sunflower 0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE +4 -0
- data/README +21 -0
- data/bin/sunflower-setup +68 -0
- data/example-bot.rb +12 -0
- data/lib/sunflower/commontasks.rb +251 -0
- data/lib/sunflower/core.rb +253 -0
- data/lib/sunflower/listmaker.rb +152 -0
- data/lib/sunflower.rb +4 -0
- data/scripts/ZDBOT.rb +62 -0
- data/scripts/aktualizacjapilkarzy.rb +339 -0
- data/scripts/author-list.rb +36 -0
- data/scripts/changeimage.rb +42 -0
- data/scripts/fix-bold-in-headers.rb +53 -0
- data/scripts/fix-double-pipes.rb +49 -0
- data/scripts/fix-langs.rb +43 -0
- data/scripts/fix-multiple-same-refs.rb +102 -0
- data/scripts/fix-some-entities.rb +43 -0
- data/scripts/fix-unicode-control-chars.rb +51 -0
- data/scripts/insight.rb +133 -0
- data/scripts/lekkoatl-portal.rb +51 -0
- data/scripts/make-id2team-list.rb +32 -0
- data/scripts/recat.rb +32 -0
- data/scripts/wanted.rb +72 -0
- data/use-easy-bot.rb +54 -0
- metadata +115 -0
@@ -0,0 +1,152 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
class Sunflower
|
3
|
+
# Makes a list of articles. Returns array of titles.
|
4
|
+
def make_list type, *parameters
|
5
|
+
type=type.downcase.gsub(/[^a-z]/, '')
|
6
|
+
first=parameters[0]
|
7
|
+
firstE=CGI.escape first
|
8
|
+
|
9
|
+
case type
|
10
|
+
when 'file'
|
11
|
+
f=File.open first
|
12
|
+
list=f.read.sub(/\357\273\277/,'').strip.split(/\r?\n/)
|
13
|
+
f.close
|
14
|
+
|
15
|
+
when 'page', 'pages'
|
16
|
+
list=parameters
|
17
|
+
|
18
|
+
when 'input'
|
19
|
+
puts 'Insert titles of articles to edit:'
|
20
|
+
puts 'Press [Enter] without inputting any text to finish.'
|
21
|
+
puts 'Press [Ctrl]+[C] to kill bot.'
|
22
|
+
list=[]
|
23
|
+
while true
|
24
|
+
input=gets.strip
|
25
|
+
break if input==''
|
26
|
+
|
27
|
+
list<<input
|
28
|
+
end
|
29
|
+
|
30
|
+
when 'categorieson'
|
31
|
+
r=self.API('action=query&prop=categories&cllimit=500&titles='+firstE)
|
32
|
+
list=r['query']['pages'].first['categories'].map{|v| v['title']} #extract titles
|
33
|
+
|
34
|
+
when 'category'
|
35
|
+
r=self.API('action=query&list=categorymembers&cmprop=title&cmlimit=5000&cmtitle='+firstE)
|
36
|
+
list=r['query']['categorymembers'].map{|v| v['title']} #extract titles
|
37
|
+
|
38
|
+
when 'categoryr', 'categoryrecursive'
|
39
|
+
list=[] #list of articles
|
40
|
+
catsToProcess=[first] #list of categories to be processes
|
41
|
+
while !catsToProcess.empty?
