html_from_pdf 0.1.0 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +5 -4
- data/lib/html_from_pdf.rb +21 -3
- data/lib/html_from_pdf/converter.rb +3 -6
- data/lib/html_from_pdf/downloader.rb +31 -0
- data/lib/html_from_pdf/helpers.rb +12 -0
- data/lib/html_from_pdf/version.rb +1 -1
- metadata +4 -3
- data/CODE_OF_CONDUCT.md +0 -74
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 05efcbae774d4b590ae4638028a3746414a8fa67036471eee913a1a346c4412d
|
4
|
+
data.tar.gz: e61a1af451bf0c72b6d86eca07c0ca10e3d7e7b39a6aa5feefd7ba6d38dcd910
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 48ca0cba23e73b52a50f0fbf7637d14c7d78bd16b41def184e7845dbbdc9acc3daebfc288a4481433d42a8814e5c3eec69cf29219bbcaa715f0ed3ff95eb78cf
|
7
|
+
data.tar.gz: 3cb4b4159b5ac0091e4d70576eb59a369a930072fbc558aa8c8332953f1c741a0b3e762abed15f359798fda0f2077d3bff6644dfda6537c8502cd81a7e2ecfe4
|
data/README.md
CHANGED
@@ -24,12 +24,17 @@ Or install it yourself as:
|
|
24
24
|
|
25
25
|
```ruby
|
26
26
|
HtmlFromPdf.convert('sample.pdf', 'path/to/html.html', options: { zoom: 1.5 })
|
27
|
+
HtmlFromPdf.convert('https://url_path_for_pdf', options: { zoom: 1.5 })
|
27
28
|
```
|
28
29
|
Path to html is optional
|
29
30
|
```ruby
|
30
31
|
HtmlFromPdf.convert('sample.pdf', options: { zoom: 1.5 })
|
31
32
|
```
|
32
33
|
|
34
|
+
**HtmlFromPdf** has a two methods: **convert** and **convert!**.
|
35
|
+
* The first doesn't raise exceptions and returns *nil* if something went wrong
|
36
|
+
* The second raises exceptions if something went wrong
|
37
|
+
|
33
38
|
#### Allowed options:
|
34
39
|
|
35
40
|
```ruby
|
@@ -96,7 +101,3 @@ Bug reports and pull requests are welcome on GitHub at [html_from_pdf](https://g
|
|
96
101
|
## License
|
97
102
|
|
98
103
|
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
99
|
-
|
100
|
-
## Code of Conduct
|
101
|
-
|
102
|
-
Everyone interacting in the HtmlFromPdf project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/oleksiivykhor/html_from_pdf/blob/master/CODE_OF_CONDUCT.md).
|
data/lib/html_from_pdf.rb
CHANGED
@@ -1,14 +1,32 @@
|
|
1
1
|
require 'html_from_pdf/version'
|
2
2
|
require 'byebug'
|
3
3
|
require 'yaml'
|
4
|
+
require 'open-uri'
|
5
|
+
require 'fileutils'
|
6
|
+
require 'html_from_pdf/helpers'
|
4
7
|
require 'html_from_pdf/exceptions'
|
5
8
|
require 'html_from_pdf/converter'
|
9
|
+
require 'html_from_pdf/downloader'
|
6
10
|
|
7
11
|
module HtmlFromPdf
|
8
12
|
def self.convert(pdf_path, html_path = nil, options: {})
|
9
|
-
|
13
|
+
convert_pdf_to_html(pdf_path, html_path, options)
|
14
|
+
rescue
|
15
|
+
end
|
16
|
+
|
17
|
+
def self.convert!(pdf_path, html_path = nil, options: {})
|
18
|
+
convert_pdf_to_html(pdf_path, html_path, options)
|
19
|
+
end
|
20
|
+
|
21
|
+
class << self
|
22
|
+
private
|
23
|
+
|
24
|
+
def convert_pdf_to_html(pdf_path, html_path, options)
|
25
|
+
pdf_path = HtmlFromPdf::Downloader.download(pdf_path) || pdf_path
|
26
|
+
raise HtmlFromPdf::PdfNotFound unless File.exist? pdf_path
|
10
27
|
|
11
|
-
|
12
|
-
|
28
|
+
converter = HtmlFromPdf::Converter.new(pdf_path, html_path, options)
|
29
|
+
converter.convert
|
30
|
+
end
|
13
31
|
end
|
14
32
|
end
|
@@ -1,5 +1,7 @@
|
|
1
1
|
module HtmlFromPdf
|
2
2
|
class Converter
|
3
|
+
include HtmlFromPdf::Helpers
|
4
|
+
|
3
5
|
def initialize(pdf_path, html_path, options = {})
|
4
6
|
@pdf_path = pdf_path
|
5
7
|
@html_path = html_path
|
@@ -28,7 +30,7 @@ module HtmlFromPdf
|
|
28
30
|
when !@html_path && @options[:dest_dir]
|
29
31
|
file_name = nil
|
30
32
|
else
|
31
|
-
@options[:dest_dir], file_name = File.split(
|
33
|
+
@options[:dest_dir], file_name = File.split(default_file_path)
|
32
34
|
end
|
33
35
|
file_name
|
34
36
|
end
|
@@ -44,10 +46,5 @@ module HtmlFromPdf
|
|
44
46
|
|
45
47
|
result
|
46
48
|
end
|
47
|
-
|
48
|
-
def default_html_path
|
49
|
-
file_name = "#{Time.now.strftime('%m_%d_%Y__%H_%M_%S')}.html"
|
50
|
-
File.join('/tmp/html_from_pdf', file_name)
|
51
|
-
end
|
52
49
|
end
|
53
50
|
end
|
@@ -0,0 +1,31 @@
|
|
1
|
+
module HtmlFromPdf
|
2
|
+
class Downloader
|
3
|
+
extend HtmlFromPdf::Helpers
|
4
|
+
|
5
|
+
def self.download(url)
|
6
|
+
return unless valid_url? url
|
7
|
+
|
8
|
+
file_path = default_file_path(:pdf)
|
9
|
+
dir_path = File.split(file_path).first
|
10
|
+
create_dir dir_path
|
11
|
+
File.open(file_path, 'wb') do |file|
|
12
|
+
file.write open(url).read
|
13
|
+
end
|
14
|
+
file_path
|
15
|
+
end
|
16
|
+
|
17
|
+
class << self
|
18
|
+
private
|
19
|
+
|
20
|
+
def valid_url?(url)
|
21
|
+
regex = /^(http|https):\/\/[a-z0-9]+([\-\.]{1}[a-z0-9]+)*\.[a-z]{2,5}
|
22
|
+
(([0-9]{1,5})?\/.*)?$/ix
|
23
|
+
return false unless url[regex]
|
24
|
+
|
25
|
+
open(url).status.include?('200')
