book_finder 0.0.2 → 0.0.3
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.
- checksums.yaml +4 -4
- data/Gemfile +3 -0
- data/lib/bok.rb +112 -98
- data/lib/book_finder.rb +19 -13
- data/lib/libgen.rb +60 -58
- metadata +17 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 7f7bb75d03f76832c6248ecbd129e7b93708a472e8e1b77c0e829389f3acf382
|
|
4
|
+
data.tar.gz: 737464685e8856f55de5d0028a8b31834a5a18a838f03be7f1e9e28332e56c6f
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 19e0e595c6aff091c9fff46037bb846d06768086a59e5fec1b43aad42dd8230055cbfea1ecfa8b372af26b85c9f992ad81614d2c189c9dd994986ce044e96409
|
|
7
|
+
data.tar.gz: abeaaf270a9f4e3d3acdaaa1234f9955ac62c82e16c6d9ee315d91798244f7dbef3b2636048fb6d2ccc6bdb6fe2d168b7fd445002d93f2cb7c4ea5ca6f2b25aa
|
data/Gemfile
ADDED
data/lib/bok.rb
CHANGED
|
@@ -3,127 +3,141 @@
|
|
|
3
3
|
require "nokogiri"
|
|
4
4
|
require "open-uri"
|
|
5
5
|
|
|
6
|
-
|
|
7
|
-
class Bok
|
|
8
|
-
BASEURL = "https://b-ok.cc"
|
|
6
|
+
class Hash
|
|
9
7
|
|
|
10
|
-
def
|
|
11
|
-
|
|
8
|
+
def stringify_keys
|
|
9
|
+
inject({}) do |hash, (key, value)|
|
|
10
|
+
value = value.stringify_keys if value.is_a?(Hash)
|
|
11
|
+
hash[key.to_s] = value
|
|
12
|
+
hash
|
|
13
|
+
end
|
|
14
|
+
end
|
|
12
15
|
|
|
13
|
-
|
|
16
|
+
end
|
|
14
17
|
|
|
15
|
-
|
|
18
|
+
module BookFinder
|
|
19
|
+
# b-ok api interface for simple use with web scrapping
|
|
20
|
+
class Bok
|
|
21
|
+
BASEURL = "https://b-ok.cc"
|
|
16
22
|
|
|
17
|
-
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
23
|
+
def search(params)
|
|
24
|
+
setup
|
|
25
|
+
|
|
26
|
+
query, page, from, to, language, order_by = params.values
|
|
27
|
+
|
|
28
|
+
return :QUERY_MISSING unless query
|
|
29
|
+
|
|
30
|
+
@page = page || 1
|
|
31
|
+
url = BASEURL + "/s/?q=#{query}&page=#{page}"
|
|
32
|
+
if from && to
|
|
33
|
+
url += "&yearFrom=#{from}&yearTo=#{to}"
|
|
34
|
+
end
|
|
35
|
+
if language
|
|
36
|
+
url += "&language=#{language}"
|
|
37
|
+
end
|
|
38
|
+
if order_by
|
|
39
|
+
url += "&order=#{order_by}"
|
|
40
|
+
end
|
|
41
|
+
html = URI.parse(url).open
|
|
42
|
+
@doc = Nokogiri::HTML(html)
|
|
43
|
+
run
|
|
44
|
+
structure
|
|
27
45
|
end
|
|
28
|
-
html = URI.parse(url).open
|
|
29
|
-
@doc = Nokogiri::HTML(html)
|
|
30
|
-
run
|
|
31
|
-
structure
|
|
32
|
-
end
|
|
33
46
|
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
47
|
+
def setup
|
|
48
|
+
@page = nil
|
|
49
|
+
@img_by_book = []
|
|
50
|
+
@title_by_book = []
|
|
51
|
+
@mirrors_by_book = []
|
|
52
|
+
@authors_by_book = []
|
|
53
|
+
@year_by_book = []
|
|
54
|
+
@language_by_book = []
|
|
55
|
+
@extension_by_book = []
|
|
56
|
+
@size_by_book = []
|
|
57
|
+
end
|
|
45
58
|
|
|
46
|
-
|
|
59
|
+
private
|
|
47
60
|
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
61
|
+
def run
|
|
62
|
+
img_urls
|
|
63
|
+
book_titles
|
|
64
|
+
book_authors
|
|
65
|
+
book_year
|
|
66
|
+
book_language
|
|
67
|
+
book_file
|
|
68
|
+
end
|
|
56
69
|
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
70
|
+
def structure
|
|
71
|
+
books = []
|
|
72
|
+
@img_by_book.zip(
|
|
73
|
+
@title_by_book,
|
|
74
|
+
@mirrors_by_book,
|
|
75
|
+
@authors_by_book,
|
|
76
|
+
@year_by_book,
|
|
77
|
+
