pageflow-chart 2.1.0 → 2.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.travis.yml +1 -0
- data/CHANGELOG.md +12 -8
- data/README.md +2 -2
- data/app/assets/javascripts/pageflow/chart/consent.js +16 -0
- data/app/assets/javascripts/pageflow/chart/editor/config.js +7 -0
- data/app/assets/javascripts/pageflow/chart/editor/models/scraped_site.js +11 -50
- data/app/assets/javascripts/pageflow/chart/editor/views/configuration_editor.js +6 -4
- data/app/assets/javascripts/pageflow/chart/editor/views/embedded/iframe_embedded_view.js +32 -16
- data/app/assets/javascripts/pageflow/chart/editor/views/inputs/scraped_url_input_view.js +18 -39
- data/app/assets/javascripts/pageflow/chart/editor.js +4 -3
- data/app/assets/javascripts/pageflow/chart/page_type.js +61 -53
- data/app/assets/javascripts/pageflow/chart.js +2 -3
- data/app/assets/stylesheets/pageflow/chart/editor.scss +3 -20
- data/app/assets/stylesheets/pageflow/chart/themes/default.scss +3 -0
- data/app/assets/stylesheets/pageflow/chart.scss +9 -16
- data/app/helpers/pageflow/chart/scraped_sites_helper.rb +17 -8
- data/app/jobs/pageflow/chart/scrape_site_job.rb +14 -4
- data/app/models/pageflow/chart/scraped_site.rb +37 -4
- data/app/views/pageflow/chart/editor/scraped_sites/_scraped_site.json.jbuilder +1 -0
- data/app/views/pageflow/chart/page.html.erb +9 -2
- data/chart.gemspec +2 -2
- data/config/locales/de.yml +4 -0
- data/config/locales/en.yml +4 -0
- data/db/migrate/20190531141820_add_file_attributes_to_scraped_sites.rb +8 -0
- data/db/migrate/20190531145431_insert_file_usages_for_scraped_sites.rb +59 -0
- data/db/migrate/20200507141608_add_javascript_body_attachment_to_scraped_site.rb +5 -0
- data/lib/pageflow/chart/configuration.rb +6 -3
- data/lib/pageflow/chart/downloader.rb +4 -1
- data/lib/pageflow/chart/page_type.rb +17 -0
- data/lib/pageflow/chart/plugin.rb +10 -0
- data/lib/pageflow/chart/refresh_tag_following_downloader.rb +3 -3
- data/lib/pageflow/chart/scraper.rb +25 -13
- data/lib/pageflow/chart/version.rb +1 -1
- data/lib/pageflow/chart.rb +4 -0
- data/spec/factories/scraped_sites.rb +17 -3
- data/spec/fixtures/all.css +3 -0
- data/spec/fixtures/all.js +1 -0
- data/spec/fixtures/all_body.js +1 -0
- data/spec/fixtures/data.csv +1 -0
- data/spec/fixtures/index.html +7 -0
- data/spec/helpers/pageflow/chart/scraped_sites_helper_spec.rb +59 -0
- data/spec/integration/file_type_spec.rb +10 -0
- data/spec/jobs/pageflow/chart/scrape_site_job_spec.rb +14 -1
- data/spec/models/pageflow/chart/scraped_site_spec.rb +54 -0
- data/spec/pageflow/chart/downloader_spec.rb +13 -3
- data/spec/pageflow/chart/refresh_tag_following_downloader_spec.rb +23 -10
- data/spec/pageflow/chart/scraper_spec.rb +201 -63
- metadata +28 -20
- data/app/assets/javascripts/pageflow/chart/editor/collections/scraped_sites_collection.js +0 -23
- data/app/assets/javascripts/pageflow/chart/editor/initializers/setup_collections.js +0 -1
- data/app/assets/javascripts/pageflow/chart/editor/templates/scraped_site_status.jst.ejs +0 -2
- data/app/assets/javascripts/pageflow/chart/editor/templates/url_input.jst.ejs +0 -7
- data/app/assets/javascripts/pageflow/chart/editor/views/scraped_site_status_view.js +0 -18
- data/app/controllers/pageflow/chart/application_controller.rb +0 -6
- data/app/controllers/pageflow/chart/scraped_sites_controller.rb +0 -25
