baiduserp 2.0.10 → 2.1.1
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/baiduserp/client.rb +8 -1
- data/lib/baiduserp/parser.rb +2 -1
- data/lib/baiduserp/result.rb +5 -0
- data/lib/baiduserp/version.rb +1 -1
- data/lib/parsers/pinpaizhuanqu.rb +1 -2
- data/lib/parsers/zhixin.rb +9 -0
- metadata +4 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: c411628080652da333ee3833dc986e0ede74639c
|
4
|
+
data.tar.gz: 555ff4417a419c469459883781a2e01fc7e2c5e4
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: a7aa377b0ad8b77909eb916394554994bb3e5649b215ae68bf8ff5e794c1297313e9fef5464ece6f85db6af0638358d141f2e749d119dcd574b4f6dccfbe8d27
|
7
|
+
data.tar.gz: 7b1a2a7e8f3c56bd60eef8e148c15aebd913ee27bae78fcf8719923973932f2eda10bd46656818ac10118ab05afd8ebed53eab405d08c9abeb1b5308e1daf7ed
|
data/lib/baiduserp/client.rb
CHANGED
@@ -15,7 +15,14 @@ module Baiduserp
|
|
15
15
|
|
16
16
|
def self.get_serp(url, retries = 6)
|
17
17
|
if retries > 0
|
18
|
-
|
18
|
+
begin
|
19
|
+
response = self.get(url)
|
20
|
+
rescue Timeout::Error => e
|
21
|
+
puts e.class
|
22
|
+
puts e.message
|
23
|
+
sleep(10)
|
24
|
+
retry
|
25
|
+
end
|
19
26
|
if response.code == 301
|
20
27
|
sleep(rand(60)+60)
|
21
28
|
response = self.get_serp(url,retries - 1)
|
data/lib/baiduserp/parser.rb
CHANGED
@@ -3,6 +3,7 @@ require 'nokogiri'
|
|
3
3
|
require 'uri'
|
4
4
|
require 'baiduserp/client'
|
5
5
|
require 'baiduserp/helper'
|
6
|
+
require 'baiduserp/result'
|
6
7
|
|
7
8
|
module Baiduserp
|
8
9
|
class Parser
|
@@ -11,7 +12,7 @@ module Baiduserp
|
|
11
12
|
def parse(html)
|
12
13
|
html = html.encode!('UTF-8','UTF-8',:invalid => :replace)
|
13
14
|
@file = Hash.new
|
14
|
-
@serp =
|
15
|
+
@serp = Baiduserp::Result.new
|
15
16
|
|
16
17
|
@file[:html] = html
|
17
18
|
@file[:doc] = Nokogiri::HTML(html)
|
data/lib/baiduserp/version.rb
CHANGED
@@ -1,6 +1,5 @@
|
|
1
1
|
class Baiduserp::Parser
|
2
2
|
def _parse_pinpaizhuanqu(file)
|
3
|
-
|
4
|
-
html.include?('bs.baidu.com/adcoup-mat') && html.include?('http://clkmk.baidu.com/clkmk-rcv/lnk')
|
3
|
+
file[:doc].search("div[@id='content_left']").first.children[2].name == 'script'
|
5
4
|
end
|
6
5
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: baiduserp
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 2.
|
4
|
+
version: 2.1.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- MingQian Zhang
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2013-11-
|
11
|
+
date: 2013-11-05 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -49,6 +49,7 @@ files:
|
|
49
49
|
- lib/baiduserp/client.rb
|
50
50
|
- lib/baiduserp/helper.rb
|
51
51
|
- lib/baiduserp/parser.rb
|
52
|
+
- lib/baiduserp/result.rb
|
52
53
|
- lib/baiduserp/version.rb
|
53
54
|
- lib/baiduserp.rb
|
54
55
|
- lib/parsers/ads_right.rb
|
@@ -61,6 +62,7 @@ files:
|
|
61
62
|
- lib/parsers/right_personinfo.rb
|
62
63
|
- lib/parsers/right_relaperson.rb
|
63
64
|
- lib/parsers/right_weather.rb
|
65
|
+
- lib/parsers/zhixin.rb
|
64
66
|
- bin/baiduserp
|
65
67
|
- README.md
|
66
68
|
- lib/baiduserp/user_agents.yml
|