@language_by_book,
|
|
78
|
+
@extension_by_book,
|
|
79
|
+
@size_by_book
|
|
80
|
+
).each do |book|
|
|
81
|
+
books.push({
|
|
82
|
+
img: book[0],
|
|
83
|
+
title: book[1],
|
|
84
|
+
mirrors: [book[2]],
|
|
85
|
+
authors: book[3],
|
|
86
|
+
year: book[4],
|
|
87
|
+
language: book[5],
|
|
88
|
+
extension: book[6],
|
|
89
|
+
size: book[7]
|
|
90
|
+
}.stringify_keys)
|
|
91
|
+
end
|
|
92
|
+
books
|
|
78
93
|
end
|
|
79
|
-
books
|
|
80
|
-
end
|
|
81
94
|
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
95
|
+
def img_urls
|
|
96
|
+
@doc.search("img.cover.lazy").each do |node|
|
|
97
|
+
@img_by_book.push("https:" + node["data-src"].to_s)
|
|
98
|
+
end
|
|
85
99
|
end
|
|
86
|
-
end
|
|
87
100
|
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
|
|
101
|
+
def book_titles
|
|
102
|
+
@doc.search('[@itemprop="name"] a').each do |node|
|
|
103
|
+
@title_by_book.push(node.text.to_s)
|
|
104
|
+
url = BASEURL.to_s + node["href"].to_s
|
|
105
|
+
doc = Nokogiri::HTML(URI.parse(url).open)
|
|
106
|
+
doc.search("a.dlButton").each do |nodes|
|
|
107
|
+
@mirrors_by_book.push(BASEURL.to_s + nodes["href"].to_s)
|
|
108
|
+
end
|
|
95
109
|
end
|
|
96
110
|
end
|
|
97
|
-
end
|
|
98
111
|
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
112
|
+
def book_authors
|
|
113
|
+
@doc.search('[@class="authors"]').each do |node|
|
|
114
|
+
authors = {}
|
|
115
|
+
node.search("a").each do |author|
|
|
116
|
+
authors[author.text.to_s] = (BASEURL.to_s + author["href"].to_s)
|
|
117
|
+
end
|
|
118
|
+
@authors_by_book.push(authors)
|
|
104
119
|
end
|
|
105
|
-
@authors_by_book.push(authors)
|
|
106
120
|
end
|
|
107
|
-
end
|
|
108
121
|
|
|
109
|
-
|
|
110
|
-
|
|
111
|
-
|
|
122
|
+
def book_year
|
|
123
|
+
@doc.search("div.bookProperty.property_year").each do |node|
|
|
124
|
+
@year_by_book.push(node.text.to_s.gsub!(/\s+/, "").gsub!(/\w+:/, ""))
|
|
125
|
+
end
|
|
112
126
|
end
|
|
113
|
-
end
|
|
114
127
|
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
|
|
128
|
+
def book_language
|
|
129
|
+
@doc.search("div.bookProperty.property_language").each do |node|
|
|
130
|
+
@language_by_book.push(node.text.to_s.gsub!(/\s+/, "").gsub!(/\w+:/, ""))
|
|
131
|
+
end
|
|
118
132
|
end
|
|
119
|
-
end
|
|
120
133
|
|
|
121
|
-
|
|
122
|
-
|
|
123
|
-
|
|
124
|
-
|
|
125
|
-
|
|
126
|
-
|
|
134
|
+
def book_file
|
|
135
|
+
@doc.search("div.bookProperty.property__file").each do |node|
|
|
136
|
+
extension, size = node.text.to_s.gsub!(/\s+/, "")
|
|
137
|
+
.gsub!(/\w+:/, "").split(",")
|
|
138
|
+
@extension_by_book.push(extension)
|
|
139
|
+
@size_by_book.push(size)
|
|
140
|
+
end
|
|
127
141
|
end
|
|
128
142
|
end
|
|
129
143
|
end
|
data/lib/book_finder.rb
CHANGED
|
@@ -1,30 +1,36 @@
|
|
|
1
1
|
require_relative "bok"
|
|
2
2
|
require_relative "libgen"
|
|
3
3
|
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
end
|
|
11
|
-
|
|
12
|
-
def search(api: nil, params: {})
|
|
13
|
-
|
|
4
|
+
module BookFinder
|
|
5
|
+
@libgen = BookFinder::Libgen.new
|
|
6
|
+
@bok = BookFinder::Bok.new
|
|
7
|
+
@result = []
|
|
8
|
+
|
|
9
|
+
def self.search(api: nil, params: {})
|
|
14
10
|
@result = []
|
|
15
11
|
|
|
16
12
|
return :PARAMS_MISSING if params.empty?
