webget-football 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: c46b38f5ebe600370371d7032f6178fb4ae22dde
+  data.tar.gz: fd4ca8d6d218dc140f8c63f13f9028ace9a6eda1
+SHA512:
+  metadata.gz: 23e896f122b3f8068ea0acb82f85e60ebaff68d231d86923778dbc8de6cd345d2914f7401f2cd28fd10635ad276504f9d53655808b3d222559455d8f1adfdaee
+  data.tar.gz: 69516f9db9e2a495c378759e5c9195f596fb4be30147cba24fdcf04bf7f55e28325324d07a0f304200cb093d3ef61d239db4275d6d2a51863a1d2eea3e17fe17

data/CHANGELOG.md

@@ -0,0 +1,4 @@
+### 0.0.1 / 2020-11-09
+
+* Everything is new. First release.
+

data/Manifest.txt

@@ -0,0 +1,18 @@
+CHANGELOG.md
+Manifest.txt
+README.md
+Rakefile
+lib/webget-football.rb
+lib/webget-football/apis.rb
+lib/webget-football/apis/config.rb
+lib/webget-football/apis/download.rb
+lib/webget-football/version.rb
+lib/webget-football/worldfootball.rb
+lib/webget-football/worldfootball/config.rb
+lib/webget-football/worldfootball/download.rb
+lib/webget-football/worldfootball/page.rb
+lib/webget-football/worldfootball/page_report.rb
+lib/webget-football/worldfootball/page_schedule.rb
+lib/webget/football.rb
+test/helper.rb
+test/test_version.rb

data/README.md

@@ -0,0 +1,28 @@
+# webget-football - get football data via web pages or web api (json) calls
+
+
+* home  :: [github.com/sportdb/sport.db](https://github.com/sportdb/sport.db)
+* bugs  :: [github.com/sportdb/sport.db/issues](https://github.com/sportdb/sport.db/issues)
+* gem   :: [rubygems.org/gems/webget-football](https://rubygems.org/gems/webget-football)
+* rdoc  :: [rubydoc.info/gems/webget-football](http://rubydoc.info/gems/webget-football)
+* forum :: [groups.google.com/group/opensport](https://groups.google.com/group/opensport)
+
+
+## Usage
+
+TBD
+
+
+## License
+
+![](https://publicdomainworks.github.io/buttons/zero88x31.png)
+
+The `webget-football` scripts are dedicated to the public domain.
+Use it as you please with no restrictions whatsoever.
+
+
+## Questions? Comments?
+
+Send them along to the
+[Open Sports & Friends Forum/Mailing List](http://groups.google.com/group/opensport).
+Thanks!

data/Rakefile

@@ -0,0 +1,26 @@
+require 'hoe'
+require './lib/webget-football/version.rb'
+
+Hoe.spec 'webget-football' do
+
+  self.version = Webget::Module::Football::VERSION
+
+  self.summary = 'webget-football - get football data via web pages or web api (json) calls'
+  self.description = summary
+
+  self.urls = { home: 'https://github.com/sportdb/sport.db' }
+
+  self.author = 'Gerald Bauer'
+  self.email  = 'opensport@googlegroups.com'
+
+  # switch extension to .markdown for gihub formatting
+  self.readme_file  = 'README.md'
+  self.history_file = 'CHANGELOG.md'
+
+  self.licenses = ['Public Domain']
+
+  self.spec_extras = {
+   required_ruby_version: '>= 2.2.2'
+  }
+
+end

data/lib/webget-football.rb

@@ -0,0 +1,16 @@
+## 3rd party (our own)
+require 'webget'    ## incl. webget, webcache, webclient, etc.
+
+## 3rd party
+require 'nokogiri'
+
+
+###
+# our own code
+require 'webget-football/version' # let version always go first
+
+require 'webget-football/apis'
+require 'webget-football/worldfootball'
+
+
+puts Webget::Module::Football.banner   # say hello

data/lib/webget-football/apis.rb

@@ -0,0 +1,10 @@
+###########################
+#  note: split code in two parts
+#    metal  - "bare" basics - no ref to sportdb
+#    and rest / convert  with sportdb references / goodies
+
+## our own code
+require_relative 'apis/config'
+require_relative 'apis/download'
+
+