|
42
|
+
list2=self.make_list('category',catsToProcess[0]) # get contents of first cat in list
|
43
|
+
catsToProcess=catsToProcess+list2.select{|el| el=~/\AKategoria:/} # find categories in it and queue them to be processes
|
44
|
+
catsToProcess.delete_at 0 # remove first category from list
|
45
|
+
list=list+list2 #add articles to main list
|
46
|
+
end
|
47
|
+
list.uniq! #remove dupes
|
48
|
+
|
49
|
+
when 'linkson'
|
50
|
+
r=self.API('action=query&prop=links&pllimit=5000&titles='+firstE)
|
51
|
+
list=r['query']['pages'].first['links'].map{|v| v['title']} #extract titles
|
52
|
+
|
53
|
+
when 'transclusionson', 'templateson'
|
54
|
+
r=self.API('action=query&prop=templates&tllimit=5000&titles='+firstE)
|
55
|
+
list=r['query']['pages'].first['templates'].map{|v| v['title']} #extract titles
|
56
|
+
|
57
|
+
when 'usercontribs', 'contribs'
|
58
|
+
r=self.API('action=query&list=usercontribs&uclimit=5000&ucprop=title&ucuser='+firstE)
|
59
|
+
list=r['query']['usercontribs'].map{|v| v['title']} #extract titles
|
60
|
+
|
61
|
+
when 'whatlinksto', 'whatlinkshere'
|
62
|
+
r=self.API('action=query&list=backlinks&bllimit=5000&bltitle='+firstE)
|
63
|
+
list=r['query']['backlinks'].map{|v| v['title']} #extract titles
|
64
|
+
|
65
|
+
when 'whattranscludes', 'whatembeds'
|
66
|
+
r=self.API('action=query&list=embeddedin&eilimit=5000&eititle='+firstE)
|
67
|
+
list=r['query']['embeddedin'].map{|v| v['title']} #extract titles
|
68
|
+
|
69
|
+
when 'image', 'imageusage'
|
70
|
+
r=self.API('action=query&list=imageusage&iulimit=5000&iutitle='+firstE)
|
71
|
+
list=r['query']['imageusage'].map{|v| v['title']} #extract titles
|
72
|
+
|
73
|
+
when 'search'
|
74
|
+
r=self.API('action=query&list=search&srwhat=text&srlimit=5000&srnamespace='+(parameters[1]=='allns' ? CGI.escape('0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|100|101|102|103') : '0')+'&srsearch='+firstE)
|
75
|
+
list=r['query']['search'].map{|v| v['title']} #extract titles
|
76
|
+
|
77
|
+
when 'searchtitles'
|
78
|
+
r=self.API('action=query&list=search&srwhat=title&srlimit=5000&srnamespace='+(parameters[1]=='allns' ? CGI.escape('0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|100|101|102|103') : '0')+'&srsearch='+firstE)
|
79
|
+
list=r['query']['search'].map{|v| v['title']} #extract titles
|
80
|
+
|
81
|
+
when 'random'
|
82
|
+
r=self.API('action=query&list=random&rnnamespace=0&rnlimit='+first.gsub(/\D/))
|
83
|
+
list=r['query']['random'].map{|v| v['title']} #extract titles
|
84
|
+
|
85
|
+
when 'external', 'linksearch'
|
86
|
+
r=self.API('action=query&euprop=title&list=exturlusage&eulimit=5000&euquery='+firstE)
|
87
|
+
list=r['query']['exturlusage'].map{|v| v['title']} #extract titles
|
88
|
+
|
89
|
+
when 'google'
|
90
|
+
limit=[parameters[1].to_i,999].min
|
91
|
+
from=0
|
92
|
+
list=[]
|
93
|
+
|
94
|
+
while from<limit
|
95
|
+
p=HTTP.get(URI.parse("http://www.google.pl/custom?q=kot&start=#{from}&sitesearch=#{@wikiURL}"))
|
96
|
+
p.scan(/<div class=g><h2 class=r><a href="http:\/\/#{@wikiURL}\/wiki\/([^#<>\[\]\|\{\}]+?)" class=l>/){
|
97
|
+
list<<CGI.unescape($1).gsub('_',' ')
|
98
|
+
}
|
99
|
+
|
100
|
+
from+=10
|
101
|
+
end
|
102
|
+
|
103
|
+
when 'grep', 'regex', 'regexp'
|
104
|
+
split=@wikiURL.split('.')
