liveblog-indexer 0.2.0 → 0.2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- checksums.yaml.gz.sig +0 -0
- data/lib/liveblog-indexer.rb +14 -9
- data.tar.gz.sig +0 -0
- metadata +1 -1
- metadata.gz.sig +0 -0
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: f82780521af1cc06c3f824c15200ce00745a99b7
|
4
|
+
data.tar.gz: 66819da8961da8a60b3e7441318d9f898274893f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: dbea6b4324aaad28c221b24d57b9bb06801d74678dbd0953dc54d3602f39e115b74e12cb66e90c2a86ef769d2432313b533afc3fd19b6eda5f9fcec189e112ac
|
7
|
+
data.tar.gz: 0b9dbb25e21b8adf798a4bc766ae338821b2b4e79f7e44ad9c76e4311ae868233a407ceb55669c80ae90c688134e7d474fe63cf36b8d173266c5433c74e50bff
|
checksums.yaml.gz.sig
CHANGED
Binary file
|
data/lib/liveblog-indexer.rb
CHANGED
@@ -19,7 +19,12 @@ class LiveBlogIndexer
|
|
19
19
|
end
|
20
20
|
|
21
21
|
@xws = XWS.new
|
22
|
-
|
22
|
+
|
23
|
+
@url_index = if urls_indexed and File.exists? urls_indexed then
|
24
|
+
JSON.parse(File.read(urls_indexed))
|
25
|
+
else
|
26
|
+
{}
|
27
|
+
end
|
23
28
|
|
24
29
|
end
|
25
30
|
|
@@ -40,11 +45,10 @@ class LiveBlogIndexer
|
|
40
45
|
|
41
46
|
url = "%s/#%s" % [link[/^https?:\/\/[^\/]+(.*)(?=\/$)/,1], \
|
42
47
|
section.attributes[:id]]
|
43
|
-
|
44
48
|
h = @xws.scan section.element('details')
|
45
49
|
|
46
50
|
h.each do |k, v|
|
47
|
-
|
51
|
+
|
48
52
|
word, count = k, v
|
49
53
|
|
50
54
|
keyword = @master[word]
|
@@ -61,6 +65,8 @@ class LiveBlogIndexer
|
|
61
65
|
end # /keyword
|
62
66
|
end # /h
|
63
67
|
end # /section
|
68
|
+
|
69
|
+
true
|
64
70
|
end # /add_index
|
65
71
|
|
66
72
|
def crawl(location)
|
@@ -81,14 +87,16 @@ class LiveBlogIndexer
|
|
81
87
|
private
|
82
88
|
|
83
89
|
def index_file(location)
|
84
|
-
|
90
|
+
|
91
|
+
return if @url_index.has_key? location
|
92
|
+
|
85
93
|
puts 'indexing : ' + location.inspect
|
86
94
|
doc = Rexle.new(RXFHelper.read(location).first)
|
87
95
|
summary = doc.root.element 'summary'
|
88
96
|
return unless summary
|
89
97
|
|
90
98
|
result = add_index doc
|
91
|
-
return
|
99
|
+
return unless result
|
92
100
|
|
93
101
|
prev_day = summary.text 'prev_day'
|
94
102
|
|
@@ -98,9 +106,6 @@ class LiveBlogIndexer
|
|
98
106
|
index_file(url)
|
99
107
|
end
|
100
108
|
end
|
101
|
-
|
102
|
-
def save_urlsindex(filepath)
|
103
|
-
|
104
|
-
end
|
109
|
+
|
105
110
|
|
106
111
|
end
|
data.tar.gz.sig
CHANGED
Binary file
|
metadata
CHANGED
metadata.gz.sig
CHANGED
Binary file
|