get_tapas 0.9.2 → 0.9.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +1 -0
- data/README.md +8 -0
- data/exe/get-tapas +6 -2
- data/lib/get_tapas/downloader.rb +13 -1
- data/lib/get_tapas/page_parser.rb +13 -7
- data/lib/get_tapas/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 13e579fd245dac6c5c005e32e58fed5a40daf655
|
4
|
+
data.tar.gz: 403989d84bf35a73f6ebdc752ed50138dbfd2557
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8400e1777e08589b7b3666b936b310e0e016122f38d4171be507d3d8fbce877a01a97d9322944c1f026d44750fd0d9743f3cbde6ac88b3b551c39d3bf65a8c07
|
7
|
+
data.tar.gz: d68aeadc9e3ad5da7b29516ee0b0815a821feb39abf4c80d64ed2e843cc9af401ce33bf137ae2043923f9597f48e38c02f2b5903ff3e1575ad7d05609bf4eb95
|
data/.gitignore
CHANGED
data/README.md
CHANGED
@@ -57,3 +57,11 @@ Usage: get-tapas [options]
|
|
57
57
|
-h, --help Show this message
|
58
58
|
```
|
59
59
|
|
60
|
+
For your convenience, the output directory defaults to `$HOME/ruby-tapas`.
|
61
|
+
|
62
|
+
## Validation of the Dowloaded Files
|
63
|
+
|
64
|
+
The script makes only a crude test to see that the file has been successfully downloaded
|
65
|
+
(see `Downloader#validate_downloaded_file`).
|
66
|
+
You may want to verify that yourself. If you find an error condition not already tested,
|
67
|
+
please let me know (directly or by posting an issue) and I may be able to add a test for it.
|
data/exe/get-tapas
CHANGED
@@ -30,6 +30,8 @@ end
|
|
30
30
|
|
31
31
|
def process_options
|
32
32
|
|
33
|
+
no_args_were_provided = ARGV.empty?
|
34
|
+
|
33
35
|
option_parser = nil
|
34
36
|
output_help_and_terminate = -> { puts option_parser; puts; exit(-1) }
|
35
37
|
|
@@ -78,7 +80,7 @@ def process_options
|
|
78
80
|
|
79
81
|
end.parse!
|
80
82
|
|
81
|
-
if
|
83
|
+
if no_args_were_provided
|
82
84
|
output_help_and_terminate.()
|
83
85
|
end
|
84
86
|
|
@@ -90,8 +92,10 @@ def get_html(options)
|
|
90
92
|
input = options.input_spec
|
91
93
|
if input == '-'
|
92
94
|
STDIN.read
|
93
|
-
|
95
|
+
elsif input.is_a?(String) && File.file?(input)
|
94
96
|
File.read(input)
|
97
|
+
else
|
98
|
+
raise "Invalid download list HTML input source: #{input.inspect}"
|
95
99
|
end
|
96
100
|
end
|
97
101
|
|
data/lib/get_tapas/downloader.rb
CHANGED
@@ -18,7 +18,7 @@ class Downloader
|
|
18
18
|
|
19
19
|
|
20
20
|
def ensure_output_dir_exists(dir)
|
21
|
-
return if Dir.
|
21
|
+
return if Dir.exist?(dir)
|
22
22
|
begin
|
23
23
|
FileUtils.mkdir_p(dir)
|
24
24
|
puts "Created output data directory #{dir}."
|
@@ -62,11 +62,23 @@ class Downloader
|
|
62
62
|
end
|
63
63
|
|
64
64
|
|
65
|
+
def validate_downloaded_file(filespec)
|
66
|
+
if File.size(filespec) < 20000
|
67
|
+
text = File.read(filespec)
|
68
|
+
if %r{<Error>}.match(text) && %r{</Error>}.match(text)
|
69
|
+
puts "\nDownload error, text was:\n#{text}\n\n\n"
|
70
|
+
raise "Download error"
|
71
|
+
end
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
|
65
76
|
def download_file(link, data_dir)
|
66
77
|
puts "Downloading #{link.filespec}..."
|
67
78
|
tempfilespec = File.join(data_dir, 'tempfile')
|
68
79
|
`curl -o #{tempfilespec} #{Shellwords.shellescape(link.url)}`
|
69
80
|
if $?.exitstatus == 0
|
81
|
+
validate_downloaded_file(tempfilespec)
|
70
82
|
FileUtils.mv(tempfilespec, link.filespec)
|
71
83
|
puts "Finished downloading #{link.filename}\n\n"
|
72
84
|
else
|
@@ -7,20 +7,26 @@ module PageParser
|
|
7
7
|
|
8
8
|
# Example Input: "https://rubytapas-media.s3.amazonaws.com/298-file-find.mp4?response-content-disposition=...
|
9
9
|
# Example Return: '298-file-find.mp4'
|
10
|
-
|
10
|
+
def self.ruby_tapas_url_to_filename(url)
|
11
|
+
url.split('?').first.split('/').last
|
12
|
+
end
|
11
13
|
|
12
14
|
|
13
15
|
# @param html_string an HTML string from https://www.rubytapas.com/download-list/
|
14
16
|
# @return an array of DownloadLink instances.
|
15
|
-
def self.parse(html_string
|
17
|
+
def self.parse(html_string)
|
16
18
|
html_doc = Nokogiri::HTML(html_string)
|
17
19
|
html_links = html_doc.xpath("//*[contains(@class, 'video-download-link')]")
|
18
20
|
|
19
|
-
html_links.
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
21
|
+
if html_links.empty?
|
22
|
+
raise "No screencast links found. Are you sure about the input HTML source?"
|
23
|
+
else
|
24
|
+
html_links.map do |link|
|
25
|
+
url = link.children.first.attributes['href'].value
|
26
|
+
description = link.children.first.text.strip
|
27
|
+
filename = ruby_tapas_url_to_filename(url)
|
28
|
+
DownloadLink.new(url, filename, description)
|
29
|
+
end
|
24
30
|
end
|
25
31
|
end
|
26
32
|
end
|
data/lib/get_tapas/version.rb
CHANGED