-lock.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dhalang",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.7.0",
|
|
4
4
|
"lockfileVersion": 3,
|
|
5
5
|
"requires": true,
|
|
6
6
|
"packages": {
|
|
7
7
|
"": {
|
|
8
8
|
"name": "dhalang",
|
|
9
|
-
"version": "0.
|
|
9
|
+
"version": "0.7.0",
|
|
10
10
|
"license": "MIT",
|
|
11
11
|
"dependencies": {
|
|
12
12
|
"puppeteer": "^22.5.0"
|
data/package.json
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: Dhalang
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.7.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Niels Steensma
|
|
8
|
-
autorequire:
|
|
8
|
+
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2024-
|
|
11
|
+
date: 2024-04-29 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|
|
@@ -80,7 +80,7 @@ dependencies:
|
|
|
80
80
|
- - "~>"
|
|
81
81
|
- !ruby/object:Gem::Version
|
|
82
82
|
version: '3.0'
|
|
83
|
-
description:
|
|
83
|
+
description:
|
|
84
84
|
email:
|
|
85
85
|
- nielssteensma@yahoo.nl
|
|
86
86
|
executables: []
|
|
@@ -97,14 +97,17 @@ files:
|
|
|
97
97
|
- README.md
|
|
98
98
|
- Rakefile
|
|
99
99
|
- lib/Dhalang.rb
|
|
100
|
+
- lib/Dhalang/configuration.rb
|
|
100
101
|
- lib/Dhalang/error.rb
|
|
101
102
|
- lib/Dhalang/file_utils.rb
|
|
102
|
-
- lib/Dhalang/
|
|
103
|
+
- lib/Dhalang/node_script_invoker.rb
|
|
103
104
|
- lib/Dhalang/url_utils.rb
|
|
104
105
|
- lib/Dhalang/version.rb
|
|
105
106
|
- lib/PDF.rb
|
|
107
|
+
- lib/Scraper.rb
|
|
106
108
|
- lib/Screenshot.rb
|
|
107
109
|
- lib/js/dhalang.js
|
|
110
|
+
- lib/js/html-scraper.js
|
|
108
111
|
- lib/js/pdf-generator.js
|
|
109
112
|
- lib/js/screenshot-generator.js
|
|
110
113
|
- package-lock.json
|
|
@@ -113,7 +116,7 @@ homepage: https://github.com/NielsSteensma/Dhalang
|
|
|
113
116
|
licenses:
|
|
114
117
|
- MIT
|
|
115
118
|
metadata: {}
|
|
116
|
-
post_install_message:
|
|
119
|
+
post_install_message:
|
|
117
120
|
rdoc_options: []
|
|
118
121
|
require_paths:
|
|
119
122
|
- lib
|
|
@@ -128,8 +131,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
128
131
|
- !ruby/object:Gem::Version
|
|
129
132
|
version: '0'
|
|
130
133
|
requirements: []
|
|
131
|
-
rubygems_version: 3.3.
|
|
132
|
-
signing_key:
|
|
134
|
+
rubygems_version: 3.3.7
|
|
135
|
+
signing_key:
|
|
133
136
|
specification_version: 4
|
|
134
137
|
summary: Ruby wrapper for Puppeteer. Generate screenshots and PDF's from HTML!
|
|
135
138
|
test_files: []
