husc 0.2.2 → 0.2.3
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/lib/husc/version.rb +1 -1
- data/lib/husc.rb +13 -4
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b88c62b3a30dcb02a077d16c07ba7b4f9c08e626133869525b7561f8b5a6aa56
|
4
|
+
data.tar.gz: 0dd75e421be8bac745a6390d32b7eec232ce29a2b2a9f17ca6c3670c26381b4c
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0443eaddb26088cdc733bef5166bc6566b050fe2dd1b8582cd5ca6e6286bf4a01ee9e0ffef894b5fa9b7793acb34b671fc612084e152a71c35c4214e4e5b0c5b
|
7
|
+
data.tar.gz: fd12a24502ae56cd594458db36829e0735b5713a78f317c95e2009f34cc917ff92dcf37d16df09b7a963e3954c548f8071126331b36a212c6f490671ea39d6b8
|
data/lib/husc/version.rb
CHANGED
data/lib/husc.rb
CHANGED
@@ -9,7 +9,7 @@ require 'husc/version'
|
|
9
9
|
class Husc
|
10
10
|
class Error < StandardError; end
|
11
11
|
|
12
|
-
attr_reader :url, :html, :tables, :params
|
12
|
+
attr_reader :url, :html, :tables, :params, :code
|
13
13
|
|
14
14
|
# 特殊配列
|
15
15
|
class CrawlArray < Array
|
@@ -32,16 +32,17 @@ class Husc
|
|
32
32
|
return eval("Husc.new(doc: nil).#{method}(*#{args})")
|
33
33
|
end
|
34
34
|
|
35
|
-
return eval("self[0]
|
35
|
+
return eval("self[0].method}(*#{args})")
|
36
36
|
end
|
37
37
|
end
|
38
38
|
|
39
|
-
def initialize(url = nil, doc: nil, html: nil, user_agent: nil, request_headers: nil)
|
39
|
+
def initialize(url = nil, doc: nil, html: nil, user_agent: nil, request_headers: nil, timeout: 10)
|
40
40
|
## -----*----- コンストラクタ -----*----- ##
|
41
41
|
@agent = Mechanize.new
|
42
42
|
@agent.keep_alive = false
|
43
43
|
@agent.user_agent = user_agent unless user_agent.nil?
|
44
44
|
@agent.request_headers = request_headers unless request_headers.nil?
|
45
|
+
@agent.read_timeout = timeout
|
45
46
|
|
46
47
|
if !url.nil?
|
47
48
|
get(url)
|
@@ -60,7 +61,14 @@ class Husc
|
|
60
61
|
def get(url)
|
61
62
|
## -----*----- ページ推移 -----*----- ##
|
62
63
|
@url = url
|
63
|
-
|
64
|
+
begin
|
65
|
+
page = @agent.get(@url)
|
66
|
+
@code = page.code
|
67
|
+
rescue Mechanize::ResponseCodeError => e
|
68
|
+
@code = e.page.body
|
69
|
+
rescue Net::HTTP::Persistent::Error => e
|
70
|
+
puts e
|
71
|
+
end
|
64
72
|
html = page.content.toutf8
|
65
73
|
update_params(html)
|
66
74
|
end
|
@@ -218,3 +226,4 @@ class Husc
|
|
218
226
|
return str.gsub(" ", ' ').squeeze(' ').gsub("\n \n", "\n").gsub("\n ", "\n").gsub("\r", "\n").squeeze("\n").gsub("\t", "").strip
|
219
227
|
end
|
220
228
|
end
|
229
|
+
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: husc
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Tatsuya Abe
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-03-
|
11
|
+
date: 2020-03-07 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: mechanize
|