RusaMember 1.0.0 → 1.0.1

data/Manifest.txt

@@ -3,4 +3,28 @@ Manifest.txt
 README.txt
 Rakefile
 bin/rusa_member
+lib/member.rb
+lib/parse_member.rb
+lib/parse_result.rb
 lib/rusa_member.rb
+test/files/boston.html
+test/files/clubMembers.txt
+test/files/doe.txt
+test/files/dussler.html
+test/files/dussler.txt
+test/files/dussler_results_2006.html
+test/files/dussler_results_2007.html
+test/files/dussler_results_2008.html
+test/files/member_pre.txt
+test/files/member_search.txt
+test/files/multiSmith.txt
+test/files/no_results.html
+test/files/one_result.html
+test/files/post.txt
+test/files/smith.html
+test/files/smith.txt
+test/files/thomas.html
+test/files/thomas_results_2008.html
+test/html_frags.rb
+test/test_parse_member.rb
+test/test_parse_results.rb

data/README.txt

@@ -12,8 +12,11 @@ Extract data from RUSA web site to get members information, results, awards
 * FIX (list of features or problems)
 
 == SYNOPSIS:
-
-  FIX (code sample of usage)
+print membership information, current year results for member 136
+  bin/rusa_member --id 136
+  
+print membership information, 2003 and 2007 results for Peter Dusel
+  bin/rusa_member --lname dusel --year 2003,2007
 
 == REQUIREMENTS:
 
@@ -21,7 +24,7 @@ Extract data from RUSA web site to get members information, results, awards
 
 == INSTALL:
 
-* FIX (sudo gem install, anything else)
+sudo gem install RusaMember
 
 == LICENSE:
 

data/Rakefile

@@ -13,5 +13,4 @@ Hoe.new('RusaMember', RusaMember::VERSION) do |p|
    
 end
 
-#task :gem => 'test'
 # vim: syntax=Ruby

data/bin/rusa_member

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby -w
+
+require 'rubygems'
+require 'lib/parse_member'
+
+ParseMember.run

data/lib/member.rb

@@ -0,0 +1,71 @@
+#!/usr/bin/env ruby
+
+##
+# collection of people in the club
+class Members < Hash
+  
+  def << person
+    self[person.id.to_i] = person
+  end
+  
+  def find_by_id id
+    self[id]
+  end
+  
+end
+
+class Person
+  ATTRIBUTES =  
+[:first_name, :last_name, :id, :member_expiration_date, :club, :results, :awards]
+  attr_accessor(*ATTRIBUTES)
+
+  def initialize meta = nil
+    ## I was trying to avoid initializing an ivar in the do loop
+    ## if it had already been initialized, but couldn't figure out how to do that
+    ## 
+    ## I was trying to make this work without having to init the array and hash
+    ## after the do loop
+    #@results = []
+    #@awards = {}
+    #ATTRIBUTES.find_all{|a| self.a.nil?}.each do |item| <-- does not work
+    #
+    # the 'unless' below does work but doesn't look right
+
+    @results = []
+    @awards = {}
+    
+    ATTRIBUTES.each do |item|
+      self.send("#{item}=", (meta[item] || "")) unless item == :results or item == :awards
+    end if meta
+
+  end
+  
+end
+
+##
+# the result of an event that the member participated in
+class Result
+  ATTRIBUTES = [ :certificate, :date, :distance, :organizer, :type ]
+  attr_accessor(*ATTRIBUTES)
+
+  def initialize meta = nil
+    ATTRIBUTES.each do |item|
+      self.send("#{item}=", (meta[item] || ""))
+    end if meta
+  end
+
+end
+
+##
+# awards for total distance, number of events
+class Award
+  ATTRIBUTES = [ :type, :year ]
+  attr_accessor(*ATTRIBUTES)
+  
+  def initialize meta = nil
+    ATTRIBUTES.each do |item|
+      self.send("#{item}=", (meta[item] || ""))
+    end if meta
+  end
+  
+end