|
|
17
13
|
|
|
18
|
-
if api
|
|
14
|
+
if api.nil? || api.downcase == "libgen"
|
|
19
15
|
@result += @libgen.search(params)
|
|
20
16
|
end
|
|
21
17
|
|
|
22
|
-
if api
|
|
18
|
+
if api.nil? || api.downcase == "bok"
|
|
23
19
|
@result += @bok.search(params)
|
|
24
20
|
end
|
|
25
21
|
|
|
26
|
-
@result
|
|
22
|
+
@result = @result.map do |book|
|
|
23
|
+
book.map { |key, value| [key.to_s.downcase.chomp, value.to_s.downcase.chomp] }.to_h
|
|
24
|
+
end
|
|
25
|
+
|
|
26
|
+
@result.uniq { |book| {authors: book["authors"], title: book["title"], year: book["year"], language: book["language"], size: book["size"], extension: book["extension"]} }
|
|
27
27
|
|
|
28
28
|
end
|
|
29
29
|
|
|
30
30
|
end
|
|
31
|
+
|
|
32
|
+
# books = BookFinder.search(params:{query:"dog"})
|
|
33
|
+
# puts books.length
|
|
34
|
+
# puts books.shift, books.pop
|
|
35
|
+
# puts "------"
|
|
36
|
+
# p books
|
data/lib/libgen.rb
CHANGED
|
@@ -1,72 +1,74 @@
|
|
|
1
1
|
require "nokogiri"
|
|
2
2
|
require "open-uri"
|
|
3
3
|
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
BASE_URL = "http://gen.lib.rus.ec/search.php".freeze
|
|
9
|
-
|
|
10
|
-
def search(params)
|
|
11
|
-
|
|
12
|
-
query, by, ordered_by, order_mode, page = params.values
|
|
13
|
-
|
|
14
|
-
return :QUERY_MISSING unless query
|
|
15
|
-
|
|
16
|
-
url = BASE_URL + "?req=#{query}"
|
|
17
|
-
url << "&sort=#{ordered_by}" if ordered_by
|
|
18
|
-
url << "&sortmode=#{order_mode}" if order_mode
|
|
19
|
-
url << "&column=#{by}" if by
|
|
20
|
-
url << "&page=#{page}" if page
|
|
21
|
-
|
|
22
|
-
html = URI.parse(url).open
|
|
23
|
-
@doc = Nokogiri::HTML(html)
|
|
24
|
-
|
|
25
|
-
initialize_columns
|
|
26
|
-
initialize_rows
|
|
27
|
-
books
|
|
28
|
-
end
|
|
4
|
+
module BookFinder
|
|
5
|
+
class Libgen
|
|
6
|
+
attr_accessor :columns, :row
|
|
7
|
+
attr_writer :books
|
|
29
8
|
|
|
30
|
-
|
|
31
|
-
@books = @rows.map { |r|
|
|
32
|
-
@columns.zip(vals(r)).to_h
|
|
33
|
-
}
|
|
34
|
-
end
|
|
9
|
+
BASE_URL = "http://gen.lib.rus.ec/search.php".freeze
|
|
35
10
|
|
|
36
|
-
|
|
11
|
+
def search(params)
|
|
37
12
|
|
|
38
|
-
|
|
39
|
-
dom_cols = @doc.search('[@bgcolor="#C0C0C0"]').first.children
|
|
40
|
-
@columns = dom_cols.map { |col|
|
|
41
|
-
col.content.strip.downcase.tr("()", "") unless col.content.strip.empty?