|
data/lib/Dhalang/puppeteer.rb
DELETED
|
@@ -1,97 +0,0 @@
|
|
|
1
|
-
module Dhalang
|
|
2
|
-
# Contains common logic for interacting with Puppeteer.
|
|
3
|
-
class Puppeteer
|
|
4
|
-
NODE_MODULES_PATH = Dir.pwd + '/node_modules/'.freeze
|
|
5
|
-
private_constant :NODE_MODULES_PATH
|
|
6
|
-
|
|
7
|
-
USER_OPTIONS = {
|
|
8
|
-
navigationTimeout: 10000,
|
|
9
|
-
printToPDFTimeout: 0, # unlimited
|
|
10
|
-
navigationWaitUntil: 'load',
|
|
11
|
-
navigationWaitForSelector: '',
|
|
12
|
-
navigationWaitForXPath: '',
|
|
13
|
-
userAgent: '',
|
|
14
|
-
isHeadless: true,
|
|
15
|
-
viewPort: '',
|
|
16
|
-
httpAuthenticationCredentials: '',
|
|
17
|
-
isAutoHeight: false,
|
|
18
|
-
chromeOptions: []
|
|
19
|
-
}
|
|
20
|
-
private_constant :USER_OPTIONS
|
|
21
|
-
|
|
22
|
-
DEFAULT_PDF_OPTIONS = {
|
|
23
|
-
scale: 1,
|
|
24
|
-
displayHeaderFooter: false,
|
|
25
|
-
headerTemplate: '',
|
|
26
|
-
footerTemplate: '',
|
|
27
|
-
headerTemplateFile: '',
|
|
28
|
-
footerTemplateFile: '',
|
|
29
|
-
printBackground: true,
|
|
30
|
-
landscape: false,
|
|
31
|
-
pageRanges: '',
|
|
32
|
-
format: 'A4',
|
|
33
|
-
width: '',
|
|
34
|
-
height: '',
|
|
35
|
-
margin: { top: 36, right: 36, bottom: 20, left: 36 },
|
|
36
|
-
preferCSSPageSize: true,
|
|
37
|
-
omitBackground: false
|
|
38
|
-
}
|
|
39
|
-
private_constant :DEFAULT_PDF_OPTIONS
|
|
40
|
-
|
|
41
|
-
DEFAULT_SCREENSHOT_OPTIONS = {
|
|
42
|
-
fullPage: true,
|
|
43
|
-
clip: nil,
|
|
44
|
-
omitBackground: false
|
|
45
|
-
}
|
|
46
|
-
private_constant :DEFAULT_SCREENSHOT_OPTIONS
|
|
47
|
-
|
|
48
|
-
DEFAULT_JPEG_OPTIONS = {
|
|
49
|
-
quality: 100
|
|
50
|
-
}
|
|
51
|
-
private_constant :DEFAULT_JPEG_OPTIONS
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
# Launches a new Node process, executing the (Puppeteer) script under the given script_path.
|
|
55
|
-
#
|
|
56
|
-
# @param [String] page_url The url to pass to the goTo method of Puppeteer.
|
|
57
|
-
# @param [String] script_path The absolute path of the JS script to execute.
|
|
58
|
-
# @param [String] temp_file_path The absolute path of the temp file to use to write any actions from Puppeteer.
|
|
59
|
-
# @param [String] temp_file_extension The extension of the temp file.
|
|
60
|
-
# @param [Object] options Set of options to use, configurable by the user.
|
|
61
|
-
def self.visit(page_url, script_path, temp_file_path, temp_file_extension, options)
|
|
62
|
-
configuration = create_configuration(page_url, script_path, temp_file_path, temp_file_extension, options)
|
|
63
|
-
|
|
64
|
-
command = "node #{script_path} #{Shellwords.escape(configuration)}"
|
|
65
|
-
|
|
66
|
-
Open3.popen2e(command) do |_stdin, stdouterr, wait|
|
|
67
|
-
return nil if wait.value.success?
|
|
68
|
-
|
|
69
|
-
output = stdouterr.read.strip
|
|
70
|
-
output = nil if output == ''
|
|
71
|
-
message = output || "Exited with status #{wait.value.exitstatus}"
|
|
72
|
-
raise DhalangError, message
|
|
73
|
-
end
|
|
74
|
-
end
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
# Returns a JSON string with the configuration to use within the Puppeteer script.
|
|
78
|
-
#
|
|
79
|
-
# @param [String] page_url The url to pass to the goTo method of Puppeteer.
|
|
80
|
-
# @param [String] script_path The absolute path of the JS script to execute.
|
|
81
|
-
# @param [String] temp_file_path The absolute path of the temp file to use to write any actions from Puppeteer.
|
|
82
|
-
# @param [String] temp_file_extension The extension of the temp file.
|
|
83
|
-
# @param [Hash] options Set of options to use, configurable by the user.
|
|
84
|
-
private_class_method def self.create_configuration(page_url, script_path, temp_file_path, temp_file_extension, options)
|
|
85
|
-
{
|
|
86
|
-
webPageUrl: page_url,
|
|
87
|
-
tempFilePath: temp_file_path,
|
|
88
|
-
puppeteerPath: NODE_MODULES_PATH,
|
|
89
|
-
imageType: temp_file_extension,
|
|
90
|
-
userOptions: USER_OPTIONS.map { |option, value| [option, options.has_key?(option) ? options[option] : value]}.to_h,
|
|
91
|
-
pdfOptions: DEFAULT_PDF_OPTIONS.map { |option, value| [option, options.has_key?(option) ? options[option] : value] }.to_h,
|
|
92
|
-
screenshotOptions: DEFAULT_SCREENSHOT_OPTIONS.map { |option, value| [option, options.has_key?(option) ? options[option] : value] }.to_h,
|
|
93
|
-
jpegOptions: DEFAULT_JPEG_OPTIONS.map { |option, value| [option, options.has_key?(option) ? options[option] : value] }.to_h
|
|
94
|
-
}.to_json
|
|
95
|
-
end
|
|
96
|
-
end
|
|
97
|
-
end
|