- data/config/routes.rb +0 -3
- data/spec/controllers/pageflow/chart/scraped_sites_controller_spec.rb +0 -35
- data/spec/requests/scraping_site_spec.rb +0 -23
@@ -8,7 +8,8 @@ module Pageflow
|
|
8
8
|
def perform_with_result(scraped_site,
|
9
9
|
_options = {},
|
10
10
|
downloader: downloader_for(scraped_site))
|
11
|
-
downloader.load_following_refresh_tags(scraped_site.url
|
11
|
+
downloader.load_following_refresh_tags(scraped_site.url,
|
12
|
+
raise_on_http_error: true) do |file|
|
12
13
|
scraper = Scraper.new(file.read, Chart.config.scraper_options)
|
13
14
|
scraped_site.html_file = StringIOWithContentType.new(
|
14
15
|
scraper.html,
|
@@ -16,11 +17,18 @@ module Pageflow
|
|
16
17
|
content_type: 'text/html'
|
17
18
|
)
|
18
19
|
|
19
|
-
downloader.load_all(scraper.
|
20
|
+
downloader.load_all(scraper.javascript_urls_in_head,
|
20
21
|
extension: '.js',
|
21
22
|
before_each: begin_try_catch,
|
22
|
-
after_each: end_try_catch) do |
|
23
|
-
scraped_site.javascript_file =
|
23
|
+
after_each: end_try_catch) do |javascript_head_file|
|
24
|
+
scraped_site.javascript_file = javascript_head_file
|
25
|
+
end
|
26
|
+
|
27
|
+
downloader.load_all(scraper.javascript_urls_in_body,
|
28
|
+
extension: '.js',
|
29
|
+
before_each: begin_try_catch,
|
30
|
+
after_each: end_try_catch) do |javascript_body_file|
|
31
|
+
scraped_site.javascript_body_file = javascript_body_file
|
24
32
|
end
|
25
33
|
|
26
34
|
downloader.load_all(scraper.stylesheet_urls,
|
@@ -35,6 +43,8 @@ module Pageflow
|
|
35
43
|
end
|
36
44
|
|
37
45
|
:ok
|
46
|
+
rescue Downloader::HTTPError
|
47
|
+
:error
|
38
48
|
end
|
39
49
|
|
40
50
|
private
|
@@ -1,12 +1,16 @@
|
|
1
1
|
module Pageflow
|
2
2
|
module Chart
|
3
3
|
class ScrapedSite < ActiveRecord::Base
|
4
|
+
include Pageflow::ReusableFile
|
5
|
+
|
4
6
|
has_attached_file :javascript_file, Chart.config.paperclip_options(extension: 'js')
|
7
|
+
has_attached_file :javascript_body_file, Chart.config.paperclip_options(basename: 'all_body', extension: 'js')
|
5
8
|
has_attached_file :stylesheet_file, Chart.config.paperclip_options(extension: 'css')
|
6
9
|
has_attached_file :html_file, Chart.config.paperclip_options(extension: 'html')
|
7
10
|
has_attached_file :csv_file, Chart.config.paperclip_options(basename: 'data', extension: 'csv')
|
8
11
|
|
9
12
|
do_not_validate_attachment_file_type(:javascript_file)
|
13
|
+
do_not_validate_attachment_file_type(:javascript_body_file)
|
10
14
|
do_not_validate_attachment_file_type(:stylesheet_file)
|
11
15
|
do_not_validate_attachment_file_type(:html_file)
|
12
16
|
do_not_validate_attachment_file_type(:csv_file)
|
@@ -23,6 +27,10 @@ module Pageflow
|
|
23
27
|
transition 'unprocessed' => 'processing'
|
24
28
|
end
|
25
29
|
|
30
|
+
event :skip_reprocessing_imported_site do
|
31
|
+
transition 'unprocessed' => 'processed'
|
32
|
+
end
|
33
|
+
|
26
34
|
event :reprocess do
|
27
35
|
transition 'processed' => 'processing'
|
28
36
|
transition 'processing_failed' => 'processing'
|
@@ -44,10 +52,6 @@ module Pageflow
|
|
44
52
|
URI.join(url, 'data.csv').to_s
|
45
53
|
end
|
46
54
|
|
47
|
-
def as_json(*)
|
48
|
-
super.merge(html_file_url: html_file_url)
|
49
|
-
end
|
50
|
-
|
51
55
|
def html_file_url
|
52
56
|
return unless html_file.try(:path)
|
53
57
|
if Chart.config.scraped_sites_root_url.present?