data/lib/webget-football/apis/config.rb

@@ -0,0 +1,17 @@
+module Footballdata
+
+  class Configuration
+    ## note: nothing here for now
+  end # class Configuration
+
+
+  ## lets you use
+  ##   Footballdata.configure do |config|
+  ##      config.convert.out_dir = './o'
+  ##   end
+
+  def self.configure()  yield( config ); end
+
+  def self.config()  @config ||= Configuration.new;  end
+
+end   # module Footballdata

data/lib/webget-football/apis/download.rb

@@ -0,0 +1,72 @@
+module Footballdata
+
+## todo/check: put in Downloader namespace/class - why? why not?
+##   or use Metal    - no "porcelain" downloaders / machinery
+class Metal
+  BASE_URL = 'http://api.football-data.org/v2'
+
+
+  def self.competitions_url( plan )  "#{BASE_URL}/competitions?plan=#{plan}"; end
+
+  ## just use matches_url - why? why not?
+  def self.competition_matches_url( code, year )  "#{BASE_URL}/competitions/#{code}/matches?season=#{year}"; end
+  def self.competition_teams_url( code, year )    "#{BASE_URL}/competitions/#{code}/teams?season=#{year}";   end
+
+
+
+  def self.competitions_tier_one
+    get( competitions_url( 'TIER_ONE' ))
+  end
+
+  def self.competitions_tier_two
+    get( competions_url( 'TIER_TWO' ))
+  end
+
+  def self.competitions_tier_three
+    get( competions_url( 'TIER_THREE' ))
+  end
+
+  def self.competition( code, year )
+    get( competition_matches_url( code, year ))
+    get( competition_teams_url( code, year ))
+  end
+
+
+=begin
+  def self.matches
+    # note: Specified period must not exceed 10 days.
+
+    ## try query (football) week by week - tuesday to monday!!
+    ##  note: TIER_ONE does NOT include goals!!!
+    code       = 'FL1'
+    start_date = '2019-08-09'
+    end_date   = '2019-08-16'
+
+    get( "matches?competitions=#{code}&dateFrom=#{start_date}&dateTo=#{end_date}" )
+  end
+=end
+
+
+  def self.get( url )
+    token = ENV['FOOTBALLDATA']
+    ## note: because of public workflow log - do NOT output token
+    ## puts token
+
+    headers = {}
+    headers['X-Auth-Token'] = token    if token
+    headers['User-Agent']   = 'ruby'
+    headers['Accept']       = '*/*'
+
+    ## note: add format: 'json' for pretty printing json (before) save in cache
+    response = Webget.call( url, headers: headers )
+
+    ## for debugging print pretty printed json first 400 chars
+    puts response.json.pretty_inspect[0..400]
+
+    exit 1  if response.status.nok?   # e.g. HTTP status code != 200
+  end
+
+
+end  ## class Metal
+end # module Footballdata
+

data/lib/webget-football/version.rb

@@ -0,0 +1,22 @@
+class Webget   ## note: Webget is for now a class (NOT a module)
+module Module
+module Football
+  MAJOR = 0    ## todo: namespace inside version or something - why? why not??
+  MINOR = 0
+  PATCH = 1
+  VERSION = [MAJOR,MINOR,PATCH].join('.')
+
+  def self.version
+    VERSION
+  end
+
+  def self.banner
+    "webget-football/#{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}]"
+  end
+
+  def self.root
+    File.expand_path( File.dirname(File.dirname(File.dirname(__FILE__))) )
+  end
+end  # module Football
+end  # module Module
+end  # class Webget

data/lib/webget-football/worldfootball.rb

@@ -0,0 +1,12 @@
+###########################
+#  note: split code in two parts
+#    metal  - "bare" basics - no ref to sportdb
+#    and rest / convert  with sportdb references / goodies
+
+
+## our own code
+require_relative 'worldfootball/config'
+require_relative 'worldfootball/download'
+require_relative 'worldfootball/page'
+require_relative 'worldfootball/page_schedule'
+require_relative 'worldfootball/page_report'

data/lib/webget-football/worldfootball/config.rb

@@ -0,0 +1,17 @@
+module Worldfootball
+
+
+class Configuration
+  # nothing here for now
+end # class Configuration
+
+
+## lets you use
+##   Worldfootball.configure do |config|
+##      config.convert.out_dir = './o'
+##   end
+
+def self.configure() yield( config ); end
+def self.config()    @config ||= Configuration.new;  end
+
+end   # module Worldfootball

