page_by_page 0.1.6 → 0.1.7
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/page_by_page/version.rb +1 -1
- data/lib/page_by_page.rb +4 -4
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b503de846c6f14e44ebb68d6da30f0647e3a9e42
|
4
|
+
data.tar.gz: 0b74d6adf88048ed8a78441ec24fad1f686c8ac7
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 032d1274977d459339c51d44648b56ba3eb066818137866ed8c80753f0b9009bebf40a59ef614601034e56e02d466a8636cbf5af86bb9b68309da20c01ba09bd
|
7
|
+
data.tar.gz: 70f97621564edf8ccbade3a23131ca53722f5e7357382d1803ffdf5e17cb1a359e397ac2d6d32c97d8411bca1391a2bc1c51aae6e9378ae1dd508cf50d254f40
|
data/lib/page_by_page/version.rb
CHANGED
data/lib/page_by_page.rb
CHANGED
@@ -51,13 +51,13 @@ class PageByPage
|
|
51
51
|
@enum = MutexEnum.new options
|
52
52
|
parallel_fetch
|
53
53
|
end
|
54
|
-
nodes_2d.flatten
|
54
|
+
nodes_2d.reject(&:nil?).flatten
|
55
55
|
end
|
56
56
|
|
57
57
|
private
|
58
58
|
|
59
59
|
def _fetch
|
60
|
-
items,
|
60
|
+
items, pages = [nil], []
|
61
61
|
catch :no_more do
|
62
62
|
until items.empty?
|
63
63
|
n = @enum.next
|
@@ -65,10 +65,10 @@ class PageByPage
|
|
65
65
|
url = @tmpl.result binding
|
66
66
|
doc = parse url
|
67
67
|
items = doc.css @selector
|
68
|
-
|
68
|
+
pages[n] = items
|
69
69
|
end
|
70
70
|
end
|
71
|
-
|
71
|
+
pages
|
72
72
|
end
|
73
73
|
|
74
74
|
def parallel_fetch
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: page_by_page
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.7
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- ken
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-01-
|
11
|
+
date: 2017-01-04 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -108,7 +108,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
108
108
|
version: '0'
|
109
109
|
requirements: []
|
110
110
|
rubyforge_project:
|
111
|
-
rubygems_version: 2.
|
111
|
+
rubygems_version: 2.6.7
|
112
112
|
signing_key:
|
113
113
|
specification_version: 4
|
114
114
|
summary: scrape page by page , according to url pattern
|