|
105
|
+
ns=(parameters[1] ? parameters[1].to_s.gsub(/\D/,'') : '0')
|
106
|
+
redirs=(parameters[2] ? '&redirects=on' : '')
|
107
|
+
list=[]
|
108
|
+
|
109
|
+
p=HTTP.get(URI.parse("http://toolserver.org/~nikola/grep.php?pattern=#{firstE}&lang=#{split[0]}&wiki=#{split[1]}&ns=#{ns}#{redirs}"))
|
110
|
+
p.scan(/<tr><td><a href="http:\/\/#{@wikiURL}\/wiki\/([^#<>\[\]\|\{\}]+?)(?:\?redirect=no|)">/){
|
111
|
+
list<<CGI.unescape($1).gsub('_',' ')
|
112
|
+
}
|
113
|
+
end
|
114
|
+
|
115
|
+
return list
|
116
|
+
end
|
117
|
+
end
|
118
|
+
|
119
|
+
if $0==__FILE__
|
120
|
+
puts 'What kind of list do you want to create?'
|
121
|
+
if !(t=ARGV.shift)
|
122
|
+
t=gets
|
123
|
+
else
|
124
|
+
t=t.strip
|
125
|
+
puts t
|
126
|
+
end
|
127
|
+
puts ''
|
128
|
+
|
129
|
+
puts 'Supply arguments to pass to listmaker:'
|
130
|
+
puts '(press [Enter] without writing anything to finish)'
|
131
|
+
arg=[]
|
132
|
+
ARGV.each do |i|
|
133
|
+
arg<<i.strip
|
134
|
+
puts i.strip
|
135
|
+
end
|
136
|
+
while (a=gets.strip)!=''
|
137
|
+
arg<<a
|
138
|
+
end
|
139
|
+
|
140
|
+
puts 'Making list, wait patiently...'
|
141
|
+
|
142
|
+
s=Sunflower.new
|
143
|
+
s.login
|
144
|
+
|
145
|
+
l=s.make_list(t, *arg)
|
146
|
+
l.sort!
|
147
|
+
f=File.open('list.txt','w')
|
148
|
+
f.write(l.join("\n"))
|
149
|
+
f.close
|
150
|
+
|
151
|
+
puts 'Done! List saved to "list.txt".'
|
152
|
+
end
|
data/lib/sunflower.rb
ADDED
data/scripts/ZDBOT.rb
ADDED
@@ -0,0 +1,62 @@
|
|
1
|
+
require 'sunflower-core.rb'
|
2
|
+
require 'sunflower-commontasks.rb'
|
3
|
+
s=Sunflower.new
|
4
|
+
s.login
|
5
|
+
|
6
|
+
$summary='archiwizacja zadań'
|
7
|
+
|
8
|
+
pp=Page.get('Wikipedia:Zadania dla botów')
|
9
|
+
tasks=pp.text
|
10
|
+
|
11
|
+
tasksDone=[]
|
12
|
+
tasksError=[]
|
13
|
+
tasksOld=[]
|
14
|
+
|
15
|
+
tasks=tasks.gsub(/\n==\s*(.+?)\s*==\s*\{\{\/Status\|([^}]+)\}\}([\s\S]+?)(?=\r?\n==|\s*\Z)/) do
|
16
|
+
title=$1.strip
|
17
|
+
status=$2.strip
|
18
|
+
text=$3.strip
|
19
|
+
|
20
|
+
bval=''
|
21
|
+
|
22
|
+
if (['wykonane','zrobione','błąd','błędne','stare'].index(status)==nil)
|
23
|
+
bval=$&
|
24
|
+
elsif (status=='wykonane' || status=='zrobione')
|
25
|
+
tasksDone<<"== "+title+" ==\n{{/Status|"+status+"}}\n"+text
|
26
|
+
elsif (status=='błąd' || status=='błędne')
|
27
|
+
tasksError<<"== "+title+" ==\n{{/Status|"+status+"}}\n"+text
|
28
|
+
elsif (status=='stare')
|
29
|
+
tasksOld<<"== "+title+" ==\n{{/Status|"+status+"}}\n"+text
|
30
|
+
end
|
31
|
+
|
32
|
+
bval
|
33
|
+
end
|
34
|
+
|
35
|
+
puts 'Data loaded. Saving...'