data/lib/parse_member.rb

@@ -0,0 +1,164 @@
+#!/usr/bin/env ruby -w
+
+##
+# Student Name: bill dussler
+# Homework Week: 8
+#
+# screen scrape data from a web site, parse content
+# and instatntiate club member information
+#
+require 'rubygems'
+require 'nokogiri'
+require 'net/http'
+require 'optparse'
+require 'time'
+require 'lib/member'
+require 'lib/parse_result'
+
+class ParseMember
+  attr_accessor :members, :options, :url, :parse_result
+
+  MEMBER_QUERY_URL = 'http://www.rusa.org/cgi-bin/membersearch_PF.pl'
+
+  # match parm key with parameter we will pass
+  PARMS = {'clubs' => 'club',
+           'ids' => 'mid',
+           'lnames' => 'sname'}
+  
+  def self.run
+    pm = ParseMember.new
+    pm.run
+    pm.report
+
+  end
+  
+  def initialize
+    @members = Members.new
+    @url = MEMBER_QUERY_URL
+    @parse_result = ParseResult.new
+
+    # The options specified on the command line will be collected in *options*.
+    # We set default values here.
+    @options = {}
+    @options['status'] = 'current'
+    @options['year'] = [Time.now.year]
+
+    opts = OptionParser.new do |opts|
+      opts.banner = "Usage: parse_member.rb [options]"
+
+      # include these clubs
+      opts.on("--club seattle,oregon,boston", Array, "include the following clubs") do |list|
+        @options['clubs'] = list
+      end
+      # include membership ids
+      opts.on("--id 137,2245,2157", Array, "include the following membership ids") do |list|
+        @options['ids'] = list
+      end
+
+      # include these last names
+      opts.on("--lname smith,jones,brown", Array, "Include members with the following last names") do |list|
+        @options['lnames'] = list
+      end
+
+      # get results for these years
+      opts.on("--year ", Array, "get results for the following years. Defaults to current year") do |list|
+        @options['year'] = list
+      end
+
+      # Boolean switch. default is current members (no expired memberships)
+      opts.on("-a",  "Current and past members") do |a|
+        @options['status'] = a ? 'all' : 'current'
+      end
+
+      # No argument, shows at tail.  This will print an options summary.
+      opts.on_tail("-h", "--help", "Show this message") do
+        puts opts
+        exit
+      end
+    end
+
+    opts.parse!(ARGV)
+
+  end
+
+  def run &block
+    if block_given? then
+      doc = fetch(@url, {}, &block)
+      parse(doc, &block)
+
+    else
+      # get requested parms  and fetch url with them
+      parms = {'status' => @options['status']}
+      PARMS.each do |key, parm|
+        next if @options[key].nil?
+        @options[key].each do |value|
+          parms[parm] = value
+          doc = fetch(@url, parms, &block)
+          parse(doc)
+        end
+        parms.delete parm
+      end
+    end
+  end
+  
+  def fetch url, parms=nil
+    if block_given? then
+      f = yield url
+    else
+      f = Net::HTTP.post_form(URI.parse(url), parms).body
+    end
+    Nokogiri::HTML(f)
+  end
+
+  def parse doc
+    ##
+    # the data we care about starts in <td> that lists count of matches found
+    doc.css('td').each do |link|
+      if ( link.text =~ /(\d+) Matches Found\n/im ) then
+        # member element is in a <p>, instantiate Person with relevant data
+        link.css('p').each do |member|
+          member.text =~ /(.*), (.*) \| RUSA No\. (\d+) \|.*\n(.*) \|.*(\d{4}\/\d{2}\/\d{2})/im
+          
+          member = Person.new({
+            :last_name => $1.strip,
+            :first_name => $2.strip,
+            :id => $3,
+            :club => $4.strip,
+            :member_expiration_date => Time.parse($5)
+          } )
+
+          # don't run if block given (such as during test)
+          unless block_given? then
+            @options['year'].each do |year|
+              @parse_result.results member, year
+            end
+          end
+          
+          @members<< member
+        end
+      end
+    end
+  end
+    
+  def report
+    @members.sort{|a,b| a[1].last_name + a[1].first_name <=> b[1].last_name + b[1].first_name}.each do |id, member|
+      puts "%25s\t%7s\t%12s\t%30s\n" % ["#{member.first_name} #{member.last_name}",
+                                        member.id,
+                                        member.member_expiration_date,
+                                        member.club]
+      member.results.sort{|a,b| a.date <=> b.date}.each do |result|
+        puts "   Result: %12s\t%10s\t%10s\t%8s\n" % [result.date, result.distance,
+                                                        result.certificate, result.type]
+       end
+
+      member.awards.each do |year, awards|
+        awards.each do |award|
+          puts "   Award: %8s\t%10s\n" % [award.year, award.type]
+        end
+       end
+    end
+  end
+
+end
+
+ParseMember.run if $0 == __FILE__

