arb-crawler 1.0.0 → 1.0.1
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/arb/crawler/version.rb +1 -1
- data/lib/arb/crawler.rb +22 -6
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 11a51e3d1ff02b3c4c221f655a651a3c96266c93
|
4
|
+
data.tar.gz: a24e36d8a46bce45d9f56deaf2c30c821f5f0254
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 63cc9d20c65e70f32efa22ec48bf1c8b7c76fa906a25254c0d7f7dfebd6b1c7135774d102ce6e16d294e9c580f543065fc7906e635690c26dceb60944c420823
|
7
|
+
data.tar.gz: eb551ccc891e231c710ee228995943a150fa69c292ed3126ebb64a79077028c08b2c8d2c71d3d123ba847b57b7b36db5b79d4962c65795bc47ff3440fd3fae99
|
data/lib/arb/crawler/version.rb
CHANGED
data/lib/arb/crawler.rb
CHANGED
@@ -15,6 +15,16 @@ module Arb
|
|
15
15
|
client
|
16
16
|
end
|
17
17
|
|
18
|
+
define_method :filter_str do |str, black_list=nil|
|
19
|
+
black_list||=%w{\ / : * ? < > |} << "\n"
|
20
|
+
black_list.each do |i|
|
21
|
+
loop do
|
22
|
+
break unless str.sub!(i,'')
|
23
|
+
end
|
24
|
+
end
|
25
|
+
str
|
26
|
+
end
|
27
|
+
|
18
28
|
define_method :filename_of_url do |url|
|
19
29
|
url && url[url.rindex('/')+1..-1]
|
20
30
|
end
|
@@ -34,18 +44,24 @@ module Arb
|
|
34
44
|
methods.each do |method|
|
35
45
|
ways.each do |way|
|
36
46
|
define_method "#{method}_by_#{way}_raw" do |url,css_or_xpath,&blk|
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
47
|
+
begin
|
48
|
+
::Nokogiri.parse(client.send(method,url).body).send(way,css_or_xpath).tap do |res|
|
49
|
+
if blk
|
50
|
+
res.each do |e|
|
51
|
+
blk[e]
|
52
|
+
end
|
41
53
|
end
|
42
54
|
end
|
55
|
+
rescue Exception=>e
|
56
|
+
$stderr.puts e
|
57
|
+
nil
|
43
58
|
end
|
44
59
|
end
|
45
60
|
|
46
61
|
define_method "#{method}_by_#{way}" do |url,css_or_xpath,&blk|
|
47
62
|
[].tap do |arr|
|
48
|
-
send("#{method}_by_#{way}_raw",url,css_or_xpath)
|
63
|
+
raw=send("#{method}_by_#{way}_raw",url,css_or_xpath)
|
64
|
+
raw && raw.each do |nokogiri_element|
|
49
65
|
arr<<Hash.new.tap do |hash|
|
50
66
|
nokogiri_element.attributes.keys.each do |key|
|
51
67
|
hash[key.to_sym]=nokogiri_element.attribute(key).value
|
@@ -53,7 +69,7 @@ module Arb
|
|
53
69
|
hash.singleton_class.send :define_method, :text do
|
54
70
|
nokogiri_element.text
|
55
71
|
end
|
56
|
-
blk[
|
72
|
+
blk[hash] if blk
|
57
73
|
end
|
58
74
|
end
|
59
75
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: arb-crawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- arybin
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-02-
|
11
|
+
date: 2017-02-18 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|