data/lib/webget-football/worldfootball/download.rb

@@ -0,0 +1,89 @@
+
+
+module Worldfootball
+
+
+
+
+## todo/check: put in Downloader namespace/class - why? why not?
+##   or use Metal    - no "porcelain" downloaders / machinery
+class Metal
+
+  BASE_URL = 'https://www.weltfussball.de'
+
+
+  def self.schedule_url( slug )  "#{BASE_URL}/alle_spiele/#{slug}/";  end
+  def self.report_url( slug )    "#{BASE_URL}/spielbericht/#{slug}/"; end
+
+
+  def self.download_schedule( slug )
+    url = schedule_url( slug )
+    get( url )
+  end
+
+  def self.download_report( slug, cache: true )
+    url  = report_url( slug )
+
+    ## check check first
+    if cache && Webcache.cached?( url )
+       puts "  reuse local (cached) copy >#{Webcache.url_to_id( url )}<"
+    else
+      get( url )
+    end
+  end
+
+
+
+
+
+  def self.download_schedule_reports( slug, cache: true ) ## todo/check: rename to reports_for_schedule or such - why? why not?
+
+    page = Page::Schedule.from_cache( slug )
+    matches = page.matches
+
+    puts "matches - #{matches.size} rows:"
+    pp matches[0]
+
+    puts "#{page.generated_in_days_ago}  - #{page.generated}"
+
+    ## todo/fix: restore sleep to old value at the end!!!!
+    ## Webget.config.sleep = 8    ## fetch 7-8 pages/min
+
+    matches.each_with_index do |match,i|
+       est = (Webget.config.sleep * (matches.size-(i+1)))/60.0   # estimated time left
+
+       puts "fetching #{i+1}/#{matches.size} (#{est} min(s)) - #{match[:round]} | #{match[:team1]} v #{match[:team2]}..."
+       report_ref = match[:report_ref ]
+       if report_ref
+         download_report( report_ref, cache: cache )
+       else
+         puts "!! WARN: report ref missing for match:"
+         pp match
+       end
+    end
+  end
+
+
+  ### add some "old" (back compat) aliases - keep - why? why not?
+  class << self
+    alias_method :schedule,          :download_schedule
+    alias_method :report,            :download_report
+    alias_method :schedule_reports,  :download_schedule_reports
+  end
+
+
+  ##################
+  #  helpers
+  def self.get( url )  ## get & record/save to cache
+
+    response = Webget.page( url )  ## fetch (and cache) html page (via HTTP GET)
+
+    ## note: exit on get / fetch error - do NOT continue for now - why? why not?
+    exit 1   if response.status.nok?    ## e.g.  HTTP status code != 200
+  end
+
+
+end # class Metal
+end # module Worldfootball
+
+

data/lib/webget-football/worldfootball/page.rb

@@ -0,0 +1,106 @@
+
+module Worldfootball
+  class Page
+
+  def self.from_file( path )
+    html = File.open( path, 'r:utf-8' ) {|f| f.read }
+    new( html )
+  end
+
+  def initialize( html )
+    @html = html
+  end
+
+  def doc
+    ## note: if we use a fragment and NOT a document - no access to page head (and meta elements and such)
+    @doc ||= Nokogiri::HTML( @html )
+  end
+
+  def title
+   # <title>Bundesliga 2010/2011 &raquo; Spielplan</title>
+     @title ||= doc.css( 'title' ).first
+     @title.text  ## get element's text content
+  end
+
+  def keywords
+     # <meta name="keywords"
+     #  content="Bundesliga, 2010/2011, Spielplan, KSV Superfund, SC Magna Wiener Neustadt, SV Ried, FC Wacker Innsbruck, Austria Wien, Sturm Graz, SV Mattersburg, LASK Linz, Rapid Wien, RB Salzburg" />
+     @keywords ||= doc.css( 'meta[name="keywords"]' ).first
+     @keywords[:content]  ## get content attribute
+     ## or      doc.xpath( '//meta[@name="keywords"]' ).first
+     ## pp keywords
+     # puts "  #{keywords[:content]}"
+
+     # keywords = doc.at( 'meta[@name="Keywords"]' )
+     # pp keywords
+     ## check for
+  end
+
+  # <meta property="og:url"
+  #       content="//www.weltfussball.de/alle_spiele/aut-bundesliga-2010-2011/" />
+  def url
+    @url ||= doc.css( 'meta[property="og:url"]' ).first
+    @url[:content]
+  end
+
+
+
+##  <!-- [generated 2020-06-30 22:30:19] -->
+##  <!-- [generated 2020-06-30 22:30:19] -->
+GENERATED_RE = %r{
+  <!--
+    [ ]+
+    \[generated
+        [ ]+
+      (?<date>\d+-\d+-\d+)
+        [ ]+
+      (?<time>\d+:\d+:\d+)
+    \]
+    [ ]+
+    -->
+   }x
+
+
+   def generated
+      @generated ||= begin
+        m=GENERATED_RE.match( @html )
+        if m
+         DateTime.strptime( "#{m[:date]} #{m[:time]}", '%Y-%m-%d %H:%M:%S')
+        else
+         puts "!! WARN - no generated timestamp found in page"
+         nil
+        end
+      end
+   end
+
+   ### convenience helper / formatter
+   def generated_in_days_ago
+     if generated
+      diff_in_days = Date.today.jd - generated.jd
+      "#{diff_in_days}d"
+     else
+      '?'
+     end
+   end
+
+######################
+##  helper methods
+
+def squish( str )
+  str = str.strip
+  str = str.gsub( "\u{00A0}", ' ' )  # Unicode Character 'NO-BREAK SPACE' (U+00A0)
+  str = str.gsub( /[ \t\n]+/, ' ' )  ## fold whitespace to one max.
+  str
+end
+
+def assert( cond, msg )
+  if cond
+    # do nothing
+  else
+    puts "!!! assert failed (in parse page) - #{msg}"
+    exit 1
+  end
+end
+
+end # class Page
+end # module Worldfootball

