page_by_page 0.1.3 → 0.1.4
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.rb +15 -4
- data/lib/page_by_page/{url.rb → enum.rb} +3 -5
- data/lib/page_by_page/version.rb +1 -1
- 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: c96552a7455f5395239cef9f555ecba50b2fe8f6
|
|
4
|
+
data.tar.gz: e3415ab5619370a7a344cb39834d884d605eaedb
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 8ef3e5d85b79c37c2e9c3a5b2319f9cb5036ba6632799f4241ba426fd21cf032015b2ae2d283abdd0805175a99a99834e12686824ce202c3ddf4d4ffd79533b2
|
|
7
|
+
data.tar.gz: 77ed820bd3e4ece113c752993b1076a992c7e18e80d003d4bd175ae1f70e3387e8ec70fa77af6dd9366b5e03c0c1bb963d0b1038c32443b8526b255006bf0df0
|
data/lib/page_by_page.rb
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
require 'page_by_page/version'
|
|
2
|
-
require 'page_by_page/
|
|
2
|
+
require 'page_by_page/enum'
|
|
3
3
|
require 'nokogiri'
|
|
4
4
|
require 'open-uri'
|
|
5
5
|
|
|
@@ -17,7 +17,7 @@ class PageByPage
|
|
|
17
17
|
end
|
|
18
18
|
|
|
19
19
|
def url tmpl
|
|
20
|
-
@tmpl = tmpl
|
|
20
|
+
@tmpl = ERB.new tmpl
|
|
21
21
|
end
|
|
22
22
|
|
|
23
23
|
def selector sl
|
|
@@ -32,12 +32,19 @@ class PageByPage
|
|
|
32
32
|
@step = n
|
|
33
33
|
end
|
|
34
34
|
|
|
35
|
+
def to n
|
|
36
|
+
@to = n
|
|
37
|
+
end
|
|
38
|
+
|
|
35
39
|
def fetch
|
|
36
|
-
|
|
40
|
+
enum = Enum.new options
|
|
37
41
|
items, all_items = [nil], []
|
|
38
42
|
catch :no_more do
|
|
39
43
|
until items.empty?
|
|
40
|
-
|
|
44
|
+
n = enum.next
|
|
45
|
+
break if n > limit
|
|
46
|
+
url = @tmpl.result binding
|
|
47
|
+
doc = parse url
|
|
41
48
|
items = doc.css @selector
|
|
42
49
|
all_items << items
|
|
43
50
|
end
|
|
@@ -64,4 +71,8 @@ class PageByPage
|
|
|
64
71
|
opt
|
|
65
72
|
end
|
|
66
73
|
|
|
74
|
+
def limit
|
|
75
|
+
@to || Float::INFINITY
|
|
76
|
+
end
|
|
77
|
+
|
|
67
78
|
end
|
|
@@ -2,18 +2,16 @@ require 'forwardable'
|
|
|
2
2
|
require 'erb'
|
|
3
3
|
|
|
4
4
|
class PageByPage
|
|
5
|
-
class
|
|
5
|
+
class Enum
|
|
6
6
|
extend Forwardable
|
|
7
7
|
|
|
8
8
|
def_delegator :@enum, :next
|
|
9
9
|
|
|
10
|
-
def initialize
|
|
11
|
-
@tmpl = ERB.new tmpl
|
|
10
|
+
def initialize from: 1, step: 1
|
|
12
11
|
@enum = Enumerator.new do |yielder|
|
|
13
12
|
n = from
|
|
14
13
|
loop do
|
|
15
|
-
|
|
16
|
-
yielder.yield rendered
|
|
14
|
+
yielder.yield n
|
|
17
15
|
n = n + step
|
|
18
16
|
end
|
|
19
17
|
end
|
data/lib/page_by_page/version.rb
CHANGED
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: 0.1.4
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- ken
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date:
|
|
11
|
+
date: 2017-01-01 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|
|
@@ -83,7 +83,7 @@ files:
|
|
|
83
83
|
- bin/console
|
|
84
84
|
- bin/setup
|
|
85
85
|
- lib/page_by_page.rb
|
|
86
|
-
- lib/page_by_page/
|
|
86
|
+
- lib/page_by_page/enum.rb
|
|
87
87
|
- lib/page_by_page/version.rb
|
|
88
88
|
- page_by_page.gemspec
|
|
89
89
|
homepage: https://github.com/turnon/page_by_page
|