|
@@ -56,6 +60,35 @@ module Pageflow
|
|
56
60
|
html_file.url
|
57
61
|
end
|
58
62
|
end
|
63
|
+
|
64
|
+
# ReusableFile-overrides:
|
65
|
+
def url
|
66
|
+
read_attribute(:url)
|
67
|
+
end
|
68
|
+
|
69
|
+
def retryable?
|
70
|
+
processing_failed?
|
71
|
+
end
|
72
|
+
|
73
|
+
def ready?
|
74
|
+
processed?
|
75
|
+
end
|
76
|
+
|
77
|
+
def publish!
|
78
|
+
if html_file.present?
|
79
|
+
skip_reprocessing_imported_site!
|
80
|
+
else
|
81
|
+
process!
|
82
|
+
end
|
83
|
+
end
|
84
|
+
|
85
|
+
def retry!
|
86
|
+
reprocess!
|
87
|
+
end
|
88
|
+
|
89
|
+
def attachments_for_export
|
90
|
+
[javascript_file, javascript_body_file, stylesheet_file, html_file, csv_file]
|
91
|
+
end
|
59
92
|
end
|
60
93
|
end
|
61
94
|
end
|
@@ -0,0 +1 @@
|
|
1
|
+
json.call(scraped_site, :url, :html_file_url, :use_custom_theme)
|
@@ -7,9 +7,16 @@
|
|
7
7
|
|
8
8
|
<div class="content">
|
9
9
|
<div class="iframeWrapper">
|
10
|
-
<%= scraped_site_iframe(configuration
|
11
|
-
|
10
|
+
<%= scraped_site_iframe(configuration) %>
|
11
|
+
<%= third_party_embed_opt_in(
|
12
|
+
entry: entry,
|
13
|
+
vendor_name: 'datawrapper',
|
14
|
+
message: t('pageflow.public.chart.opt_in_prompt')
|
15
|
+
) %>
|
12
16
|
<div class="bigscreen_toggler" tabindex="4" title="<%= t('pageflow.public.chart.toggle') %>"><%= t('pageflow.public.chart.toggle') %></div>
|
17
|
+
<div class="opt_out_wrapper">
|
18
|
+
<%= third_party_embed_opt_out_info(entry) %>
|
19
|
+
</div>
|
13
20
|
</div>
|
14
21
|
<div class="scroller">
|
15
22
|
<div>
|
data/chart.gemspec
CHANGED
@@ -18,11 +18,11 @@ Gem::Specification.new do |spec|
|
|
18
18
|
|
19
19
|
spec.required_ruby_version = '~> 2.1'
|
20
20
|
|
21
|
-
spec.add_runtime_dependency 'pageflow', '~>
|
21
|
+
spec.add_runtime_dependency 'pageflow', '~> 15.7.x'
|
22
22
|
spec.add_runtime_dependency 'nokogiri', '~> 1.0'
|
23
23
|
spec.add_runtime_dependency 'pageflow-public-i18n', '~> 1.0'
|
24
24
|
|
25
|
-
spec.add_development_dependency 'pageflow-support', '~>
|
25
|
+
spec.add_development_dependency 'pageflow-support', '~> 15.x'
|
26
26
|
spec.add_development_dependency 'bundler', ['>= 1.0', '< 3']
|
27
27
|
spec.add_development_dependency 'rake', '~> 12.0'
|
28
28
|
spec.add_development_dependency 'rspec-rails', '~> 3.0'
|
data/config/locales/de.yml
CHANGED
@@ -31,6 +31,8 @@ de:
|
|
31
31
|
|
32
32
|
Typische Anwendungsbeispiele: Statistiken, Diagramme, Zahlen&Fakten
|
33
33
|
page_attributes:
|
34
|
+
chart_url:
|
35
|
+
label: Diagramm URL
|
34
36
|
full_width:
|
35
37
|
inline_help: Verbreitert das Diagramm, so dass es die maximal verfügbare Breite nutzt.
