-
Notifications
You must be signed in to change notification settings - Fork 13
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'master' into feature/osci_scraper
- Loading branch information
Showing
8 changed files
with
209 additions
and
12 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,52 @@ | ||
require 'open-uri' | ||
require 'csv' | ||
require 'nokogiri' | ||
|
||
module Ingestors | ||
class DccIngestor < Ingestor | ||
def self.config | ||
{ | ||
key: 'dcc_event', | ||
title: 'DCC Events API', | ||
category: :events | ||
} | ||
end | ||
|
||
def read(url) | ||
begin | ||
process_dcc(url) | ||
rescue Exception => e | ||
@messages << "#{self.class.name} failed with: #{e.message}" | ||
end | ||
|
||
# finished | ||
nil | ||
end | ||
|
||
private | ||
|
||
def process_dcc(url) | ||
event_page = Nokogiri::HTML5.parse(open_url(url.to_s, raise: true)).css("div[class='archive__content grid']")[0].css("div[class='column span-4-sm span-8-md span-6-lg']") | ||
event_page.each do |event_data| | ||
event = OpenStruct.new | ||
|
||
event.url = event_data.css("h2[class='post-item__title h5']")[0].css("a")[0].get_attribute('href') | ||
event.title = event_data.css("h2[class='post-item__title h5']")[0].css("a")[0].text.strip | ||
|
||
start_str = event_data.css("ul[class='post-item__meta']")[0].css("li")[0].text.strip.split('—') | ||
event.start = Time.zone.parse(start_str[0]) | ||
event.end = Time.zone.parse(start_str[0]).beginning_of_day + Time.zone.parse(start_str[1]).seconds_since_midnight.seconds | ||
|
||
event.venue = event_data.css("ul[class='post-item__meta']")[0].css("li")[1].text.strip | ||
|
||
event.source = 'DCC' | ||
event.timezone = 'Amsterdam' | ||
event.set_default_times | ||
|
||
add_event(event) | ||
rescue Exception => e | ||
@messages << "Extract event fields failed with: #{e.message}" | ||
end | ||
end | ||
end | ||
end |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,58 @@ | ||
require 'test_helper' | ||
|
||
class DccIngestorTest < ActiveSupport::TestCase | ||
setup do | ||
@user = users(:regular_user) | ||
@content_provider = content_providers(:another_portal_provider) | ||
mock_ingestions | ||
mock_timezone # System time zone should not affect test result | ||
end | ||
|
||
teardown do | ||
reset_timezone | ||
end | ||
|
||
test 'can ingest events from dcc' do | ||
source = @content_provider.sources.build( | ||
url: 'https://dcc-po.nl/agenda/', | ||
method: 'dcc', | ||
enabled: true | ||
) | ||
|
||
ingestor = Ingestors::DccIngestor.new | ||
|
||
# check event doesn't | ||
new_title = "DCC-PO dag" | ||
new_url = 'https://dcc-po.nl/agenda/dcc-po-dag/' | ||
refute Event.where(title: new_title, url: new_url).any? | ||
|
||
# run task | ||
assert_difference 'Event.count', 1 do | ||
freeze_time(2019) do | ||
VCR.use_cassette("ingestors/dcc") do | ||
ingestor.read(source.url) | ||
ingestor.write(@user, @content_provider) | ||
end | ||
end | ||
end | ||
|
||
assert_equal 1, ingestor.events.count | ||
assert ingestor.materials.empty? | ||
assert_equal 1, ingestor.stats[:events][:added] | ||
assert_equal 0, ingestor.stats[:events][:updated] | ||
assert_equal 0, ingestor.stats[:events][:rejected] | ||
|
||
# check event does exist | ||
event = Event.where(title: new_title, url: new_url).first | ||
assert event | ||
assert_equal new_title, event.title | ||
assert_equal new_url, event.url | ||
|
||
# check other fields | ||
assert_equal 'DCC', event.source | ||
assert_equal 'Amsterdam', event.timezone | ||
assert_equal Time.zone.parse('Mon, 09 Oct 2019 10:00:00.000000000 UTC +00:00'), event.start | ||
assert_equal Time.zone.parse('Mon, 09 Oct 2019 16:30:00.000000000 UTC +00:00'), event.end | ||
assert_equal 'Domstad, Utrecht', event.venue | ||
end | ||
end |
Large diffs are not rendered by default.
Oops, something went wrong.