|
36
|
+
|
37
|
+
p=Page.get('Wikipedia:Zadania_dla_botów/Archiwum/błędne')
|
38
|
+
p.append tasksError.join("\n\n") unless tasksError.empty?
|
39
|
+
p.save unless tasksError.empty?
|
40
|
+
puts 'Error - saved.'
|
41
|
+
|
42
|
+
p=Page.get('Wikipedia:Zadania_dla_botów/Archiwum/wykonane')
|
43
|
+
p.append tasksDone.join("\n\n") unless tasksDone.empty?
|
44
|
+
p.save unless tasksDone.empty?
|
45
|
+
puts 'Done - saved.'
|
46
|
+
|
47
|
+
p=Page.get('Wikipedia:Zadania_dla_botów/Archiwum/stare')
|
48
|
+
p.append tasksOld.join("\n\n") unless tasksOld.empty?
|
49
|
+
p.save unless tasksOld.empty?
|
50
|
+
puts 'Old - saved.'
|
51
|
+
|
52
|
+
pp.text=tasks
|
53
|
+
pp.save
|
54
|
+
puts 'Main - saved.'
|
55
|
+
|
56
|
+
# File.open('ZDBOT_main.txt','w').write(tasks)
|
57
|
+
# File.open('ZDBOT_done.txt','w').write(tasksDone.join("\n\n")) unless tasksDone.empty?
|
58
|
+
# File.open('ZDBOT_error.txt','w').write(tasksError.join("\n\n")) unless tasksError.empty?
|
59
|
+
# File.open('ZDBOT_old.txt','w').write(tasksOld.join("\n\n")) unless tasksOld.empty?
|
60
|
+
|
61
|
+
puts "Stats: done: #{tasksDone.length}; error: #{tasksError.length}; old: #{tasksOld.length}"
|
62
|
+
gets
|
@@ -0,0 +1,339 @@
|
|
1
|
+
require 'orderedhash'
|
2
|
+
require 'hpricot'
|
3
|
+
require 'net/http'
|
4
|
+
require 'sunflower-core.rb'
|
5
|
+
require 'sunflower-listmaker.rb'
|
6
|
+
include Net
|
7
|
+
|
8
|
+
$datafile=File.open('aktual.txt','w')
|
9
|
+
$datafile.sync=true
|
10
|
+
|
11
|
+
id2team={}
|
12
|
+
begin
|
13
|
+
File.open('id2team.txt') do |f|
|
14
|
+
id2team.replace Hash[*f.read.strip.split(/\r?\n|\t/)]
|
15
|
+
end
|
16
|
+
rescue
|
17
|
+
end
|
18
|
+
|
19
|
+
# comes from http://rubyforge.org/frs/?group_id=6257&release_id=36721
|
20
|
+
module Levenshtein
|
21
|
+
VERSION = "0.2.0"
|
22
|
+
|
23
|
+
# Returns the Levenshtein distance as a number between 0.0 and
|
24
|
+
# 1.0. It's basically the Levenshtein distance divided by the
|
25
|
+
# length of the longest sequence.
|
26
|
+
|
27
|
+
def self.normalized_distance(s1, s2, threshold=nil)
|
28
|
+
s1, s2 = s2, s1 if s1.length > s2.length # s1 is the short one; s2 is the long one.
|
29
|
+
|
30
|
+
if s2.length == 0
|
31
|
+
0.0 # Since s1.length < s2.length, s1 must be empty as well.
|
32
|
+
else
|
33
|
+
if threshold
|
34
|
+
if d = self.distance(s1, s2, (threshold*s2.length+1).to_i)
|
35
|
+
d.to_f/s2.length
|
36
|
+
else
|
37
|
+
nil
|
38
|
+
end
|
39
|
+
else
|
40
|
+
self.distance(s1, s2).to_f/s2.length
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
# Returns the Levenshtein distance between two sequences.
|
46
|
+
#
|
47
|
+
# The two sequences can be two strings, two arrays, or two other
|
48
|
+
# objects. Strings, arrays and arrays of strings are handled with
|
49
|
+
# optimized (very fast) C code. All other sequences are handled
|
50
|
+
# with generic (fast) C code.
|
51
|
+
#
|
52
|
+
# The sequences should respond to :length and :[] and all objects
|
53
|
+
# in the sequences (as returned by []) should response to :==.
|
54
|
+
|
55
|
+
def self.distance(s1, s2, threshold=nil)
|
56
|
+
s1, s2 = s2, s1 if s1.length > s2.length # s1 is the short one; s2 is the long one.