data/lib/webget-football/worldfootball/page_report.rb

@@ -0,0 +1,186 @@
+
+module Worldfootball
+  class Page
+
+class Report < Page  ## note: use nested class for now - why? why not?
+
+
+  def self.from_cache( slug )
+    url  = Worldfootball::Metal.report_url( slug )
+    html = Webcache.read( url )
+    new( html )
+  end
+
+
+
+  def find_table_tore
+    # <table class="" cellpadding="3" cellspacing="1">
+    # <tr>
+    #   <td colspan="2" class="ueberschrift" align="center">Tore</td>
+    # </tr>
+
+   ## get table
+   ##   first table row is Tore
+    tables = doc.css( 'table.standard_tabelle' )
+    # puts "  found #{tables.size} table.standard_tabelle" # e.g. found 6 table.standard_tabelle
+    tables.each do |table|
+      trs = table.css( 'tr' )
+      ## puts "     found #{trs.size} trs"
+      tds = trs[0].css( 'td' )
+      ## puts "     found #{tds.size} tds"
+
+      if tds.size > 0 && tds[0].text == 'Tore'
+        return table
+      end
+    end
+
+    nil  ## nothing found; auto-report error -why? why not?
+  end
+
+  def goals
+    @goals ||= begin
+
+ # <div class="data">
+ # <table class="standard_tabelle" cellpadding="3" cellspacing="1">
+
+ # puts table.class.name  #=> Nokogiri::XML::Element
+ # puts table.text
+
+ table  = find_table_tore
+ ## pp table
+
+ trs   = table.css( 'tr' )
+ # puts trs.size
+
+
+
+ rows = []
+ last_score1 = 0
+ last_score2 = 0
+
+ trs.each_with_index do |tr,i|
+
+   next if i==0   # skip Tore headline row
+
+   break if i==1 && tr.text.strip == 'keine'  ## assume 0:0 - no goals
+
+# <tr>
+#  <td class="hell" align="center" width="20%">
+#   <b>0 : 1</b>
+#  </td>
+#  <td class="hell" style="padding-left: 50px;">
+#   <a href="/spieler_profil/luis-phelipe/" title="Luis Phelipe">Luis Phelipe</a> 34. / Rechtsschuss								&nbsp;(<a href="/spieler_profil/alexander-prass/" title="Alexander Prass">Alexander Prass</a>)
+# </td>
+# </tr>
+
+       tds = tr.css( 'td' )
+
+     score_str  = squish( tds[0].text )
+
+     player_str = squish( tds[1].text )
+
+     print '[%03d] ' % i
+     print score_str
+     print " | "
+     print player_str
+     print "\n"
+
+     score_str = score_str.gsub( ':', '-' )
+     score_str = score_str.gsub( ' ', '' )   ## remove all white space
+
+
+     ### todo/fix: use new Score.split helper here
+     ## score1, score2 = Score.split( score_str )
+     parts = score_str.split('-')
+     score1 = parts[0].to_i
+     score2 = parts[1].to_i
+
+     if last_score1+1 == score1 && last_score2 == score2
+       team = 1
+     elsif last_score2+1 == score2 && last_score1 == score1
+       team = 2
+     else
+       puts "!! ERROR - unexpected score advance (one goal at a time expected):"
+       puts "  #{last_score1}-#{last_score2}=> #{score1}-#{score2}"
+       exit 1
+     end
+
+
+     last_score1 = score1
+     last_score2 = score2
+
+
+
+     if player_str.index('/')
+       parts = player_str.split('/')
+       # pp parts
+       notes = parts[1].strip
+
+       if parts[0].strip =~ /^([^0-9]+)[ ]+([0-9]+)\.$/
+         player_name = $1
+         goal_minute = $2
+          # puts " >#{player_name}< | >#{goal_minute}<"
+       else
+         puts "!! ERROR - unknown goal format (in part i):"
+         puts player_str
+         pp parts
+         exit 1
+       end
+      else  # (simple line with no divider (/)
+        #  Andrés Andrade 88.  (Nicolas Meister)
+        if m = %r{^([^0-9]+)
+                  [ ]+
+                 ([0-9]+)\.
+                  (?:
+                    [ ]+
+                    (\([^)]+\))
+                  )?
+                $}x.match( player_str )
+            player_name = m[1]
+            goal_minute = m[2]
+            notes       = m[3] ? m[3] : ''
+        else
+          puts "!! ERROR - unknown goal format:"
+          puts player_str
+          exit 1
+        end
+      end
+
+
+     ## check for "flags" e.g. own goal or penalty
+     ##   if found - remove from notes (use its own flag)
+     owngoal = false
+     penalty = false
+
+    if notes.index( 'Eigentor' )
+       owngoal = true
+       notes = notes.sub('Eigentor', '' ).strip
+    elsif notes.index( 'Elfmeter' )
+      ## e.g.  Elfmeter  (Marco Hausjell)
+       penalty = true
+       notes = notes.sub('Elfmeter', '' ).strip
+    else
+      ## nothing - keep going
+    end
+
+     rec = { score:   score_str,
+             team:    team,     # 1 or 2
+             player:  player_name,
+             minute:  goal_minute
+             }
+      rec[:owngoal] = true   if owngoal
+      rec[:penalty] = true   if penalty
+      rec[:notes]   = notes  unless notes.empty?
+
+      rows << rec
+   end ## each tr
+      rows
+   end
+ end  # goals
+
+
+end # class Report
+
+
+  end # class Page
+end # module Worldfootball