data/lib/parse_result.rb

@@ -0,0 +1,94 @@
+#!/usr/bin/env ruby -w
+
+##
+# Student Name: bill dussler
+# Homework Week: 8
+#
+# screen scrape data from a web site, parse content
+# and instatntiate club member information
+#
+require 'rubygems'
+require 'nokogiri'
+require 'net/http'
+require 'optparse'
+require 'time'
+require 'date'
+require 'lib/member'
+
+class ParseResult
+  RESULT_QUERY_URL = 'http://www.rusa.org/cgi-bin/results.pl'
+  
+  # match parm key with parameter we will pass
+  PARMS = {'clubs' => 'club',
+           'ids' => 'mid',
+           'lnames' => 'Last_Name',
+           'fnames' => 'First_Name',
+           'years' => 'searchyear',
+           }
+
+  def results member, year=Time.now.year, url=RESULT_QUERY_URL
+
+    if block_given? then
+      f = yield url
+    else
+      parms = {'Last_Name' => member.last_name,
+               'First_Name' => member.first_name,
+               'searchyear' => year
+        }
+  
+      f = Net::HTTP.post_form(URI.parse(url), parms).body
+    end
+    doc = Nokogiri::HTML(f)
+
+    parse(member, doc)
+  end
+  
+  def parse member, doc
+    ##
+    # sanity check-- the li items gives us search terms.  compare to member data
+    doc.css('li').each_with_index do |li, i|
+      if li.text =~ /first name=(.*)/i && member.first_name.downcase != $1.downcase then
+        raise "first name #{$1} in results does not match #{member.first_name}"
+      end
+
+      if li.text =~ /last name=(.*)/i && member.last_name.downcase != $1.downcase then
+        raise "last name #{$1} in results does not match #{member.last_name}"
+      end
+    end
+
+    # year is only displayed in results, not as parm anywhere
+    year_results = nil
+    ##
+    # the data we care about starts in a <td> that lists the count of matches found
+    doc.css('table table tr').each do |row|
+      result_data = row.css('td')
+      next if result_data.size.zero?
+
+      member.results<< Result.new({
+        :certificate => result_data[0].text,
+        :type => result_data[1].text,
+        :distance => result_data[2].text,
+        # Time.parse needs slashes, not dashes
+        :date => Time.parse(result_data[3].text.gsub("-","/")),
+        :organizer => result_data[4].text,
+      } )
+    end
+
+    year_results = member.results.last.date.year unless member.results.empty?
+    member.awards[year_results] = [] unless year_results.nil? or member.awards.has_key? year_results
+    ##
+    # find the awards for this year
+    doc.css('table tr td').each do |row|
+      next unless row.text =~ /Award status: (.*)/i
+      
+      $1.split(",").each do |award_type|
+        member.awards[year_results]<< Award.new({
+          :type => award_type.strip,
+          :year => year_results.to_i,
+        })
+      end
+    end
+
+  end
+  
+end

