crawler_rocks 0.0.2 → 0.0.3
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/crawler_rocks/version.rb +1 -1
- data/lib/crawler_rocks.rb +18 -10
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 30a1e3227e4bd1320a3d72f341ce43c26febefb9
|
4
|
+
data.tar.gz: 33f927a68714710a898611bdd62915b0e46ee22e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 3d9b606ad9f7abb51943a51d35afaba067a572d2faf0312d3e5a6f8b717166476434dab6618517ce9bc68ea9adf91694f54da558f92977ab498947157ddd33fc
|
7
|
+
data.tar.gz: 4e2f7453b7d0f972eca545a8a9800ae5d602201321b00d51021acfd956f804ac9b5bc28e8f4450567571f691b3a7af0e20e9b043d795bf1483d332b8ac2983a7
|
data/lib/crawler_rocks.rb
CHANGED
@@ -4,16 +4,22 @@ require 'curb'
|
|
4
4
|
|
5
5
|
module CrawlerRocks
|
6
6
|
module DSL
|
7
|
-
attr_reader :current_url
|
7
|
+
attr_reader :current_url, :html
|
8
8
|
|
9
|
-
def
|
9
|
+
def setup opts = {}
|
10
10
|
opts = Hash[opts.map{ |k, v| [k.to_sym, v] }]
|
11
|
+
# @curl = Curl::Easy.new
|
12
|
+
# @curl.follow_location = true
|
13
|
+
# @curl.enable_cookies = true
|
14
|
+
@cookies = nil
|
11
15
|
# @encoding = opts.fetch(:encoding, 'utf-8')
|
12
16
|
end
|
13
17
|
|
14
18
|
def visit url
|
15
|
-
|
16
|
-
#
|
19
|
+
# @curl.url = url
|
20
|
+
# @curl.http_get
|
21
|
+
# handle_response
|
22
|
+
handle_response RestClient.get url
|
17
23
|
@current_url = url
|
18
24
|
end
|
19
25
|
|
@@ -39,11 +45,11 @@ module CrawlerRocks
|
|
39
45
|
end
|
40
46
|
|
41
47
|
def post url, opt = {}
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
|
48
|
+
handle_response RestClient.post url, opt.merge({cookies: @cookies})
|
49
|
+
# @curl.url = url
|
50
|
+
# @curl.http_post(opt)
|
51
|
+
# binding.pry
|
52
|
+
# handle_response
|
47
53
|
@current_url = url
|
48
54
|
end
|
49
55
|
|
@@ -53,7 +59,9 @@ module CrawlerRocks
|
|
53
59
|
|
54
60
|
private
|
55
61
|
def handle_response response
|
56
|
-
@doc = Nokogiri::HTML
|
62
|
+
# @doc = Nokogiri::HTML @curl.body_str.force_encoding(@curl.body_str.encoding)
|
63
|
+
@doc = Nokogiri::HTML response.force_encoding(response.encoding)
|
64
|
+
@html = response
|
57
65
|
@cookies ||= response.cookies
|
58
66
|
end
|
59
67
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: crawler_rocks
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Yukai Huang
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-
|
11
|
+
date: 2015-06-01 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|