|
57
|
+
|
58
|
+
# Handle some basic circumstances.
|
59
|
+
|
60
|
+
return 0 if s1 == s2
|
61
|
+
return s2.length if s1.length == 0
|
62
|
+
|
63
|
+
if threshold
|
64
|
+
return nil if (s2.length-s1.length) >= threshold
|
65
|
+
|
66
|
+
a1, a2 = nil, nil
|
67
|
+
a1, a2 = s1, s2 if s1.respond_to?(:-) and s2.respond_to?(:-)
|
68
|
+
a1, a2 = s1.scan(/./), s2.scan(/./) if s1.respond_to?(:scan) and s2.respond_to?(:scan)
|
69
|
+
|
70
|
+
if a1 and a2
|
71
|
+
return nil if (a1-a2).length >= threshold
|
72
|
+
return nil if (a2-a1).length >= threshold
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
distance_fast_or_slow(s1, s2, threshold)
|
77
|
+
end
|
78
|
+
|
79
|
+
def self.distance_fast_or_slow(s1, s2, threshold) # :nodoc:
|
80
|
+
if respond_to?(:levenshtein_distance_fast)
|
81
|
+
levenshtein_distance_fast(s1, s2, threshold) # Implemented in C.
|
82
|
+
else
|
83
|
+
levenshtein_distance_slow(s1, s2, threshold) # Implemented in Ruby.
|
84
|
+
end
|
85
|
+
end
|
86
|
+
|
87
|
+
def self.levenshtein_distance_slow(s1, s2, threshold) # :nodoc:
|
88
|
+
row = (0..s1.length).to_a
|
89
|
+
|
90
|
+
1.upto(s2.length) do |y|
|
91
|
+
prow = row
|
92
|
+
row = [y]
|
93
|
+
|
94
|
+
1.upto(s1.length) do |x|
|
95
|
+
row[x] = [prow[x]+1, row[x-1]+1, prow[x-1]+(s1[x-1]==s2[y-1] ? 0 : 1)].min
|
96
|
+
end
|
97
|
+
|
98
|
+
# Stop analysing this sequence as soon as the best possible
|
99
|
+
# result for this sequence is bigger than the best result so far.
|
100
|
+
# (The minimum value in the next row will be equal to or greater
|
101
|
+
# than the minimum value in this row.)
|
102
|
+
|
103
|
+
return nil if threshold and row.min >= threshold
|
104
|
+
end
|
105
|
+
|
106
|
+
row[-1]
|
107
|
+
end
|
108
|
+
end
|
109
|
+
|
110
|
+
|
111
|
+
def puts *arg
|
112
|
+
arg.each{|str| $stdout.puts str; $datafile.puts str}
|
113
|
+
end
|
114
|
+
|
115
|
+
def saveData
|
116
|
+
=begin
|
117
|
+
File.open('aktualdata.txt','w'){|f|
|
118
|
+
f.write "
|
119
|
+
$notfound=#{$notfound.length}
|
120
|
+
$same=#{$same.length}
|
121
|
+
$diff=#{$diff.length}
|
122
|
+
----
|
123
|
+
$notfound:
|
124
|
+
# {$notfound.join "\n"}
|
125
|
+
----
|
126
|
+
$same:
|
127
|
+
# {$same.join "\n"}
|
128
|
+
----
|
129
|
+
$diff:
|
130
|
+
# {$diff.join "\n"}
|
131
|
+
"
|