data/lib/rusa_member.rb

@@ -1,3 +1,3 @@
 class RusaMember
-  VERSION = '1.0.0'
+  VERSION = '1.0.1'
 end

data/test/files/boston.html

@@ -0,0 +1,209 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML Level 3.2//EN">
+<HTML>
+<HEAD>
+<TITLE>RUSA: Members </TITLE>
+<META HTTP-EQUIV="Keywords" CONTENT="Bicycle Touring, Bicycle Racing, Long Distance Cycling, Cycling, Bicycling, Randonneur, Randonneuring, Brevet, RUSA">
+<META HTTP-EQUIV="Reply-to" CONTENT="lois_springsteen@prodigy.net (Lois Springsteen)">
+<BASEFONT SIZE=3>
+</HEAD>
+<BODY BGCOLOR="#FFFFFF" TEXT="#003399" LINK="#FF0000" VLINK="#FF0000" ALINK="#003399">
+<TABLE BORDER=0 HSPACE=0 cellpadding=10 WIDTH=100%>
+<TR>
+<TD ALIGN=left VALIGN=middle width=140>
+<IMG SRC="http://www.rusa.org/Images/logorusa.gif" ALT="RUSA Logo"  HSPACE=0 ALIGN=absmiddle>
+</TD>
+<TD ALIGN=left VALIGN=middle>
+<H1><FONT FACE="ARIAL, HELVETICA"><B>Members</B></FONT></H1>
+</TD>
+<TD ALIGN=right VALIGN=middle></TD>
+</TR>
+</TABLE>
+<HR SIZE=3 WIDTH="100%" ALIGN=CENTER>
+<TABLE BORDER=0 HSPACE=0 cellpadding=10>
+<TR ALIGN=left VALIGN=top width=140>
+<TD NOWRAP>
+<FONT FACE="ARIAL, HELVETICA" SIZE=-1>
+<B>General</B><SMALL>
+<BR>-- <A HREF="http://www.rusa.org/announce.html"><FONT COLOR="#3cb545">Announcements (11/28)</FONT></A>
+<BR>-- <A HREF="http://www.rusa.org/about.html">About Randonneuring</A>
+<BR>-- <A HREF="http://www.rusa.org/links.html">Links</A>
+<BR>-- <A HREF="http://www.rusa.org/index.html">Home</A>
+</SMALL>
+<P><B>Search For</B><SMALL>
+<BR>-- <A HREF="http://www.rusa.org/cgi-bin/eventsearch_GF.pl">Rides</A>
+<BR>-- <A HREF="http://www.rusa.org/results_search.html">Results</A>
+<BR>-- <A HREF="http://www.rusa.org/cgi-bin/membersearch_GF.pl">Members</A>
+<BR>-- <A HREF="http://www.rusa.org/cgi-bin/officialsearch_GF.pl">Officials</A>
+<BR>-- <A HREF="http://www.rusa.org/cgi-bin/clubsearch_GF.pl">ACP Club Codes</A>
+<BR>-- <A HREF="http://www.rusa.org/cgi-bin/routesearch_GF.pl">Routes</A>
+<BR>-- <A HREF="http://www.rusa.org/teamrando.html">Team Events</A>
+<BR>-- <A HREF="http://www.rusa.org/perminfo.html">Permanents</A>
+</SMALL>
+<P><B>Members' Info</B><SMALL>
+<BR>-- <A HREF="http://www.rusa.org/join.html">Join/Renew</A>
+<BR>-- <A HREF="http://www.rusa.org/awards.html">Awards</A>
+<BR>-- <A HREF="http://www.rusa.org/cgi-bin/store_GF.pl">Online Store</A>
+<BR>-- <A HREF="http://www.rusa.org/nletter.html">Newsletter</A>
+<BR>-- <A HREF="http://www.rusa.org/pbpphotogallery.html">Photo Gallery</A>
+<BR>-- <A HREF="http://www.rusa.org/stories.html">Rider Stories</A>
+</SMALL>
+<P><B>Long Brevets</B><SMALL>
+<BR>-- <A HREF="http://www.rusa.org/pbp.html">PBP: Paris-Brest-Paris</A>
+<BR>-- <A HREF="http://www.rusa.org/1200kms.html">Others</A>
+</SMALL>
+<P><B>Administration</B><SMALL>
+<BR>-- <A HREF="http://www.rusa.org/rules.html">Rules</A>
+<BR>-- <A HREF="http://www.rusa.org/rbakit.html">RBAs</A>
+<BR>-- <A HREF="http://www.rusa.org/records.html">Records</A>
+</SMALL>
+</FONT>
+</TD>
+<TD ALIGN=left VALIGN=top>
+
+
+28 Matches Found
+<P><B>Beaulieu</B>, Lynda M | RUSA No. 5213 | Cambridge, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Brandhorst</B>, Eric | RUSA No. 5138 | Carlisle, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Brooke</B>, Justin | RUSA No. 4193 | Cambridge, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2010/12/31</B>
