portal_scraper 2.0.0 → 2.0.1

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 31516d14a7a801b838c845184d8c561170532c39cedb017efe9c543fdf5ecc9c
4
- data.tar.gz: 7858244b3bfca539c9303f8bad9e0cfaaa0bfe1116ca34f67782ee97f112ffad
3
+ metadata.gz: 3f511d4ae5d6568df6bc6960907a0964ecfb6c8f0c8d5850b5ad757a0ed35039
4
+ data.tar.gz: 5edb4fdbd33676d7b03623a86815b0b865fd214d85e4cd6e34e7fe42fa67204b
5
5
  SHA512:
6
- metadata.gz: 8ca16dace317cacf3f1351d7009c29ef1231341372f764c34182f866727ca2e155fca3f90487d9d3a36ef4e296a12db5be12deef452288f5d4d18c2558059c86
7
- data.tar.gz: fe54374b24f9252cc4186208b5947d5de58ddf77c9541a868774eedae939a3e02218466f23b08398722948e6b85c0c917661fd3a68c7e7e1b2e2dc698902cc80
6
+ metadata.gz: 5df684726b58e1d8da72af7abd8b0395d36bc403f8d045ef0abbf628a8eee0aeebaa13f13ecbc9e80b9ff1dd088695eec92470dac707d5e5977dab1961196234
7
+ data.tar.gz: d93c42d08e8f39ddacf8828060e91324f0ad1b42f1f131b381d43ba693bbba8d05c3d82e1c669736fc153d087b9f648ba1af8fab7936be25c70ee10d811c2708
@@ -21,35 +21,35 @@ module PortalScraper
21
21
  login
22
22
  accounts_data = { accounts: [] }
23
23
 
24
- results = app.post(url_for('/appRecherche.do'), { nom: '', prenom: '', chercher: 'Chercher' })
24
+ user_page = app.post(url_for('/appRecherche.do'), { nom: '', prenom: '', chercher: 'Chercher' })
25
25
  loop do
26
- results.links_with(href: /appTiersDetail.do/).each do |link|
27
- account = link.click
28
- transfers = []
29
- account.links_with(css: 'table#contrat td a').each do |transfer|
30
- result = transfer.click
31
- result.search('table#operation tbody tr').each do |row|
32
- transfers << {
33
- operation_date: parse_date(row.search('td[1]')),
34
- nature: row.search('td[2]').text.strip.gsub(/[\n,\t,'']/, ''),
35
- value_date: parse_date(row.search('td[3]')),
36
- debit: parse_number(row.search('td[4]')),
37
- credit: parse_number(row.search('td[5]')),
38
- }
26
+ user_page.links_with(href: /appTiersDetail.do/).each do |link|
27
+ account = link.click
28
+ selected_row = nil
29
+ selected_row_date = nil
30
+
31
+ account.links_with(css: 'table#contrat td a').each do |row|
32
+ row_date = parse_date(row.node.ancestors('tr').at('td[2]'))&.to_date
33
+ if selected_row_date.nil? || selected_row_date < row_date
34
+ selected_row_date = row_date
35
+ selected_row = row
39
36
  end
40
37
  end
38
+
39
+ transfers = scrap_transfers(selected_row)
40
+ balance = selected_row&.node&.ancestors('tr')&.at('td[4]')
41
41
  accounts_data[:accounts] << {
42
42
  client_ref: find_table_value(account, 'Identifiant tiers'),
43
- balance: parse_number(account.search('table#contrat th.n')),
44
- opened_on: parse_dates(account.search('table#contrat td'))&.max,
43
+ balance: balance.nil? ? "0".to_d : parse_number(balance),
44
+ opened_on: selected_row_date.nil? ? parse_dates(account.search('table#contrat td'))&.max : selected_row_date.to_s,
45
45
  transfers: transfers,
46
46
  }
47
47
  end
48
48
 
49
- break unless results.search('.pg_next').present?
49
+ break unless user_page.search('.pg_next').present?
50
50
  # Need to fetch the first page as you cannot navigate from client back to research page
51
51
  app.post(url_for('/appRecherche.do'), { nom: '', prenom: '', chercher: 'Chercher' })
52
- results = app.get(results.search('a.pg_next').first['href'])
52
+ user_page = app.get(user_page.search('a.pg_next').first['href'])
53
53
  end
54
54
  accounts_data
55
55
  end
@@ -174,6 +174,23 @@ module PortalScraper
174
174
  def config
175
175
  PortalScraper.config
176
176
  end
177
+
178
+ def scrap_transfers(selected_row)
179
+ transfers = []
180
+ transfers_page = selected_row&.click
181
+ if transfers_page
182
+ transfers_page.search('table#operation tbody tr').each do |row|
183
+ transfers << {
184
+ operation_date: parse_date(row.search('td[1]')),
185
+ nature: row.search('td[2]').text.strip.gsub(/[\n,\t,'']/, ''),
186
+ value_date: parse_date(row.search('td[3]')),
187
+ debit: parse_number(row.search('td[4]')),
188
+ credit: parse_number(row.search('td[5]')),
189
+ }
190
+ end
191
+ end
192
+ transfers
193
+ end
177
194
  end
178
195
  end
179
196
  end
@@ -2,7 +2,7 @@ module PortalScraper
2
2
  class Version
3
3
  MAJOR = 2
4
4
  MINOR = 0
5
- PATCH = 0
5
+ PATCH = 1
6
6
 
7
7
  def self.to_s
8
8
  [MAJOR, MINOR, PATCH].compact.join('.')
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: portal_scraper
3
3
  version: !ruby/object:Gem::Version
4
- version: 2.0.0
4
+ version: 2.0.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Armand Mégrot
@@ -9,7 +9,7 @@ authors:
9
9
  autorequire:
10
10
  bindir: bin
11
11
  cert_chain: []
12
- date: 2020-01-05 00:00:00.000000000 Z
12
+ date: 2020-01-06 00:00:00.000000000 Z
13
13
  dependencies:
14
14
  - !ruby/object:Gem::Dependency
15
15
  name: mechanize