adops_report_scrapper 0.2.19 → 0.2.20
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/CHANGELOG +3 -0
- data/Rakefile +5 -0
- data/lib/adops_report_scrapper/adsparc_client.rb +62 -0
- data/lib/adops_report_scrapper/version.rb +1 -1
- data/lib/adops_report_scrapper.rb +1 -0
- data/secret.sample.yml +3 -0
- metadata +2 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 98a0c77cfd9e06624bf5994f7cc64a4833987e04
|
4
|
+
data.tar.gz: 695e54b633e13adafe601bd7a6edb22fd482253b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 59c9a0041d61d1957e9a8cf6ad2cc91d022382d7ba067138b2aa59ba5685ae5c23f983e64be6efcf8c3a6047ca26f1d0e6a8298ac875eeb56a8895f76f96efe1
|
7
|
+
data.tar.gz: d152000831ee7a2e83072f112b1889b67a91249ca8fd652874d138efd46dbde3832434796154ebabc0a60ee11e40eff51d78de939e0c6ea0f46fb758a6b13282
|
data/CHANGELOG
CHANGED
data/Rakefile
CHANGED
@@ -211,6 +211,11 @@ task :adsupplybuyer do
|
|
211
211
|
save_as_csv :adsupplybuyer, :adsupplybuyer
|
212
212
|
end
|
213
213
|
|
214
|
+
desc 'Collect adsparc data'
|
215
|
+
task :adsparc do
|
216
|
+
save_as_csv :adsparc, :adsparc
|
217
|
+
end
|
218
|
+
|
214
219
|
def date
|
215
220
|
@date ||= ENV['date'].nil? ? Date.today - 1 : Date.today - ENV['date'].to_i
|
216
221
|
end
|
@@ -0,0 +1,62 @@
|
|
1
|
+
require 'date'
|
2
|
+
require_relative 'base_client'
|
3
|
+
|
4
|
+
class AdopsReportScrapper::AdsparcClient < AdopsReportScrapper::BaseClient
|
5
|
+
def date_supported?(date = nil)
|
6
|
+
_date = date || @date
|
7
|
+
return true if _date >= Date.today - 2
|
8
|
+
false
|
9
|
+
end
|
10
|
+
|
11
|
+
private
|
12
|
+
|
13
|
+
def login
|
14
|
+
@client.visit 'http://publisher.adsparc.com/login.php'
|
15
|
+
@client.fill_in 'Email', :with => @login
|
16
|
+
@client.fill_in 'Password', :with => @secret
|
17
|
+
@client.click_button 'Login'
|
18
|
+
begin
|
19
|
+
@client.find :xpath, '//*[text()="Logout"]'
|
20
|
+
rescue Exception => e
|
21
|
+
raise e, 'Adsparc login error'
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
def scrap
|
26
|
+
request_report
|
27
|
+
extract_data_from_report
|
28
|
+
end
|
29
|
+
|
30
|
+
def request_report
|
31
|
+
sleep 5
|
32
|
+
url = @client.find(:css, '#iframe').base.attributes['src']
|
33
|
+
@client.visit url
|
34
|
+
sleep 5
|
35
|
+
@client.find(:css, '#topCalendar').click
|
36
|
+
@client.find(:xpath, '//*[text()="Month to date "]').click
|
37
|
+
@client.find(:xpath, '//*[text()="Last 7 Days"]').click
|
38
|
+
@client.click_button 'Apply'
|
39
|
+
sleep 0.5
|
40
|
+
wait_for_loading
|
41
|
+
end
|
42
|
+
|
43
|
+
def extract_data_from_report
|
44
|
+
header = @client.find(:xpath, '//*[contains(@class, "widget-item") and .//*[text()="Publisher Earnings Report - by Day"]]//table/thead/tr').find_css('td,th').map { |td| td.visible_text }
|
45
|
+
@data = [header]
|
46
|
+
date_str = @date.strftime '%d %b %Y'
|
47
|
+
rows = @client.find_all(:xpath, "//*[contains(@class, \"widget-item\") and .//*[text()=\"Publisher Earnings Report - by Day\"]]//table/tbody/tr[./td[text()=\"#{date_str}\"]]")
|
48
|
+
rows = rows.to_a
|
49
|
+
@data.concat(rows.map { |tr| tr.find_css('td,th').map { |td| td.visible_text } })
|
50
|
+
end
|
51
|
+
|
52
|
+
def wait_for_loading
|
53
|
+
30.times do |_i| # wait 5 min
|
54
|
+
begin
|
55
|
+
@client.find(:xpath, '//*[text()="Day"]')
|
56
|
+
break
|
57
|
+
rescue Exception => e
|
58
|
+
sleep 10
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
data/secret.sample.yml
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: adops_report_scrapper
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.20
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Stayman Hou
|
@@ -249,6 +249,7 @@ files:
|
|
249
249
|
- lib/adops_report_scrapper/adforge_client.rb
|
250
250
|
- lib/adops_report_scrapper/adiply_client.rb
|
251
251
|
- lib/adops_report_scrapper/adsense_client.rb
|
252
|
+
- lib/adops_report_scrapper/adsparc_client.rb
|
252
253
|
- lib/adops_report_scrapper/adsupply_client.rb
|
253
254
|
- lib/adops_report_scrapper/adsupplybuyer_client.rb
|
254
255
|
- lib/adops_report_scrapper/adtechus_client.rb
|