data/lib/webget-football/worldfootball/page_schedule.rb

@@ -0,0 +1,262 @@
+
+module Worldfootball
+  class Page
+
+class Schedule < Page  ## note: use nested class for now - why? why not?
+
+
+  def self.from_cache( slug )
+    url  = Worldfootball::Metal.schedule_url( slug )
+    html = Webcache.read( url )
+    new( html )
+  end
+
+
+
+  def matches
+    @matches ||= begin
+
+ # <div class="data">
+ # <table class="standard_tabelle" cellpadding="3" cellspacing="1">
+
+ ## note: use > for "strict" sibling (child without any in-betweens)
+ table = doc.css( 'div.data > table.standard_tabelle' ).first    ## get table
+ # puts table.class.name  #=> Nokogiri::XML::Element
+ # puts table.text
+
+ trs   = table.css( 'tr' )
+ # puts trs.size
+ i = 0
+
+ last_date_str = nil
+ last_round    = nil
+
+ rows = []
+
+ trs.each do |tr|
+   i += 1
+
+
+   if tr.text.strip =~ /Spieltag/ ||
+      tr.text.strip =~ /[1-9]\.[ ]Runde|
+                           Qual\.[ ][1-9]\.[ ]Runde|  # see EL or CL Quali
+                           Qualifikation|     # see CA Championship
+                           Sechzehntelfinale|   # see EL
+                           Achtelfinale|
+                           Viertelfinale|
+                           Halbfinale|
+                           Finale|
+                           Gruppe[ ][A-Z]|    # see CL
+                           Playoffs           # see EL Quali
+                           /x
+     puts
+     print '[%03d] ' % i
+     ## print squish( tr.text )
+     print "round >#{tr.text.strip}<"
+     print "\n"
+
+     last_round = tr.text.strip
+   else   ## assume table row (tr) is match line
+     tds = tr.css( 'td' )
+
+     date_str  = squish( tds[0].text )
+     time_str  = squish( tds[1].text )
+
+     # was: team1_str = squish( tds[2].text )
+
+     ## <td><a href="/teams/hibernian-fc/" title="Hibernian FC">Hibernian FC</a></td>
+     ##  todo/check: check if tooltip title always equals text - why? why not?
+     team1_anchor = tds[2].css( 'a' )[0]
+     if team1_anchor  # note: <a> might be optional (and team name only be plain text)
+       team1_str    = squish( team1_anchor.text )
+       team1_ref    = norm_team_ref( team1_anchor[:href] )
+     else
+       team1_str    = squish( tds[2].text )
+       team1_ref    = nil
+       puts "!! WARN: no team1_ref for >#{team1_str}< found"
+     end
+
+     ##  <td> - </td>
+     ## e.g. -
+     vs_str =    squish( tds[3].text )  ## use to assert column!!!
+     assert( vs_str == '-',  "- for vs. expected; got #{vs_str}")
+     ## was: team2_str = squish( tds[4].text )
+
+     ## <td><a href="/teams/st-johnstone-fc/" title="St. Johnstone FC">St. Johnstone FC</a></td>
+     team2_anchor = tds[4].css( 'a' )[0]
+     if team2_anchor
+       team2_str    = squish( team2_anchor.text )
+       team2_ref    = norm_team_ref( team2_anchor[:href] )
+     else
+       team2_str    = squish( tds[4].text )
+       team2_ref    = nil
+       puts "!! WARN: no team2_ref for >#{team2_str}< found"
+     end
+
+     ### was: score_str = squish( tds[5].text )
+     ## <a href="/spielbericht/premiership-2020-2021-hibernian-fc-st-johnstone-fc/" title="Spielschema Hibernian FC - St. Johnstone FC">-:-</a>
+
+     score_anchor = tds[5].css( 'a' )[0]
+     if score_anchor   ## note: score ref (match report) is optional!!!!
+       score_str    = squish( score_anchor.text )
+       score_ref    = norm_score_ref( score_anchor[:href] )
+     else
+       score_str    = squish( tds[5].text )
+       score_ref    = nil
+     end
+
+
+     ##  todo - find a better way to check for live match
+     ## check for live badge image
+     ## <td>