132
|
+
}
|
133
|
+
=end
|
134
|
+
end
|
135
|
+
|
136
|
+
def get(url)
|
137
|
+
return HTTP.get(URI.parse(url))
|
138
|
+
end
|
139
|
+
|
140
|
+
def getPlayerData url
|
141
|
+
r=get url
|
142
|
+
r=~/<b>All time playing career<\/b>/
|
143
|
+
r=$'
|
144
|
+
r=~/<a name=games><\/a>/
|
145
|
+
table=$`.strip
|
146
|
+
|
147
|
+
h=Hpricot.parse table
|
148
|
+
rows=h.search 'tr+tr'
|
149
|
+
|
150
|
+
data={}
|
151
|
+
rows.each do |r|
|
152
|
+
if r.at('td')['colspan']==nil && (r.inner_html=~/No appearance data available/)==nil
|
153
|
+
cells=r.search 'td'
|
154
|
+
team=cells[0].search('font a')[0].inner_html.strip
|
155
|
+
teamid=cells[0].search('font a')[0]['href'].sub(/\A.+?(\d+)\Z/, '\1')
|
156
|
+
matches=cells[4].at('font').inner_html.split('(').map{|m| m.gsub(/[^0-9]/,'').to_i}
|
157
|
+
matches=matches[0]+matches[1]
|
158
|
+
goals=cells[5].at('font').inner_html.gsub(/[^0-9]/,'').to_i
|
159
|
+
|
160
|
+
data[team]=[matches,goals,teamid]
|
161
|
+
end
|
162
|
+
end
|
163
|
+
return data
|
164
|
+
end
|
165
|
+
|
166
|
+
def searchForPlayer text
|
167
|
+
d=get "http://www.soccerbase.com/search.sd?search_string=#{CGI.escape text}&search_cat=players"
|
168
|
+
d=~/window.location = "(http:[^"]+)"/
|
169
|
+
|
170
|
+
return $1
|
171
|
+
end
|
172
|
+
|
173
|
+
$edits=0
|
174
|
+
$summary='aktualizacja danych o meczach piłkarza'
|
175
|
+
|
176
|
+
puts 'Making list...'
|
177
|
+
s=Sunflower.new('pl.wikipedia.org')
|
178
|
+
s.login
|
179
|
+
enw=Sunflower.new('en.wikipedia.org')
|
180
|
+
enw.login
|
181
|
+
|
182
|
+
# list=(
|
183
|
+
# s.makeList('category-r', 'Kategoria:Piłkarze Aston Villa F.C.')+
|
184
|
+
# s.makeList('category-r', 'Kategoria:Piłkarze Chelsea F.C.')+
|
185
|
+
# s.makeList('category-r', 'Kategoria:Piłkarze Liverpool F.C.')
|
186
|
+
# ).uniq
|
187
|
+
# list=(
|
188
|
+
# s.makeList('category-r', 'Kategoria:Piłkarze angielskich klubów')+
|
189
|
+
# s.makeList('category-r', 'Kategoria:Piłkarze walijskich klubów')
|
190
|
+
# ).uniq
|
191
|
+
|
192
|
+
# list.delete_if{|i| i=~/^Kategoria:/}
|
193
|
+
|
194
|
+
# File.open('lista-pilkarze.txt','w').write list.join("\n")
|
195
|
+
# list=File.open('lista-pilkarze.txt').read.split(/\r?\n/)
|
196
|
+
list=['Wikipedysta:Matma Rex/brudnopis']
|
197
|
+
|
198
|
+
puts 'Done!'