|
36
38
|
label: Gesamte Breite nutzen
|
@@ -39,3 +41,5 @@ de:
|
|
39
41
|
page_type_category_name: Daten und Diagramme
|
40
42
|
page_type_description: Einbindung von Diagrammen, die mit Datawrapper erstellt wurden
|
41
43
|
page_type_name: Diagramm
|
44
|
+
chart_embed_opt_in:
|
45
|
+
feature_name: Opt-In für Datawrapper Embeds
|
data/config/locales/en.yml
CHANGED
@@ -17,6 +17,8 @@ en:
|
|
17
17
|
menu_item: Chart
|
18
18
|
text: "# Chart\n\nIntegration of a Datawrapper-Diagram\n\nHere you can add animated infographics to your Pageflow. The diagram is embedded into a background-picture/video and text. To enlarge the graphic you simply have to click on it. \n\nBut first of all you have to create your graphic externally and generate a link. You can find examples and requirements for this under www.datawrapper.de.\n\nNote that Datawrapper offers a special layout option for charts that shall be embedded into a Pageflow: In the \"Visualize\" step of the chart creation wizard, click the \"Design\" tab and select the \"Pageflow\" layout. That way a color scheme is used which complements Pageflow's look.\n\nExamples of application: statistics, diagrams, numbers & facts"
|
19
19
|
page_attributes:
|
20
|
+
chart_url:
|
21
|
+
label: Chart URL
|
20
22
|
full_width:
|
21
23
|
inline_help: Extends the chart to use the maximum width available.
|
22
24
|
label: Use full width
|
@@ -25,3 +27,5 @@ en:
|
|
25
27
|
page_type_category_name: Data and Charts
|
26
28
|
page_type_description: Embedded Datawrapper chart
|
27
29
|
page_type_name: Chart
|
30
|
+
chart_embed_opt_in:
|
31
|
+
feature_name: Opt-in for Datawrapper embeds
|
@@ -0,0 +1,8 @@
|
|
1
|
+
class AddFileAttributesToScrapedSites < ActiveRecord::Migration[5.2]
|
2
|
+
def change
|
3
|
+
add_reference :pageflow_chart_scraped_sites, :entry, index: true
|
4
|
+
add_column :pageflow_chart_scraped_sites, :rights, :string
|
5
|
+
add_column :pageflow_chart_scraped_sites, :parent_file_id, :integer
|
6
|
+
add_column :pageflow_chart_scraped_sites, :parent_file_model_type, :string
|
7
|
+
end
|
8
|
+
end
|
@@ -0,0 +1,59 @@
|
|
1
|
+
class InsertFileUsagesForScrapedSites < ActiveRecord::Migration[5.2]
