book_finder 0.0.0 → 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.
- checksums.yaml +4 -4
- data/lib/bok.rb +129 -0
- data/lib/libgen.rb +72 -0
- metadata +3 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: e4108d73d455de5755c79af70dedf91eef3ee68c0756f6f2fbad79ecdad3de5e
|
|
4
|
+
data.tar.gz: 34dcc23d2026f0d5e9e8fe3e6a653577017a96889bb95d4f82f32bf456e48c73
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 41eccfff0f174e9f92349e23535f87b2fac324f17657a9b4c43d8df2dd075ed011e5ee7fb7958cef408a41825c3ad5796599fac6eaa9f8a981d8e70b2bc123e0
|
|
7
|
+
data.tar.gz: 88cb01fc6559665d221624bb180fd48143b179b83d4915cd276683374fdfffb5e5c3dd56a62e035e505a953e3dfae2ae85d439712e48b5f4b5467106b65cc785
|
data/lib/bok.rb
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require "nokogiri"
|
|
4
|
+
require "open-uri"
|
|
5
|
+
|
|
6
|
+
# b-ok api interface for simple use with web scrapping
|
|
7
|
+
class Bok
|
|
8
|
+
BASEURL = "https://b-ok.cc"
|
|
9
|
+
|
|
10
|
+
def search(params)
|
|
11
|
+
setup
|
|
12
|
+
|
|
13
|
+
query, page, from, to, language, order_by = params.values
|
|
14
|
+
|
|
15
|
+
return :QUERY_MISSING unless query
|
|
16
|
+
|
|
17
|
+
@page = page || 1
|
|
18
|
+
url = BASEURL + "/s/?q=#{query}&page=#{page}"
|
|
19
|
+
if from && to
|
|
20
|
+
url += "&yearFrom=#{from}&yearTo=#{to}"
|
|
21
|
+
end
|
|
22
|
+
if language
|
|
23
|
+
url += "&language=#{language}"
|
|
24
|
+
end
|
|
25
|
+
if order_by
|
|
26
|
+
url += "&order=#{order_by}"
|
|
27
|
+
end
|
|
28
|
+
html = URI.parse(url).open
|
|
29
|
+
@doc = Nokogiri::HTML(html)
|
|
30
|
+
run
|
|
31
|
+
structure
|
|
32
|
+
end
|
|
33
|
+
|
|
34
|
+
def setup
|
|
35
|
+
@page = nil
|
|
36
|
+
@img_by_book = []
|
|
37
|
+
@title_by_book = []
|
|
38
|
+
@links_by_book = []
|
|
39
|
+
@authors_by_book = []
|
|
40
|
+
@year_by_book = []
|
|
41
|
+
@language_by_book = []
|
|
42
|
+
@extension_by_book = []
|
|
43
|
+
@size_by_book = []
|
|
44
|
+
end
|
|
45
|
+
|
|
46
|
+
private
|
|
47
|
+
|
|
48
|
+
def run
|
|
49
|
+
img_urls
|
|
50
|
+
book_titles
|
|
51
|
+
book_authors
|
|
52
|
+
book_year
|
|
53
|
+
book_language
|
|
54
|
+
book_file
|
|
55
|
+
end
|
|
56
|
+
|
|
57
|
+
def structure
|
|
58
|
+
books = []
|
|
59
|
+
@img_by_book.zip(
|
|
60
|
+
@title_by_book,
|
|
61
|
+
@links_by_book,
|
|
62
|
+
@authors_by_book,
|
|
63
|
+
@year_by_book,
|
|
64
|
+
@language_by_book,
|
|
65
|
+
@extension_by_book,
|
|
66
|
+
@size_by_book
|
|
67
|
+
).each do |book|
|
|
68
|
+
books.push(
|
|
69
|
+
img: book[0],
|
|
70
|
+
title: book[1],
|
|
71
|
+
link: book[2],
|
|
72
|
+
authors: book[3],
|
|
73
|
+
year: book[4],
|
|
74
|
+
language: book[5],
|
|
75
|
+
extension: book[6],
|
|
76
|
+
size: book[7]
|
|
77
|
+
)
|
|
78
|
+
end
|
|
79
|
+
books
|
|
80
|
+
end
|
|
81
|
+
|
|
82
|
+
def img_urls
|
|
83
|
+
@doc.search("img.cover.lazy").each do |node|
|
|
84
|
+
@img_by_book.push("https:" + node["data-src"].to_s)
|
|
85
|
+
end
|
|
86
|
+
end
|
|
87
|
+
|
|
88
|
+
def book_titles
|
|
89
|
+
@doc.search('[@itemprop="name"] a').each do |node|
|
|
90
|
+
@title_by_book.push(node.text.to_s)
|
|
91
|
+
url = BASEURL.to_s + node["href"].to_s
|
|
92
|
+
