This repository has been archived by the owner on Jun 5, 2019. It is now read-only.
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #2 from LoveMyData/master
updated scraper
- Loading branch information
Showing
5 changed files
with
131 additions
and
34 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,10 @@ | ||
# It's easy to add more libraries or choose different versions. Any libraries | ||
# specified here will be installed and made available to your morph.io scraper. | ||
# Find out more: https://morph.io/documentation/ruby | ||
|
||
source "https://rubygems.org" | ||
|
||
ruby "2.4.1" | ||
|
||
gem "scraperwiki", git: "https://github.com/openaustralia/scraperwiki-ruby.git", branch: "morph_defaults" | ||
gem "mechanize" |
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 +1,55 @@ | ||
GIT | ||
remote: https://github.com/openaustralia/scraperwiki-ruby.git | ||
revision: fc50176812505e463077d5c673d504a6a234aa78 | ||
branch: morph_defaults | ||
specs: | ||
scraperwiki (3.0.1) | ||
httpclient | ||
sqlite_magic | ||
|
||
GEM | ||
remote: https://rubygems.org/ | ||
specs: | ||
domain_name (0.5.20170404) | ||
unf (>= 0.0.5, < 1.0.0) | ||
http-cookie (1.0.3) | ||
domain_name (~> 0.5) | ||
httpclient (2.8.3) | ||
mechanize (2.7.5) | ||
domain_name (~> 0.5, >= 0.5.1) | ||
http-cookie (~> 1.0) | ||
mime-types (>= 1.17.2) | ||
net-http-digest_auth (~> 1.1, >= 1.1.1) | ||
net-http-persistent (~> 2.5, >= 2.5.2) | ||
nokogiri (~> 1.6) | ||
ntlm-http (~> 0.1, >= 0.1.1) | ||
webrobots (>= 0.0.9, < 0.2) | ||
mime-types (3.1) | ||
mime-types-data (~> 3.2015) | ||
mime-types-data (3.2016.0521) | ||
mini_portile2 (2.3.0) | ||
net-http-digest_auth (1.4.1) | ||
net-http-persistent (2.9.4) | ||
nokogiri (1.8.1) | ||
mini_portile2 (~> 2.3.0) | ||
ntlm-http (0.1.1) | ||
sqlite3 (1.3.13) | ||
sqlite_magic (0.0.6) | ||
sqlite3 | ||
unf (0.1.4) | ||
unf_ext | ||
unf_ext (0.0.7.4) | ||
webrobots (0.1.2) | ||
|
||
PLATFORMS | ||
ruby | ||
|
||
DEPENDENCIES | ||
mechanize | ||
scraperwiki! | ||
|
||
RUBY VERSION | ||
ruby 2.4.1p111 | ||
|
||
BUNDLED WITH | ||
1.15.1 |
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 +1,17 @@ | ||
# City of Gold Coast Council Scraper | ||
|
||
This Council involves the followings | ||
|
||
* Server - Masterview, ApplicationMaster | ||
* Cookie - Yes | ||
* Scrape detail page - No | ||
* Clearly defined data within a row - Yes | ||
* JavaScript - Yes - doPostBack | ||
|
||
Setup MORPH_PERIOD for data recovery, available options are | ||
|
||
* thisweek (default) | ||
* thismonth | ||
* lastmonth | ||
|
||
Enjoy |
This file was deleted.
Oops, something went wrong.
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 |
---|---|---|
@@ -1,63 +1,79 @@ | ||
require 'scraperwiki' | ||
require 'mechanize' | ||
|
||
starting_url = 'http://pdonline.goldcoast.qld.gov.au/masterview/modules/ApplicationMaster/default.aspx?page=found&1=thismonth&4a=BLD%27,%27MCU%27,%27OPW%27,%27ROL&6=F' | ||
comment_url = 'mailto:gcccmail@goldcoast.qld.gov.au?subject=' | ||
case ENV['MORPH_PERIOD'] | ||
when 'thismonth' | ||
period = 'thismonth' | ||
when 'lastmonth' | ||
period = 'lastmonth' | ||
else | ||
period = 'thisweek' | ||
end | ||
puts "Getting '" + period + "' data, changable via MORPH_PERIOD environment"; | ||
|
||
starting_url = 'http://pdonline.goldcoast.qld.gov.au/masterview/modules/ApplicationMaster/default.aspx?page=found&1=' +period+ '&4a=BLD%27,%27MCU%27,%27OPW%27,%27ROL&6=F' | ||
comment_url = 'mailto:gcccmail@goldcoast.qld.gov.au' | ||
|
||
def clean_whitespace(a) | ||
a.gsub("\r", ' ').gsub("\n", ' ').squeeze(" ").strip | ||
end | ||
|
||
# Extending Mechanize Form to support doPostBack | ||
# http://scraperblog.blogspot.com.au/2012/10/asp-forms-with-dopostback-using-ruby.html | ||
class Mechanize::Form | ||
def postback target, argument | ||