|
2
|
+
# Pageflow models might have gotten out of sync with schema at this
|
3
|
+
# point. Use local models instead.
|
4
|
+
class MigratedPage < ActiveRecord::Base
|
5
|
+
self.table_name = 'pageflow_pages'
|
6
|
+
|
7
|
+
belongs_to :chapter, class_name: 'MigratedChapter'
|
8
|
+
|
9
|
+
serialize :configuration, JSON
|
10
|
+
|
11
|
+
def configuration
|
12
|
+
super || {}
|
13
|
+
end
|
14
|
+
end
|
15
|
+
|
16
|
+
class MigratedChapter < ActiveRecord::Base
|
17
|
+
self.table_name = 'pageflow_chapters'
|
18
|
+
belongs_to :storyline, class_name: 'MigratedStoryline'
|
19
|
+
end
|
20
|
+
|
21
|
+
class MigratedStoryline < ActiveRecord::Base
|
22
|
+
self.table_name = 'pageflow_storylines'
|
23
|
+
end
|
24
|
+
|
25
|
+
class MigratedFileUsage < ActiveRecord::Base
|
26
|
+
self.table_name = 'pageflow_file_usages'
|
27
|
+
end
|
28
|
+
|
29
|
+
def up
|
30
|
+
MigratedPage.where(template: 'chart').find_each do |page|
|
31
|
+
scraped_site_id = page.configuration['scraped_site_id']
|
32
|
+
next unless scraped_site_id
|
33
|
+
|
34
|
+
scraped_site = Pageflow::Chart::ScrapedSite.find_by_id(scraped_site_id)
|
35
|
+
|
36
|
+
unless scraped_site
|
37
|
+
puts "Scraped site #{scraped_site_id} not found"
|
38
|
+
next
|
39
|
+
end
|
40
|
+
|
41
|
+
revision_id = page&.chapter&.storyline&.revision_id
|
42
|
+
|
43
|
+
unless revision_id
|
44
|
+
puts "No revision_id for page #{page.id}"
|
45
|
+
next
|
46
|
+
end
|
47
|
+
|
48
|
+
MigratedFileUsage.create(file_id: scraped_site.id,
|
49
|
+
file_type: 'Pageflow::Chart::ScrapedSite',
|
50
|
+
revision_id: revision_id)
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
def down
|
55
|
+
MigratedFileUsage
|
56
|
+
.where(file_type: 'Pageflow::Chart::ScrapedSite')
|
57
|
+
.delete_all
|
58
|
+
end
|
59
|
+
end
|
@@ -22,6 +22,7 @@ module Pageflow
|
|
22
22
|
#
|
23
23
|
# @param [Hash] opts
|
24
24
|
# @option opts [Array<Regexp>] :head_script_blacklist Script tags in page head are ignored if they match any of this list of regexes.
|
25
|
+
# @option opts [Array<Regexp>] :body_script_blacklist Script tags in page body are ignored if they match any of this list of regexes.
|
25
26
|
# @option opts [Array<Regexp>] :inline_script_blacklist Inline script tags are ignored if they match any of this list of regexes.
|
26
27
|
# @option opts [Array<String>] :selector_blacklist HTML-elements matched by selectors in this list will not be scraped.
|
27
28
|
# @return [Hash]
|
@@ -55,6 +56,7 @@ module Pageflow
|
|
55
56
|
def initialize
|
56
57
|
@scraper_options = {
|
57
58
|
head_script_blacklist: [/piwik/],
|
59
|
+
body_script_blacklist: [/piwik/],
|
58
60
|
inline_script_blacklist: [/piwik/],
|
59
61
|
selector_blacklist: ['body .noscript']
|
60
62
|
}
|
@@ -62,9 +64,10 @@ module Pageflow
|
|
62
64
|
@paperclip_base_path = ':pageflow_s3_root'
|
63
65
|
@scraped_sites_root_url = nil
|
64
66
|
@supported_hosts = [
|
65
|
-
'
|
66
|
-
'
|
67
|
-
'
|
67
|
+
'cf.datawrapper.de',
|
68
|
+
'charts.datawrapper.de',
|
69
|
+
'datawrapper.dwcdn.de',
|
70
|
+
'datawrapper.dwcdn.net'
|
68
71
|
]
|
69
72
|
@use_custom_theme = false
|
70
73
|
@datawrapper_themes_with_transparent_background_support = ['pageflow']
|
@@ -6,15 +6,18 @@ module Pageflow
|
|
6
6
|
class Downloader
|
7
7
|
attr_reader :options
|
8
8
|
|
9
|
+
class HTTPError < StandardError; end
|
10
|
+
|
9
11
|
def initialize(options = {})
|
10
12
|
@options = options
|
11
13
|
end
|
12
14
|
|
13
|
-
def load(url)
|
15
|
+