|
|
42
|
-
}
|
|
13
|
+
query, by, ordered_by, order_mode, page = params.values
|
|
43
14
|
|
|
44
|
-
|
|
45
|
-
@columns.shift
|
|
46
|
-
@columns.pop
|
|
47
|
-
end
|
|
15
|
+
return :QUERY_MISSING unless query
|
|
48
16
|
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
17
|
+
url = BASE_URL + "?req=#{query}"
|
|
18
|
+
url << "&sort=#{ordered_by}" if ordered_by
|
|
19
|
+
url << "&sortmode=#{order_mode}" if order_mode
|
|
20
|
+
url << "&column=#{by}" if by
|
|
21
|
+
url << "&page=#{page}" if page
|
|
54
22
|
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
.children[2]
|
|
58
|
-
.search("a")
|
|
59
|
-
.map { |a| a.attribute("href").to_s }
|
|
60
|
-
full_vals << authors.zip(a_authors).to_h
|
|
23
|
+
html = URI.parse(url).open
|
|
24
|
+
@doc = Nokogiri::HTML(html)
|
|
61
25
|
|
|
62
|
-
|
|
26
|
+
initialize_columns
|
|
27
|
+
initialize_rows
|
|
28
|
+
books
|
|
29
|
+
end
|
|
63
30
|
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
31
|
+
def books
|
|
32
|
+
@books = @rows.map { |r|
|
|
33
|
+
@columns.zip(vals(r)).to_h
|
|
34
|
+
}
|
|
35
|
+
end
|
|
36
|
+
|
|
37
|
+
private
|
|
38
|
+
|
|
39
|
+
def initialize_columns
|
|
40
|
+
dom_cols = @doc.search('[@bgcolor="#C0C0C0"]').first.children
|
|
41
|
+
@columns = dom_cols.map { |col|
|
|
42
|
+
col.content.strip.downcase.tr("()", "") unless col.content.strip.empty?
|
|
43
|
+
}
|
|
44
|
+
|
|
45
|
+
@columns.compact!
|
|
46
|
+
@columns.shift
|
|
47
|
+
@columns.pop
|
|
48
|
+
end
|
|
49
|
+
|
|
50
|
+
def vals(row)
|
|
51
|
+
full_vals = []
|
|
52
|
+
vals = row.content.split("\r\n\t\t\t\t")
|
|
53
|
+
vals.pop
|
|
54
|
+
vals.shift
|
|
55
|
+
|
|
56
|
+
authors = vals.shift.split(",")
|
|
57
|
+
a_authors = row
|
|
58
|
+
.children[2]
|
|
59
|
+
.search("a")
|
|
60
|
+
.map { |a| a.attribute("href").to_s }
|
|
61
|
+
full_vals << authors.zip(a_authors).to_h
|
|
62
|
+
|
|
63
|
+
7.times { full_vals << vals.shift }
|
|
64
|
+
|
|
65
|
+
full_vals << row.children[18..22].search("a").map { |a| a.attribute("href").to_s }
|
|
66
|
+
full_vals
|
|
67
|
+
end
|
|
67
68
|
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
69
|
+
def initialize_rows
|
|
70
|
+
@rows = [@doc.search('[@bgcolor="#C6DEFF"]'),
|
|
71
|
+
@doc.search('[@bgcolor=""]'),].flatten
|
|
72
|
+
end
|
|
71
73
|
end
|
|
72
74
|
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: book_finder
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Gerald Amezcua
|
|
@@ -10,7 +10,21 @@ autorequire:
|
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
12
|
date: 2019-10-30 00:00:00.000000000 Z
|
|
13
|
-
dependencies:
|
|
13
|
+
dependencies:
|
|
14
|
+
- !ruby/object:Gem::Dependency
|
|
15
|
+
name: nokogiri
|
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
|
17
|
+
requirements:
|
|
18
|
+
- - "~>"
|
|
19
|
+
- !ruby/object:Gem::Version
|
|
20
|
+
version: '1.6'
|
|
21
|
+
type: :runtime
|
|
22
|
+
prerelease: false
|
|
23
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
24
|
+
requirements:
|
|
25
|
+
- - "~>"
|
|
26
|
+
- !ruby/object:Gem::Version
|
|
27
|
+
version: '1.6'
|
|
14
28
|
description:
|
|
15
29
|
email:
|
|
16
30
|
- gerald.amezcua@michelada.io
|
|
@@ -19,6 +33,7 @@ executables: []
|
|
|
19
33
|
extensions: []
|
|
20
34
|
extra_rdoc_files: []
|
|
21
35
|
files:
|
|
36
|
+
- Gemfile
|
|
22
37
|
- lib/bok.rb
|
|
23
38
|
- lib/book_finder.rb
|
|
24
39
|
- lib/libgen.rb
|