parse_patriot_web.rb 5.57 KB
Newer Older
Michael Bailey's avatar
Michael Bailey committed
1 2 3 4 5 6 7
# frozen_string_literal: true

require 'thwait'
require 'httparty'
require 'nokogiri'
require 'json'

Zac Wood's avatar
Zac Wood committed
8 9 10 11 12 13 14 15 16 17 18
#
#     USAGE:
#
#     Just run it and it dynamically dumps the latest semester. There's a bit to do it for all of the ones in history commented out below but it'll thrash your RAM and probably piss off PatriotWeb. Also note this script could be trivially modified to correlate human readable names to semester IDs since they're just the .text attribute of the option node.
#
#     There's a few minor issues like multiple spaces in teacher names and we could be scraping out email addresses but no major ones.
#
#     DISCLAIMER/WARNING:
#
#     This opens a number of connections pretty transparently from a script to PatriotWeb. I am not liable if you run this a million times and somehow kill over PatriotWeb. It's a scraper, not a DoS utility.
#
Michael Bailey's avatar
Michael Bailey committed
19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42

# Credit stackoverflow
class String
  def alpha?
    !!match(/^[[:alpha:]]+$/)
  end
end

def get_details(data, titledetails, titledata)
  crn = titledetails[1].strip
  data[crn] = {} unless data[titledetails[1]]
  crsinfo = { 'name': titledetails[0].strip }
  uniquedata = { 'sect': titledetails[3].strip, 'crn': titledetails[1].strip }
  general = { 'subj': titledata[0].strip, 'code': titledata[1].strip }
  data[crn] = general.merge(uniquedata.merge(crsinfo))
  data[crn][:code] = titledetails[2].split(' ')[1]
  [data, data[crn]]
end

def sort_item(item, currentobj, data)
  if item.name == 'th'
    if item.to_html.include? '-'
      titletxt = item.text
      if item.text.include? ' - Honors'
Zac Wood's avatar
Zac Wood committed
43
        titletxt = titletxt.gsub(' - Honors', ' (Honors)')
Michael Bailey's avatar
Michael Bailey committed
44 45 46
      end
      titledetails = titletxt.split(' - ')
      if titledetails.count > 4
Zac Wood's avatar
Zac Wood committed
47
        titledetails = ["#{titledetails[0]} #{titledetails[1]}", titledetails[2], titledetails[3], titledetails[4]]
Michael Bailey's avatar
Michael Bailey committed
48 49 50 51 52
      end
      titledata = titledetails[2].split(' ')
      begin
        data = get_details(data, titledetails, titledata)[0]
        currentobj = get_details(data, titledetails, titledata)[1]
Zac Wood's avatar
Zac Wood committed
53
      rescue StandardError => e
Michael Bailey's avatar
Michael Bailey committed
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
        puts item
        puts e
        exit(1)
      end
      currentobj[:fields] = []
    end
  elsif item.is_a? Nokogiri::XML::Element
    item.css('th').each do |field|
      currentobj[:fields].push(field.text.downcase.tr(' ', '_'))
    end
    iter = 0
    if currentobj
      if currentobj[:fields]
        upper = currentobj[:fields].count - 1
        while iter <= upper
          assign = item.css('td')[iter].text
          currentobj[currentobj[:fields][iter]] = assign
          iter += 1
        end
      end
    end
  end
  currentobj
end

def feed_course_info(searcher)
  table = searcher.css('html body div.pagebodydiv table.datadisplaytable')
  data = {}
  currentobj = nil
  table.css('table.datadisplaytable').first.children.each do |row|
    next unless row.name == 'tr'
    row.children.each do |item|
      currentobj = sort_item(item, currentobj, data)
    end
  end
  data
end