def load(url, raise_on_http_error: false)
|
14
16
|
file = open(make_absolute(url))
|
15
17
|
yield(file)
|
16
18
|
rescue OpenURI::HTTPError => exception
|
17
19
|
Rails.logger.error "Exception loading url #{url}: #{exception.message}"
|
20
|
+
raise(HTTPError) if raise_on_http_error
|
18
21
|
ensure
|
19
22
|
file.close if file
|
20
23
|
end
|
@@ -10,6 +10,23 @@ module Pageflow
|
|
10
10
|
def json_seed_template
|
11
11
|
'pageflow/chart/page_type.json.jbuilder'
|
12
12
|
end
|
13
|
+
|
14
|
+
def file_types
|
15
|
+
[Chart.scraped_site_file_type]
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
def self.scraped_site_file_type
|
20
|
+
FileType.new(model: ScrapedSite,
|
21
|
+
editor_partial: 'pageflow/chart/editor/scraped_sites/scraped_site',
|
22
|
+
custom_attributes: {
|
23
|
+
url: {
|
24
|
+
permitted_create_param: true
|
25
|
+
},
|
26
|
+
use_custom_theme: {
|
27
|
+
permitted_create_param: false
|
28
|
+
}
|
29
|
+
})
|
13
30
|
end
|
14
31
|
end
|
15
32
|
end
|
@@ -9,15 +9,15 @@ module Pageflow
|
|
9
9
|
class TooManyRedirects < StandardError; end
|
10
10
|
class NoUrlInRefreshMetaTag < StandardError; end
|
11
11
|
|
12
|
-
def load_following_refresh_tags(url, redirect_count = 0, &block)
|
13
|
-
load(url) do |file|
|
12
|
+
def load_following_refresh_tags(url, options = {}, redirect_count = 0, &block)
|
13
|
+
load(url, options) do |file|
|
14
14
|
if (redirect_url = find_refresh_meta_tag_url(file.read))
|
15
15
|
if redirect_count >= MAX_REDIRECT_COUNT
|
16
16
|
raise TooManyRedirects, 'Too many redirects via refresh meta tags.'
|
17
17
|
end
|
18
18
|
|
19
19
|
redirect_url = ensure_absolute(redirect_url, url)
|
20
|
-
return load_following_refresh_tags(redirect_url, redirect_count + 1, &block)
|
20
|
+
return load_following_refresh_tags(redirect_url, options, redirect_count + 1, &block)
|
21
21
|
end
|
22
22
|
|
23
23
|
file.rewind
|
@@ -3,7 +3,11 @@ require 'nokogiri'
|
|
3
3
|
module Pageflow
|
4
4
|
module Chart
|
5
5
|
class Scraper
|
6
|
-
attr_reader :document,
|
6
|
+
attr_reader :document,
|
7
|
+
:options,
|
8
|
+
:javascript_urls_in_head,
|
9
|
+
:javascript_urls_in_body,
|
10
|
+
:stylesheet_urls
|
7
11
|
|
8
12
|
def initialize(html, options = {})
|
9
13
|
@document = Nokogiri::HTML(html)
|
@@ -23,14 +27,21 @@ module Pageflow
|
|
23
27
|
private
|
24
28
|
|
25
29
|
def parse
|
26
|
-
parse_javascript_urls
|
30
|
+
parse_javascript_urls(:head)
|
31
|
+
parse_javascript_urls(:body)
|
27
32
|
parse_stylesheet_urls
|
28
33
|
end
|
29
34
|
|
30
|
-
def parse_javascript_urls
|
31
|
-
|
35
|
+
def parse_javascript_urls(container)
|
36
|
+
script_tags = filtered_script_tags_in(container).map do |tag|
|
32
37
|
tag[:src]
|
33
38
|
end
|
39
|
+
|
40
|
+
if container.eql?(:head)
|
41
|
+
@javascript_urls_in_head = script_tags
|
42
|
+
else
|
43
|
+
@javascript_urls_in_body = script_tags
|
44
|
+
end
|
34
45
|
end
|
35
46
|
|
36
47
|
def parse_stylesheet_urls
|
@@ -42,7 +53,8 @@ module Pageflow
|
|
42
53
|
def rewrite
|
43
54
|
filter_inline_scripts
|
44
55
|
filter_by_selectors
|
45
|
-
|
56
|
+
combine_script_tags_in(:head)
|
57
|
+
combine_script_tags_in(:body)
|
46
58
|
combine_css_link_tags
|
47
59
|
end
|
48
60
|
|
@@ -66,12 +78,12 @@ module Pageflow
|
|
66
78
|
end
|
67
79
|
end
|
68
80
|
|
69
|
-
def
|
70
|
-
script_tags_to_remove =
|
81
|
+
def combine_script_tags_in(container)
|
82
|
+
script_tags_to_remove = script_src_tags_in(container)
|
71
83
|
return if script_tags_to_remove.empty?