+     ##   <img src="https://s.hs-data.com/bilder/shared/live/2.png" /></a>
+     ## </td>
+     img = tds[6].css( 'img' )[0]
+     if img && img[:src].index( '/live/')
+       puts "!! WARN: live match badge, resetting score from #{score_str} to -:-"
+       score_str = '-:-'  # note: -:- gets replaced to ---
+     end
+
+
+     date_str = last_date_str    if date_str.empty?
+
+     print '[%03d]    ' % i
+     print "%-10s | " % date_str
+     print "%-5s | " % time_str
+     print "%-22s | " % team1_str
+     print "%-22s | " % team2_str
+     print "%-10s | " % score_str
+     print (score_ref ? score_ref : 'n/a')
+     print "\n"
+
+
+     ## change  2:1 (1:1)  to 2-1 (1-1)
+     score_str = score_str.gsub( ':', '-' )
+
+     ## convert date from 25.10.2019 to 2019-25-10
+     date     = Date.strptime( date_str, '%d.%m.%Y' )
+
+     ## note: keep structure flat for now
+     ##        (AND not nested e.g. team:{text:,ref:}) - why? why not?
+     rows << { round:      last_round,
+               date:       date.strftime( '%Y-%m-%d' ),
+               time:       time_str,
+               team1:      team1_str,
+               team1_ref:  team1_ref,
+               score:      score_str,
+               team2:      team2_str,
+               team2_ref:  team2_ref,
+               report_ref: score_ref
+             }
+
+     last_date_str = date_str
+   end
+  end # each tr (table row)
+
+    rows
+   end
+ end  # matches
+
+
+
+ def teams
+  @teams ||= begin
+     h = {}
+     matches.each do |match|
+       ## index by name/text for now NOT ref - why? why not?
+       [{text: match[:team1],
+         ref:  match[:team1_ref]},
+        {text: match[:team2],
+         ref:  match[:team2_ref]}].each do |team|
+         rec = h[ team[:text] ] ||= { count: 0,
+                                      name: team[ :text],
+                                      ref:  team[ :ref ] }
+         rec[ :count ] += 1
+         ## todo/check:  check/assert that name and ref are always equal - why? why not?
+       end
+     end
+
+     h.values
+  end
+ end
+
+ def rounds
+  @rounds ||= begin
+     h = {}
+     matches.each do |match|
+       rec = h[ match[:round] ] ||= { count: 0,
+                                      name: match[ :round] }
+        rec[ :count ] += 1
+     end
+
+     h.values
+  end
+ end
+
+
+ def seasons
+  # <select name="saison" ...
+  @seasons ||= begin
+     recs = []
+     season = doc.css( 'select[name="saison"]').first
+     options = season.css( 'option' )
+
+     options.each do |option|
+        recs << { text: squish( option.text ),
+                  ref:  norm_season_ref( option[:value] )
+                }
+     end
+     recs
+  end
+end
+
+
+######
+## helpers
+
+## todo/check - rename/use HREF and not REF - why? why not?
+REF_SCORE_RE = %r{^/spielbericht/
+                     ([a-z0-9_-]+)/$}x
+
+def norm_score_ref( str )
+  ## check ref format / path
+  if m=REF_SCORE_RE.match( str )
+    m[1]
+  else
+    puts "!! ERROR: unexpected score href format >#{str}<"
+    exit 1
+  end
+end
+
+
+REF_TEAM_RE  = %r{^/teams/
+                     ([a-z0-9_-]+)/$}x
+
+def norm_team_ref( str )
+  ## check ref format / path
+  if m=REF_TEAM_RE.match( str )
+    m[1]
+  else
+    puts "!! ERROR: unexpected team href format >#{str}<"
+    exit 1
+  end
+end
+
+
+REF_SEASON_RE = %r{^/alle_spiele/
+                        ([a-z0-9_-]+)/$}x
+
+def norm_season_ref( str )
+  ## check ref format / path
+  if m=REF_SEASON_RE.match( str )
+    m[1]
+  else
+    puts "!! ERROR: unexpected season href format >#{str}<"
+    exit 1
+  end
+end
+end # class Schedule
+
+
+  end # class Page
+end # module Worldfootball

