Class: MyUniversalJobsMatch
- Inherits:
-
Object
- Object
- MyUniversalJobsMatch
- Defined in:
- lib/myuniversaljobsmatch.rb
Instance Method Summary collapse
- #dynarex ⇒ Object
-
#initialize(filepath: '') ⇒ MyUniversalJobsMatch
constructor
A new instance of MyUniversalJobsMatch.
- #query(id) ⇒ Object
-
#search(title: '', where: '', results_per_page: nil, sort_by: nil, hours: nil, contract_type: nil) ⇒ Object
options: results_per_page: 10, 25, 50 sort_by: date, highest_salary, lowest_salary hours: any, full_time, part_time contract_type: any, permanent, temporary, contract, apprenticeship.
Constructor Details
#initialize(filepath: '') ⇒ MyUniversalJobsMatch
Returns a new instance of MyUniversalJobsMatch.
24 25 26 27 28 29 30 31 32 33 |
# File 'lib/myuniversaljobsmatch.rb', line 24 def initialize(filepath: '') @filepath = filepath @url_base = 'https://findajob.dwp.gov.uk/' @dx = Dynarex.new 'ujm[title,tags]/item(job_id, title, ' + \ 'description, posting_date, company, location, industries, job_type)' end |
Instance Method Details
#dynarex ⇒ Object
35 36 37 |
# File 'lib/myuniversaljobsmatch.rb', line 35 def dynarex() @dx end |
#query(id) ⇒ Object
115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 |
# File 'lib/myuniversaljobsmatch.rb', line 115 def query(id) doc = Nokorexi.new(@url_base + 'details/' + id).to_doc title = doc.root.text('head/title') rows = doc.root.xpath('//table[1]/tbody/tr') h = rows.map do |tr| [ tr.text('th').downcase.rstrip[0..-2].gsub(/ +/,'_').to_sym, tr.text('td').to_s ] end.to_h h[:description] = doc.root.element('//div[@itemprop="description"]').xml\ .gsub(/<br *\/> */,"\n").gsub(/<\/?[^\>]+\/?>/,'').strip h[:posting_date] = h[:posting_date].to_date h[:closing_date] = h[:closing_date].to_date {title: title}.merge(h) end |
#search(title: '', where: '', results_per_page: nil, sort_by: nil, hours: nil, contract_type: nil) ⇒ Object
options:
results_per_page: 10, 25, 50
sort_by: date, highest_salary, lowest_salary
hours: any, full_time, part_time
contract_type: any, permanent, temporary, contract, apprenticeship
45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
# File 'lib/myuniversaljobsmatch.rb', line 45 def search(title: '', where: '', results_per_page: nil, sort_by: nil, hours: nil, contract_type: nil) params = { adv: 1, q: title, w: where } params[:pp] = results_per_page if results_per_page params[:cty] = contract_type if contract_type params[:cti] = hours if hours if sort_by then case sort_by.to_sym when :date params[:sb] = :date params[:sd] = :down when :highest_salary params[:sb] = :salary params[:sd] = :down when :lowest_salary params[:sb] = :salary params[:sd] = :up end end url = @url_base + 'search/?' + params.map {|x| x.join('=') }.join('&') doc = Nokorexi.new(url).to_doc rows = doc.root.xpath('//div[@class="search-result"]') a = rows.map do |row| items = row.xpath('ul/li') joburl = row.element('h3/a/@href').to_s jobtitle = row.element('h3/a/text()') jobid = joburl[/\d+$/] jobref = title[/^\d+/].to_s date = items[0].text.to_date company = items[1].text('strong') location = items[1].element('span/text()') salary = items[2].text('strong') if items[2] desc = row.text('p').strip [jobid, jobref, date, jobtitle, joburl, company, location, salary, desc] end dx = Dynarex.new('vacancies[title, desc, date, time, tags, xslt]/' + \ 'vacancy(job_id, job_ref, date, title, url, company, location, salary, desc)') dx.title = "Find a job - Search results for '#{title}'" dx.desc = "generated from web scrape of Find a job." + \ "findajob.dwp.gov.uk/; source: " + url dx. = 'jobs vacancies jobmatch ' + title.split.first dx.date = Time.now.strftime("%Y-%b-%d") dx.time = Time.now.strftime("%H:%M") a.each do |row| dx.create Hash[(%i(job_id job_ref date title url company) + \ %i(location salary desc)).zip(row)] end return dx end |