|
72
84
|
|
73
85
|
all_script_src_tag = Nokogiri::XML::Node.new('script', document)
|
74
|
-
all_script_src_tag[:src] = 'all.js'
|
86
|
+
all_script_src_tag[:src] = container.eql?(:head) ? 'all.js' : 'all_body.js'
|
75
87
|
all_script_src_tag[:type] = 'text/javascript'
|
76
88
|
|
77
89
|
script_tags_to_remove
|
@@ -91,16 +103,16 @@ module Pageflow
|
|
91
103
|
document.at_css('head') << all_css_link_tag
|
92
104
|
end
|
93
105
|
|
94
|
-
def
|
95
|
-
|
96
|
-
options.fetch(
|
106
|
+
def filtered_script_tags_in(container)
|
107
|
+
script_src_tags_in(container).reject do |tag|
|
108
|
+
options.fetch("#{container}_script_blacklist".to_sym, []).any? do |regexp|
|
97
109
|
tag[:src] =~ regexp
|
98
110
|
end
|
99
111
|
end
|
100
112
|
end
|
101
113
|
|
102
|
-
def
|
103
|
-
document.css(
|
114
|
+
def script_src_tags_in(container)
|
115
|
+
document.css("#{container} script[src]")
|
104
116
|
end
|
105
117
|
|
106
118
|
def css_link_tags
|
data/lib/pageflow/chart.rb
CHANGED
@@ -1,5 +1,19 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
1
|
+
module Pageflow
|
2
|
+
module Chart
|
3
|
+
FactoryBot.define do
|
4
|
+
factory :scraped_site, class: 'Pageflow::Chart::ScrapedSite' do
|
5
|
+
url { 'MyString' }
|
6
|
+
|
7
|
+
trait :processed do
|
8
|
+
state { 'processed' }
|
9
|
+
|
10
|
+
javascript_file { File.open(Engine.root.join('spec', 'fixtures', 'all.js')) }
|
11
|
+
javascript_body_file { File.open(Engine.root.join('spec', 'fixtures', 'all_body.js')) }
|
12
|
+
stylesheet_file { File.open(Engine.root.join('spec', 'fixtures', 'all.css')) }
|
13
|
+
html_file { File.open(Engine.root.join('spec', 'fixtures', 'index.html')) }
|
14
|
+
csv_file { File.open(Engine.root.join('spec', 'fixtures', 'data.csv')) }
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
4
18
|
end
|
5
19
|
end
|
@@ -0,0 +1 @@
|
|
1
|
+
var chart = {};
|
@@ -0,0 +1 @@
|
|
1
|
+
var chart_body = {};
|
@@ -0,0 +1 @@
|
|
1
|
+
some,values
|
@@ -0,0 +1,59 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
require 'pageflow/used_file_test_helper'
|
4
|
+
|
5
|
+
module Pageflow
|
6
|
+
module Chart
|
7
|
+
describe ScrapedSitesHelper do
|
8
|
+
include UsedFileTestHelper
|
9
|
+
|
10
|
+
before { Pageflow::Chart.config.use_custom_theme = false }
|
11
|
+
|
12
|
+
it 'renders iframe with data-src attribute for scraped site' do
|
13
|
+
scraped_site = create_used_file(:scraped_site, :processed)
|
14
|
+
|
15
|
+
html = scraped_site_iframe('scraped_site_id' => scraped_site.perma_id)
|
16
|
+
|
17
|
+
iframe = Capybara.string(html).find('iframe')
|
18
|
+