data/lib/webget/football.rb

@@ -0,0 +1,4 @@
+# note: allow require 'webget/football' too
+#        (in addition to require 'webget-football')
+
+require_relative '../webget-football'

data/test/helper.rb

@@ -0,0 +1,6 @@
+require 'minitest/autorun'
+
+
+## our own code
+require 'webget/football'     ## or require 'webget-football'
+

data/test/test_version.rb

@@ -0,0 +1,16 @@
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_version.rb
+
+
+require 'helper'
+
+class TestVersion < MiniTest::Test
+
+  def test_version
+    pp Webget::Module::Football::VERSION
+    pp Webget::Module::Football.banner
+    pp Webget::Module::Football.root
+  end
+
+end # class TestVersion

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification
+name: webget-football
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Gerald Bauer
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2020-11-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '4.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '4.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '7'
+- !ruby/object:Gem::Dependency
+  name: hoe
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.22'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.22'
+description: webget-football - get football data via web pages or web api (json) calls
+email: opensport@googlegroups.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- CHANGELOG.md
+- Manifest.txt
+- README.md
+files:
+- CHANGELOG.md
+- Manifest.txt
+- README.md
+- Rakefile
+- lib/webget-football.rb
+- lib/webget-football/apis.rb
+- lib/webget-football/apis/config.rb
+- lib/webget-football/apis/download.rb
+- lib/webget-football/version.rb
+- lib/webget-football/worldfootball.rb
+- lib/webget-football/worldfootball/config.rb
+- lib/webget-football/worldfootball/download.rb
+- lib/webget-football/worldfootball/page.rb
+- lib/webget-football/worldfootball/page_report.rb
+- lib/webget-football/worldfootball/page_schedule.rb
+- lib/webget/football.rb
+- test/helper.rb
+- test/test_version.rb
+homepage: https://github.com/sportdb/sport.db
+licenses:
+- Public Domain
+metadata: {}
+post_install_message: 
+rdoc_options:
+- "--main"
+- README.md
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.2.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.2
+signing_key: 
+specification_version: 4
+summary: webget-football - get football data via web pages or web api (json) calls
+test_files: []