tjcrawler 0.0.1 → 0.0.2
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/tjcrawler/crawler.rb +2 -1
- data/lib/tjcrawler/parser.rb +6 -5
- data/lib/tjcrawler/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 4b2e68041b0126fe587a4348cb7b5586231d025b
|
4
|
+
data.tar.gz: 827c4d9d45cdb1c4fd33cabacdc5c10af36def81
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0be2fdd12d3a5079e6979d30f200135d1eff5c193541db58e71b8a289e2d334d9b49eaad3070d0a3df4c38d20a5049d9c7ea99b062ed6d0be7d492732e5aa3c6
|
7
|
+
data.tar.gz: f9d0fa93536ebac50b13dad8988770b7bb1d97b12170d29c8ed53461c33d35aa5dde4753a4b58f379a7e44b735fc9773e482cf235e484984b6c75511985b5a6c
|
data/lib/tjcrawler/crawler.rb
CHANGED
@@ -22,7 +22,8 @@ module Tjcrawler
|
|
22
22
|
sleep 1 until page = Page.dequeue
|
23
23
|
print :'.'
|
24
24
|
result = crawl page.url
|
25
|
-
page.
|
25
|
+
page.update(content: result.content)
|
26
|
+
page.touch(:crawled_at)
|
26
27
|
result.links.each{ |url| Page.enqueue url }
|
27
28
|
end
|
28
29
|
end
|
data/lib/tjcrawler/parser.rb
CHANGED
@@ -1,10 +1,9 @@
|
|
1
1
|
require 'nokogiri'
|
2
2
|
require 'tjcrawler/page'
|
3
|
-
|
4
3
|
module Tjcrawler
|
5
4
|
class Parser
|
6
|
-
|
7
|
-
#
|
5
|
+
@@semaphore = Mutex.new
|
6
|
+
# a nokogiri doc will be yield in block
|
8
7
|
def initialize &block
|
9
8
|
yield 'Block required' unless block_given?
|
10
9
|
@strategy = block
|
@@ -12,7 +11,8 @@ module Tjcrawler
|
|
12
11
|
|
13
12
|
def parse content
|
14
13
|
doc = Nokogiri::HTML(content)
|
15
|
-
ret =
|
14
|
+
ret = nil
|
15
|
+
@@semaphore.synchronize{ ret = @strategy[doc] }
|
16
16
|
print :'.'
|
17
17
|
ret
|
18
18
|
end
|
@@ -20,7 +20,8 @@ module Tjcrawler
|
|
20
20
|
def start
|
21
21
|
loop do
|
22
22
|
sleep 1 until page = find_next
|
23
|
-
|
23
|
+
parse(page.content)
|
24
|
+
page.touch(:parsed_at)
|
24
25
|
end
|
25
26
|
end
|
26
27
|
|
data/lib/tjcrawler/version.rb
CHANGED