expect(iframe['data-src']).to match(%r{original/index\.html})
|
19
|
+
end
|
20
|
+
|
21
|
+
it 'renders no data-custom-theme attribute by default' do
|
22
|
+
scraped_site = create_used_file(:scraped_site, :processed)
|
23
|
+
|
24
|
+
html = scraped_site_iframe('scraped_site_id' => scraped_site.perma_id)
|
25
|
+
|
26
|
+
iframe = Capybara.string(html).find('iframe')
|
27
|
+
expect(iframe['data-use-custom-theme']).to be_blank
|
28
|
+
expect(iframe['data-customize-layout']).to eq('true')
|
29
|
+
end
|
30
|
+
|
31
|
+
it 'renders data-custom-theme if site has custom theme' do
|
32
|
+
Pageflow::Chart.config.use_custom_theme = true
|
33
|
+
scraped_site = create_used_file(:scraped_site, :processed)
|
34
|
+
|
35
|
+
html = scraped_site_iframe('scraped_site_id' => scraped_site.perma_id)
|
36
|
+
|
37
|
+
iframe = Capybara.string(html).find('iframe')
|
38
|
+
expect(iframe['data-use-custom-theme']).to eq('true')
|
39
|
+
expect(iframe['data-customize-layout']).to eq('true')
|
40
|
+
end
|
41
|
+
|
42
|
+
it 'renders iframe with data-src attribute for chart_url' do
|
43
|
+
html = scraped_site_iframe('chart_url' => 'https://example.com/chart')
|
44
|
+
|
45
|
+
iframe = Capybara.string(html).find('iframe')
|
46
|
+
expect(iframe['data-src']).to eq('//example.com/chart')
|
47
|
+
end
|
48
|
+
|
49
|
+
it 'renders no data-custom-theme attribute for chart_url' do
|
50
|
+
html = scraped_site_iframe('chart_url' => 'https://example.com/chart')
|
51
|
+
|
52
|
+
iframe = Capybara.string(html).find('iframe')
|
53
|
+
|
54
|
+
expect(iframe['data-customize-layout']).to be_blank
|
55
|
+
expect(iframe['data-use-custom-theme']).to be_blank
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
59
|
+
end
|
@@ -12,10 +12,23 @@ module Pageflow
|
|
12
12
|
|
13
13
|
allow(Scraper).to receive(:new).and_return(scraper)
|
14
14
|
|
15
|
-
expect(downloader).to receive(:load_following_refresh_tags)
|
15
|
+
expect(downloader).to receive(:load_following_refresh_tags)
|
16
|
+
.with('http://example.com',
|
17
|
+
raise_on_http_error: true)
|
16
18
|
|
17
19
|
job.perform_with_result(scraped_site, {}, downloader: downloader)
|
18
20
|
end
|
21
|
+
|
22
|
+
it 'returns :error on HTTP error' do
|
23
|
+
job = ScrapeSiteJob.new
|
24
|
+
scraped_site = create(:scraped_site, url: 'http://example.com/a')
|
25
|
+
|
26
|
+
stub_request(:get, 'http://example.com/a').to_return(status: 404, body: '')
|
27
|
+
|
28
|
+
result = job.perform_with_result(scraped_site)
|
29
|
+
|
30
|
+
expect(result).to eq(:error)
|
31
|
+
end
|
19
32
|
end
|
20
33
|
end
|
21
34
|
end
|