+<P><B>Carrington</B>, Dave | RUSA No. 4696 | Newport, RI 
+<BR>Boston Montreal Boston | ACP Club Code: 921003
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Coldwell</B>, Charles | RUSA No. 2271 | Somerville, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Concepcion</B>, Cris | RUSA No. 3425 | Belmont, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Creason</B>, Gary L | RUSA No. 3354 | Bedford, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Dancy</B>, Abram | RUSA No. 1258 | Shrewsbury, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Dancy</B>, Leigh | RUSA No. 5205 | Shrewsbury, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Fallon</B>, David | RUSA No. 3604 | Somerville, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Gafgen</B>, Pierce | RUSA No. 0009 | Middletown, RI 
+<BR>Boston Montreal Boston | ACP Club Code: 921003
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Howland</B>, David | RUSA No. 4950 | Worcester, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Ingle</B>, Bruce | RUSA No. 0607 | Framingham, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Ingle</B>, Tracey A L | RUSA No. 1591 | Stow, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Kassen</B>, Jonathan | RUSA No. 3598 | Medford, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2010/12/31</B>
+<P><B>Lafferty</B>, David | RUSA No. 4284 | Billerica, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Levesque</B>, Daniel | RUSA No. 2930 | Wilton, NH 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Martin</B>, Tim | RUSA No. 4234 | Westford, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>McLaughlin</B>, Jake | RUSA No. 5063 | Hanover, NH 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Omara</B>, Bill | RUSA No. 2512 | Briston, RI 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Page</B>, Walter | RUSA No. 0980 | Lincoln, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Pope-Lance</B>, Elton | RUSA No. 4734 | Sudbury, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Roy</B>, Matt | RUSA No. 4947 | Arlington, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Schwarz</B>, Bill | RUSA No. 0586 | Kinderhook, NY 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+<P><B>Searles</B>, Emily | RUSA No. 4813 | Billerica, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Spatz</B>, Harry | RUSA No. 4362 | Lexington, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Tolonen</B>, Andrew | RUSA No. 4292 | Boston, MA 
+<BR>Boston Brevet Series | ACP Club Code: 921030
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2008/12/31</B>
+<P><B>Wise</B>, Jennifer | RUSA No. 0001 | Middletown, RI 
+<BR>Boston Montreal Boston | ACP Club Code: 921003
+<BR><A HREF="/join.html">Membership Expires:</A>
+ <B>2009/12/31</B>
+
+</TD>
+</TR>
+</TABLE>
+<HR SIZE=3 WIDTH="100%" ALIGN=Center>
+<P><FONT FACE="ARIAL, HELVETICA" SIZE=-1>Revision: November 29, 2008<BR>
+Please direct questions, comments, or problem reports to the <A HREF="http://www.rusa.org/webmaster.html">webmaster</A>.<BR>
+<B>&copy; Copyright 2008, <A HREF="http://www.rusa.org">Randonneurs USA</A></B>,
+except as noted otherwise.</FONT></P>
+</BODY>
+</HTML>
+
+</BODY>
+</HTML>