def get_crn(title, code, section)
  puts "TODO #{title} #{code} #{section}"
end

def full_major(major)
Zac Wood's avatar
Zac Wood committed
97 98 99 100 101 102
  resp = HTTParty.post('https://patriotweb.gmu.edu/pls/prod/bwckschd.p_get_crse_unsec',
                       body: "term_in=201870&sel_subj=dummy&sel_day=dummy&sel_schd=dummy&sel_insm=dummy&sel_camp=dummy&sel_levl=dummy&sel_sess=dummy&sel_instr=dummy&sel_ptrm=dummy&sel_attr=dummy&sel_subj=#{major}&sel_crse=&sel_title=&sel_schd=%25&sel_from_cred=&sel_to_cred=&sel_camp=%25&sel_levl=%25&sel_ptrm=%25&sel_instr=%25&begin_hh=0&begin_mi=0&begin_ap=x&end_hh=0&end_mi=0&end_ap=x",
                       headers: {
                         'Content-Type' => 'application/x-www-form-urlencoded',
                         'charset' => 'utf-8'
                       })
Michael Bailey's avatar
Michael Bailey committed
103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
  searcher = Nokogiri::HTML(resp)
  data = feed_course_info(searcher)
end

def initialize_req(subj, num)
  base_url = 'https://patriotweb.gmu.edu/pls/prod/bwckctlg.p_disp_listcrse?term_in=201870'
  stub = "subj_in=#{subj}&crse_in=#{num}&schd_in=%25"
  resp = HTTParty.get("#{base_url}&#{stub}")
  searcher = Nokogiri::HTML(resp)
  data = feed_course_info(searcher)
end

def getSemesters
  semesters = []
  resp = HTTParty.get('https://patriotweb.gmu.edu/pls/prod/bwckschd.p_disp_dyn_sched')
  searcher = Nokogiri::HTML(resp)
  searcher.css('option').each do |opt|
    if opt.attr('value').start_with? '20'
      semesters.push(opt.attr('value'))
    end
  end
  semesters
end

def getCourses(semester)
  semesters = []
Zac Wood's avatar
Zac Wood committed
129 130 131 132 133 134
  resp = HTTParty.post('https://patriotweb.gmu.edu/pls/prod/bwckgens.p_proc_term_date',
                       body: "p_calling_proc=bwckschd.p_disp_dyn_sched&p_term=#{semester}&p_by_date=Y&p_from_date=&p_to_date=",
                       headers: {
                         'Content-Type' => 'application/x-www-form-urlencoded',
                         'charset' => 'utf-8'
                       })
Michael Bailey's avatar
Michael Bailey committed
135
  searcher = Nokogiri::HTML(resp)
Zac Wood's avatar
Zac Wood committed
136
  #  puts searcher.inspect
Michael Bailey's avatar
Michael Bailey committed
137 138 139 140 141 142 143 144
  searcher.xpath('//*[@id="subj_id"]/option').each do |opt|
    if opt.attr('value').strip.alpha?
      semesters.push(opt.attr('value'))
    end
  end
  semesters
end

Zac Wood's avatar
Zac Wood committed
145
# Initialize threads to be waited on array
Michael Bailey's avatar
Michael Bailey committed
146 147 148
threads = []

total = {}
Zac Wood's avatar
Zac Wood committed
149 150 151 152 153 154 155 156 157
# below will get you literally all semesters which is wildly overkill
# getSemesters.each do |semester|
semester = getSemesters.first
getCourses(semester).each do |course|
  threads << Thread.new {
    total[course] = full_major(course)
  }
end
# end
Michael Bailey's avatar
Michael Bailey committed
158 159 160

ThreadsWait.all_waits(*threads)

Zac Wood's avatar
Zac Wood committed
161 162 163 164 165 166 167 168 169 170 171 172 173 174
# total.each { |subject|
#   puts subject.first
#   subject[1].each { |section|
#     puts section
#   }
# }

total.each { |subject|
  subject[1].each { |crn|
    section = crn[1]
    puts section
    # puts "#{section[:subj]} #{section[:code]} #{section[:sect]} #{section[:name]}"
  }
}