instascraper 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/.gitignore +4 -0
- data/Gemfile +4 -0
- data/LICENSE +20 -0
- data/Rakefile +1 -0
- data/Readme.md +41 -0
- data/instascraper.gemspec +22 -0
- data/lib/instascraper.rb +47 -0
- data/lib/instascraper/bookmark.rb +11 -0
- data/lib/instascraper/version.rb +3 -0
- metadata +66 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2011 Andrew Nesbitt
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'bundler/gem_tasks'
|
data/Readme.md
ADDED
@@ -0,0 +1,41 @@
|
|
1
|
+
# Instascraper
|
2
|
+
|
3
|
+
This library provides a basic api to instapaper bookmarks for free by scraping the page
|
4
|
+
|
5
|
+
n.b. this is a work in progress, you probably shouldn't use it.
|
6
|
+
|
7
|
+
gem install instascraper
|
8
|
+
|
9
|
+
require 'instascraper'
|
10
|
+
|
11
|
+
i = Instascraper.new('username', 'password')
|
12
|
+
|
13
|
+
# load unread bookmarks
|
14
|
+
bookmarks = i.bookmarks
|
15
|
+
|
16
|
+
bookmarks.each do |b|
|
17
|
+
puts b.link
|
18
|
+
puts b.title
|
19
|
+
end
|
20
|
+
|
21
|
+
# folder support
|
22
|
+
folder_bookmarks = i.bookmarks('folder name')
|
23
|
+
|
24
|
+
## Development
|
25
|
+
|
26
|
+
Source hosted at [GitHub](http://github.com/andrew/instascraper).
|
27
|
+
Report Issues/Feature requests on [GitHub Issues](http://github.com/andrew/instascraper/issues).
|
28
|
+
|
29
|
+
### Note on Patches/Pull Requests
|
30
|
+
|
31
|
+
* Fork the project.
|
32
|
+
* Make your feature addition or bug fix.
|
33
|
+
* Add tests for it. This is important so I don't break it in a
|
34
|
+
future version unintentionally.
|
35
|
+
* Commit, do not mess with rakefile, version, or history.
|
36
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
37
|
+
* Send me a pull request. Bonus points for topic branches.
|
38
|
+
|
39
|
+
## Copyright
|
40
|
+
|
41
|
+
Copyright (c) 2011 Andrew Nesbitt. See [LICENSE](https://github.com/andrew/instascraper/blob/master/LICENSE) for details.
|
@@ -0,0 +1,22 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "instascraper/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "instascraper"
|
7
|
+
s.version = Instascraper::VERSION
|
8
|
+
s.authors = ["Andrew Nesbitt"]
|
9
|
+
s.email = ["andrewnez@gmail.com"]
|
10
|
+
s.homepage = "http://github.com/andrew/instascraper"
|
11
|
+
s.summary = "Basic, free bookmarks api for instapaper"
|
12
|
+
s.description = "A scraper for instapaper to provide a basic api without hacing to pay per month"
|
13
|
+
|
14
|
+
s.rubyforge_project = "instascraper"
|
15
|
+
|
16
|
+
s.files = `git ls-files`.split("\n")
|
17
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
18
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
19
|
+
s.require_paths = ["lib"]
|
20
|
+
|
21
|
+
s.add_dependency 'mechanize'
|
22
|
+
end
|
data/lib/instascraper.rb
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
require "instascraper/version"
|
2
|
+
require "instascraper/bookmark"
|
3
|
+
require 'mechanize'
|
4
|
+
|
5
|
+
class Instascraper
|
6
|
+
def initialize(username, password = '')
|
7
|
+
@agent = Mechanize.new { |agent| agent.user_agent_alias = 'Mac Safari' }
|
8
|
+
|
9
|
+
@agent.get('http://www.instapaper.com/user/login/') do |page|
|
10
|
+
form = page.form
|
11
|
+
form.texts.first.value = username
|
12
|
+
form.password = password
|
13
|
+
form.submit
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
def bookmarks(folder = nil)
|
18
|
+
if folder
|
19
|
+
home = @agent.get('http://www.instapaper.com/u/')
|
20
|
+
path = home.link_with(:text => folder).href
|
21
|
+
else
|
22
|
+
path = '/u'
|
23
|
+
end
|
24
|
+
|
25
|
+
bookmarks = []
|
26
|
+
more_pages = true
|
27
|
+
current_page = nil
|
28
|
+
|
29
|
+
while more_pages do
|
30
|
+
page = @agent.get("http://www.instapaper.com#{path}/#{current_page}")
|
31
|
+
|
32
|
+
page.parser.css('.tableViewCell').each do |bookmark|
|
33
|
+
bookmark.css('.tableViewCellTitleLink').first['href']
|
34
|
+
|
35
|
+
bookmarks << Bookmark.new(bookmark.css('.tableViewCellTitleLink').first['href'], bookmark.css('.tableViewCellTitleLink').first.text)
|
36
|
+
end
|
37
|
+
|
38
|
+
if page.link_with :text => /Older items/
|
39
|
+
current_page = (current_page ? current_page + 1 : 1 )
|
40
|
+
else
|
41
|
+
more_pages = false
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
return bookmarks
|
46
|
+
end
|
47
|
+
end
|
metadata
ADDED
@@ -0,0 +1,66 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: instascraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Andrew Nesbitt
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2011-08-07 00:00:00.000000000Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: mechanize
|
16
|
+
requirement: &70231649735820 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *70231649735820
|
25
|
+
description: A scraper for instapaper to provide a basic api without hacing to pay
|
26
|
+
per month
|
27
|
+
email:
|
28
|
+
- andrewnez@gmail.com
|
29
|
+
executables: []
|
30
|
+
extensions: []
|
31
|
+
extra_rdoc_files: []
|
32
|
+
files:
|
33
|
+
- .gitignore
|
34
|
+
- Gemfile
|
35
|
+
- LICENSE
|
36
|
+
- Rakefile
|
37
|
+
- Readme.md
|
38
|
+
- instascraper.gemspec
|
39
|
+
- lib/instascraper.rb
|
40
|
+
- lib/instascraper/bookmark.rb
|
41
|
+
- lib/instascraper/version.rb
|
42
|
+
homepage: http://github.com/andrew/instascraper
|
43
|
+
licenses: []
|
44
|
+
post_install_message:
|
45
|
+
rdoc_options: []
|
46
|
+
require_paths:
|
47
|
+
- lib
|
48
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
55
|
+
none: false
|
56
|
+
requirements:
|
57
|
+
- - ! '>='
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
version: '0'
|
60
|
+
requirements: []
|
61
|
+
rubyforge_project: instascraper
|
62
|
+
rubygems_version: 1.8.6
|
63
|
+
signing_key:
|
64
|
+
specification_version: 3
|
65
|
+
summary: Basic, free bookmarks api for instapaper
|
66
|
+
test_files: []
|