self['__EVENTTARGET'], self['__EVENTARGUMENT'] = target, argument | ||
submit | ||
end | ||
end | ||
|
||
def scrape_table(doc, comment_url) | ||
doc.search('table tbody tr').each do |tr| | ||
# Columns in table | ||
# Show Number Submitted Details | ||
tds = tr.search('td') | ||
h = tds.map{|td| td.inner_html} | ||
|
||
record = { | ||
'info_url' => (doc.uri + tds[0].at('a')['href']).to_s, | ||
'comment_url' => comment_url + CGI::escape("Development Application Enquiry: " + clean_whitespace(h[1])), | ||
'council_reference' => clean_whitespace(h[1]), | ||
'date_received' => Date.strptime(clean_whitespace(h[2]), '%d/%m/%Y').to_s, | ||
'address' => clean_whitespace(tds[3].at('b').inner_text), | ||
'address' => clean_whitespace(tds[3].at('b').inner_text) + ' QLD', | ||
'description' => CGI::unescapeHTML(clean_whitespace(h[3].split('<br>')[1..-1].join.gsub(/<\/?b>/,''))), | ||
'date_scraped' => Date.today.to_s | ||
'info_url' => (doc.uri + tds[0].at('a')['href']).to_s, | ||
'comment_url' => comment_url, | ||
'date_scraped' => Date.today.to_s, | ||
'date_received' => Date.strptime(clean_whitespace(h[2]), '%d/%m/%Y').to_s | ||
} | ||
|
||
if (ScraperWiki.select("* from data where `council_reference`='#{record['council_reference']}'").empty? rescue true) | ||
puts "Saving record " + record['council_reference'] + ", " + record['address'] | ||
# puts record | ||
ScraperWiki.save_sqlite(['council_reference'], record) | ||
else | ||
puts "Skipping already saved record " + record['council_reference'] | ||
end | ||
end | ||
end | ||
|
||
def scrape_and_follow_next_link(doc, comment_url) | ||
scrape_table(doc, comment_url) | ||
nextButton = doc.at('.rgPageNext') | ||
unless nextButton.nil? || nextButton['onclick'] =~ /return false/ | ||
form = doc.forms.first | ||
|
||
# The joy of dealing with ASP.NET | ||
form['__EVENTTARGET'] = nextButton['name'] | ||
form['__EVENTARGUMENT'] = '' | ||
# It doesn't seem to work without these stupid values being set. | ||
# Would be good to figure out where precisely in the javascript these values are coming from. | ||
form['ctl00%24RadScriptManager1']= | ||
'ctl00%24cphContent%24ctl00%24ctl00%24cphContent%24ctl00%24Radajaxpanel2Panel%7Cctl00%24cphContent%24ctl00%24ctl00%24RadGrid1%24ctl00%24ctl03%24ctl01%24ctl10' | ||
form['ctl00_RadScriptManager1_HiddenField']= | ||
'%3B%3BSystem.Web.Extensions%2C%20Version%3D3.5.0.0%2C%20Culture%3Dneutral%2C%20PublicKeyToken%3D31bf3856ad364e35%3Aen-US%3A0d787d5c-3903-4814-ad72-296cea810318%3Aea597d4b%3Ab25378d2%3BTelerik.Web.UI%2C%20Version%3D2009.1.527.35%2C%20Culture%3Dneutral%2C%20PublicKeyToken%3D121fae78165ba3d4%3Aen-US%3A1e3fef00-f492-4ed8-96ce-6371bc241e1c%3A16e4e7cd%3Af7645509%3A24ee1bba%3Ae330518b%3A1e771326%3Ac8618e41%3A4cacbc31%3A8e6f0d33%3Aed16cbdc%3A58366029%3Aaa288e2d' | ||
doc = form.submit(form.button_with(:name => nextButton['name'])) | ||
scrape_and_follow_next_link(doc, comment_url) | ||
end | ||
end | ||
|
||
agent = Mechanize.new | ||
|
||
# Jump through bollocks agree screen | ||
doc = agent.get(starting_url) | ||
doc = doc.forms.first.submit(doc.forms.first.button_with(:value => "Agree")) | ||
doc = agent.get(starting_url) | ||
|
||
scrape_and_follow_next_link(doc, comment_url) | ||
scrape_table(doc, comment_url) | ||
|
||
# Is there more than a page? | ||
begin | ||
totalPages = doc.at('div .rgInfoPart').inner_text.split(' items in ')[1].split(' pages')[0].to_i | ||
rescue | ||
totalPages = 1 | ||
end | ||
|
||
# run a loop if there are more than a page | ||
(2..totalPages).each do |i| | ||
puts "scraping for page " + i.to_s + " of " + totalPages.to_s + " pages" | ||
|
||
nextButton = doc.at('.rgPageNext') | ||
target, argument = nextButton[:onclick].scan(/'([^']*)'/).flatten | ||
doc = doc.form.postback target, argument | ||
scrape_table(doc, comment_url) | ||
i += i | ||
end |