doc = Nokogiri::HTML(URI.parse(url).open)
|
|
93
|
+
doc.search("a.dlButton").each do |nodes|
|
|
94
|
+
@links_by_book.push(BASEURL.to_s + nodes["href"].to_s)
|
|
95
|
+
end
|
|
96
|
+
end
|
|
97
|
+
end
|
|
98
|
+
|
|
99
|
+
def book_authors
|
|
100
|
+
@doc.search('[@class="authors"]').each do |node|
|
|
101
|
+
authors = {}
|
|
102
|
+
node.search("a").each do |author|
|
|
103
|
+
authors[author.text.to_s] = (BASEURL.to_s + author["href"].to_s)
|
|
104
|
+
end
|
|
105
|
+
@authors_by_book.push(authors)
|
|
106
|
+
end
|
|
107
|
+
end
|
|
108
|
+
|
|
109
|
+
def book_year
|
|
110
|
+
@doc.search("div.bookProperty.property_year").each do |node|
|
|
111
|
+
@year_by_book.push(node.text.to_s.gsub!(/\s+/, "").gsub!(/\w+:/, ""))
|
|
112
|
+
end
|
|
113
|
+
end
|
|
114
|
+
|
|
115
|
+
def book_language
|
|
116
|
+
@doc.search("div.bookProperty.property_language").each do |node|
|
|
117
|
+
@language_by_book.push(node.text.to_s.gsub!(/\s+/, "").gsub!(/\w+:/, ""))
|
|
118
|
+
end
|
|
119
|
+
end
|
|
120
|
+
|
|
121
|
+
def book_file
|
|
122
|
+
@doc.search("div.bookProperty.property__file").each do |node|
|
|
123
|
+
extension, size = node.text.to_s.gsub!(/\s+/, "")
|
|
124
|
+
.gsub!(/\w+:/, "").split(",")
|
|
125
|
+
@extension_by_book.push(extension)
|
|
126
|
+
@size_by_book.push(size)
|
|
127
|
+
end
|
|
128
|
+
end
|
|
129
|
+
end
|
data/lib/libgen.rb
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
1
|
+
require "nokogiri"
|
|
2
|
+
require "open-uri"
|
|
3
|
+
|
|
4
|
+
class Libgen
|
|
5
|
+
attr_accessor :columns, :row
|
|
6
|
+
attr_writer :books
|
|
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
|
|
29
|
+
|
|
30
|
+
def books
|
|
31
|
+
@books = @rows.map { |r|
|
|
32
|
+
@columns.zip(vals(r)).to_h
|
|
33
|
+
}
|
|
34
|
+
end
|
|
35
|
+
|
|
36
|
+
private
|
|
37
|
+
|
|
38
|
+
def initialize_columns
|
|
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
|
+
}
|
|
43
|
+
|
|
44
|
+
@columns.compact!
|
|
45
|
+
@columns.shift
|
|
46
|
+
@columns.pop
|
|
47
|
+
end
|
|
48
|
+
|
|
49
|
+
def vals(row)
|
|
50
|
+
full_vals = []
|
|
51
|
+
vals = row.content.split("\r\n\t\t\t\t")
|
|
52
|
+
vals.pop
|
|
53
|
+
vals.shift
|
|
54
|
+
|
|
55
|
+
authors = vals.shift.split(",")
|
|
56
|
+
a_authors = row
|
|
57
|
+
.children[2]
|
|
58
|
+
.search("a")
|
|
59
|
+
.map { |a| a.attribute("href").to_s }
|
|
60
|
+
full_vals << authors.zip(a_authors).to_h
|
|
61
|
+
|
|
62
|
+
7.times { full_vals << vals.shift }
|
|
63
|
+
|
|
64
|
+
full_vals << row.children[18..22].search("a").map { |a| a.attribute("href").to_s }
|
|
65
|
+
full_vals
|
|
66
|
+
end
|
|
67
|
+
|
|
68
|
+
def initialize_rows
|
|
69
|
+
@rows = [@doc.search('[@bgcolor="#C6DEFF"]'),
|
|
70
|
+
@doc.search('[@bgcolor=""]'),].flatten
|
|
71
|
+
end
|
|
72
|
+
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: 0.0.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Gerald Amezcua
|
|
@@ -19,7 +19,9 @@ executables: []
|
|
|
19
19
|
extensions: []
|
|
20
20
|
extra_rdoc_files: []
|
|
21
21
|
files:
|
|
22
|
+
- lib/bok.rb
|
|
22
23
|
- lib/book_finder.rb
|
|
24
|
+
- lib/libgen.rb
|
|
23
25
|
homepage: ''
|
|
24
26
|
licenses:
|
|
25
27
|
- MIT
|