four-chan 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/four-chan.rb +62 -0
- metadata +45 -0
data/lib/four-chan.rb
ADDED
@@ -0,0 +1,62 @@
|
|
1
|
+
require "string-enumerable"
|
2
|
+
require "net/http"
|
3
|
+
require "nokogiri"
|
4
|
+
require "open-uri"
|
5
|
+
#A method should probably be made specifically to pull/process data.
|
6
|
+
#Main class
|
7
|
+
#Pages variable holds data concerning which pages are in this object
|
8
|
+
#Data should hold the actual data
|
9
|
+
#Everything else should be methods that extract stuff from data
|
10
|
+
class Fourchan
|
11
|
+
#Pull data from 4chan to create new Fourchan object
|
12
|
+
#Pages must be an array, each element being an array with two elements: a symbol corresponding to the board you wish to pull data from (without slashes, (ex :b or :sci)
|
13
|
+
#and an array containing the numbers of the pages to be pulled
|
14
|
+
def initialize(pages)
|
15
|
+
@pages = pages
|
16
|
+
@data = Hash[]
|
17
|
+
for i in pages
|
18
|
+
board = i[0]
|
19
|
+
for j in i[1]
|
20
|
+
key = [board, j]
|
21
|
+
path = "http://boards.4chan.org/" + board.to_s + "/" + j
|
22
|
+
doc = Nokogiri::Doc.new(open(path))
|
23
|
+
@data[key] = doc
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
#Resets all page data in the current object, pulling it from the web anew
|
28
|
+
def reset
|
29
|
+
self = Fourchan.new(@pages)
|
30
|
+
end
|
31
|
+
#Pulls a new page from the web, adding the data to the present object. Note: when #reset is called, pages added with this function are also reset.
|
32
|
+
#The format of page must be the same as one of the elements in the pages argument in the initialization function(2-element array containing symbol denoting board and enumerable denoting pages)
|
33
|
+
def addPage(page)
|
34
|
+
found = false
|
35
|
+
for i in @pages
|
36
|
+
if i[0] == page[0]
|
37
|
+
i[1] = (i[1] + page[1]).uniq
|
38
|
+
found = true
|
39
|
+
break
|
40
|
+
end
|
41
|
+
end
|
42
|
+
@pages += page unless found
|
43
|
+
board = page[0]
|
44
|
+
for i in page[1]
|
45
|
+
key = [board, i]
|
46
|
+
path = "http://boards.4chan.org/" + board.to_s + "/" + i
|
47
|
+
doc = Nokogiri::Doc.new(open(path))
|
48
|
+
@data[key] = doc
|
49
|
+
end
|
50
|
+
end
|
51
|
+
#Returns an array, each element being the text from one post on the given page
|
52
|
+
def postsText(board, page)
|
53
|
+
key = [board, page]
|
54
|
+
doc = @data[key]
|
55
|
+
raw = doc.xpath("//blockquote")
|
56
|
+
raw.delete do |a|
|
57
|
+
not (a["class"].include? "post")
|
58
|
+
end
|
59
|
+
raw
|
60
|
+
end
|
61
|
+
attr_accessor :data
|
62
|
+
end
|
metadata
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: four-chan
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Eigil Rischel
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-08-22 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: A very simplistic interface to pull data from the popular website fourchan
|
15
|
+
email: ayegill@gmail.com
|
16
|
+
executables: []
|
17
|
+
extensions: []
|
18
|
+
extra_rdoc_files: []
|
19
|
+
files:
|
20
|
+
- lib/four-chan.rb
|
21
|
+
homepage: http://rubygems.org/gems/four-chan
|
22
|
+
licenses: []
|
23
|
+
post_install_message:
|
24
|
+
rdoc_options: []
|
25
|
+
require_paths:
|
26
|
+
- lib
|
27
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
28
|
+
none: false
|
29
|
+
requirements:
|
30
|
+
- - ! '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
34
|
+
none: false
|
35
|
+
requirements:
|
36
|
+
- - ! '>='
|
37
|
+
- !ruby/object:Gem::Version
|
38
|
+
version: '0'
|
39
|
+
requirements: []
|
40
|
+
rubyforge_project:
|
41
|
+
rubygems_version: 1.8.24
|
42
|
+
signing_key:
|
43
|
+
specification_version: 3
|
44
|
+
summary: fourchan interface
|
45
|
+
test_files: []
|