|
26
|
+
rescue SocketError
|
27
|
+
false
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
@@ -0,0 +1,12 @@
|
|
1
|
+
module HtmlFromPdf
|
2
|
+
module Helpers
|
3
|
+
def default_file_path(format = :html)
|
4
|
+
file_name = "#{Time.now.strftime('%m_%d_%Y__%H_%M_%S')}.#{format}"
|
5
|
+
File.join('/tmp/html_from_pdf', file_name)
|
6
|
+
end
|
7
|
+
|
8
|
+
def create_dir(dir_path)
|
9
|
+
FileUtils.mkdir_p dir_path
|
10
|
+
end
|
11
|
+
end
|
12
|
+
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: html_from_pdf
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- o.vykhor
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2018-10-
|
11
|
+
date: 2018-10-22 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -62,7 +62,6 @@ files:
|
|
62
62
|
- ".gitignore"
|
63
63
|
- ".rspec"
|
64
64
|
- ".travis.yml"
|
65
|
-
- CODE_OF_CONDUCT.md
|
66
65
|
- Gemfile
|
67
66
|
- LICENSE.txt
|
68
67
|
- README.md
|
@@ -72,7 +71,9 @@ files:
|
|
72
71
|
- html_from_pdf.gemspec
|
73
72
|
- lib/html_from_pdf.rb
|
74
73
|
- lib/html_from_pdf/converter.rb
|
74
|
+
- lib/html_from_pdf/downloader.rb
|
75
75
|
- lib/html_from_pdf/exceptions.rb
|
76
|
+
- lib/html_from_pdf/helpers.rb
|
76
77
|
- lib/html_from_pdf/options.yml
|
77
78
|
- lib/html_from_pdf/version.rb
|
78
79
|
homepage: https://github.com/oleksiivykhor/html_from_pdf
|
data/CODE_OF_CONDUCT.md
DELETED
@@ -1,74 +0,0 @@
|
|
1
|
-
# Contributor Covenant Code of Conduct
|
2
|
-
|
3
|
-
## Our Pledge
|
4
|
-
|
5
|
-
In the interest of fostering an open and welcoming environment, we as
|
6
|
-
contributors and maintainers pledge to making participation in our project and
|
7
|
-
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
-
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
-
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
-
orientation.
|
11
|
-
|
12
|
-
## Our Standards
|
13
|
-
|
14
|
-
Examples of behavior that contributes to creating a positive environment
|
15
|
-
include:
|
16
|
-
|
17
|
-
* Using welcoming and inclusive language
|
18
|
-
* Being respectful of differing viewpoints and experiences
|
19
|
-
* Gracefully accepting constructive criticism
|
20
|
-
* Focusing on what is best for the community
|
21
|
-
* Showing empathy towards other community members
|
22
|
-
|
23
|
-
Examples of unacceptable behavior by participants include:
|
24
|
-
|
25
|
-
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
-
advances
|
27
|
-
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
-
* Public or private harassment
|
29
|
-
* Publishing others' private information, such as a physical or electronic
|
30
|
-
address, without explicit permission
|
31
|
-
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
-
professional setting
|
33
|
-
|
34
|
-
## Our Responsibilities
|
35
|
-
|
36
|
-
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
-
behavior and are expected to take appropriate and fair corrective action in
|
38
|
-
response to any instances of unacceptable behavior.
|
39
|
-
|
40
|
-
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
-
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
-
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
-
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
-
threatening, offensive, or harmful.
|
45
|
-
|
46
|
-
## Scope
|
47
|
-
|
48
|
-
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
-
when an individual is representing the project or its community. Examples of
|
50
|
-
representing a project or community include using an official project e-mail
|
51
|
-
address, posting via an official social media account, or acting as an appointed
|
52
|
-
representative at an online or offline event. Representation of a project may be
|
53
|
-
further defined and clarified by project maintainers.
|
54
|
-
|
55
|
-
## Enforcement
|
56
|
-
|
57
|
-
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
-
reported by contacting the project team at o.vykhor@ukr.net. All
|
59
|
-
complaints will be reviewed and investigated and will result in a response that
|
60
|
-
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
-
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
-
Further details of specific enforcement policies may be posted separately.
|
63
|
-
|
64
|
-
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
-
faith may face temporary or permanent repercussions as determined by other
|
66
|
-
members of the project's leadership.
|
67
|
-
|
68
|
-
## Attribution
|
69
|
-
|
70
|
-
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
-
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
-
|
73
|
-
[homepage]: http://contributor-covenant.org
|
74
|
-
[version]: http://contributor-covenant.org/version/1/4/
|