|
199
|
+
puts ''
|
200
|
+
|
201
|
+
$notfound=[]
|
202
|
+
$same=[]
|
203
|
+
$diff=[]
|
204
|
+
|
205
|
+
list.each_with_index do |art, i|
|
206
|
+
exit if $edits>4
|
207
|
+
|
208
|
+
# finding data
|
209
|
+
puts "* [[#{art}]]"
|
210
|
+
pPl=Page.new(art, 'pl')
|
211
|
+
pPl.read=~/\[\[en:([^\]]+)\]\]/
|
212
|
+
if $1
|
213
|
+
artEn=$1
|
214
|
+
puts "** Interwiki-en: [[:en:#{artEn}]]"
|
215
|
+
else
|
216
|
+
artEn=art
|
217
|
+
puts "** No interwiki; guessing [[:en:#{art}]]"
|
218
|
+
end
|
219
|
+
|
220
|
+
pPl.read=~/\{\{soccerbase.*?(\d+).*?\}\}|soccerbase\.com\/players_details\.sd\?playerid=(\d+)/i
|
221
|
+
if $1||$2
|
222
|
+
soccid=$1||$2
|
223
|
+
url="http://www.soccerbase.com/players_details.sd?playerid=#{soccid}"
|
224
|
+
puts '** Found id on plwiki'
|
225
|
+
else
|
226
|
+
pEn=Page.new(art, 'en')
|
227
|
+
pEn.read=~/\{\{soccerbase.*?(\d+).*?\}\}|soccerbase\.com\/players_details\.sd\?playerid=(\d+)/i
|
228
|
+
if $1||$2
|
229
|
+
soccid=$1||$2
|
230
|
+
url="http://www.soccerbase.com/players_details.sd?playerid=#{soccid}"
|
231
|
+
puts '** Found id on enwiki'
|
232
|
+
else
|
233
|
+
url=searchForPlayer(art)||searchForPlayer(artEn)
|
234
|
+
end
|
235
|
+
end
|
236
|
+
|
237
|
+
if url==nil
|
238
|
+
puts '** Not found.'
|
239
|
+
$notfound<<art
|
240
|
+
else
|
241
|
+
data=getPlayerData url
|
242
|
+
puts "** URL: #{url}"
|
243
|
+
unless data.empty?
|
244
|
+
puts "** Found info on soccerbase."
|
245
|
+
else
|
246
|
+
puts '** Found, but no data.'
|
247
|
+
$notfound<<art
|
248
|
+
end
|
249
|
+
end
|
250
|
+
|
251
|
+
pPl.read =~ /występy\(gole\)\s*=(.+)/
|
252
|
+
if $1==nil
|
253
|
+
puts '** Wiki: error. No infobox?'
|
254
|
+
else
|
255
|
+
a=$1.split(/\s*<br.*?>\s*/)[-1].strip
|
256
|
+
a=~/(\d+)\s*\((\d+)\)/
|
257
|
+
matchesW, goalsW = $1.to_i, $2.to_i
|
258
|
+
puts "** Wiki info: #{matchesW} matches, #{goalsW} goals."
|
259
|
+
end
|
260
|
+
|
261
|
+
saveData if i%30==0 && i!=0
|
262
|
+
|
263
|
+
# $change=File.open('changelist.txt','w')
|
264
|
+
# $change.sync=true
|
265
|
+
|
266
|
+
# editing
|
267
|
+
if data
|
268
|
+
#$change.puts "* [[#{art}]] - #{matchesW}/#{goalsW} -> #{matches}/#{goals}"
|
269
|
+
|
270
|
+
pPl.text=~/(kluby\s*=\s*)([^\|]+)(\s*\|)/
|
271
|
+
kluby=$2
|
272
|
+
pPl.text=~/(występy\(gole\)\s*=\s*)([^\|]+)(\s*\|)/
|
273
|
+
wystepygole=$2
|
274
|
+
|
275
|
+
resolve={}
|
276
|
+
kluby=kluby.split(/<\/?br[^>]*>/).map do |i|
|
277
|
+
short=i.strip.gsub(/\[\[(?:[^\]\|]+\||)([^\]\|]+)\]\]/,'\1').gsub(/→|\(wyp\.\)/,'').strip
|
278
|
+
resolve[short]=i.strip
|
279
|
+
short
|
280
|
+
end
|
281
|
+
wystepygole=wystepygole.split(/<\/?br[^>]*?>/).map{|i| i.strip}
|
282
|
+
wystepygole.delete_if{|i| i==''}
|
283
|
+
kluby.delete_if{|i| i==''}
|
284
|
+
|
285
|
+
wystepygole.pop while wystepygole.length>kluby.length
|
286
|
+
wystepygole.push [0,0] while wystepygole.length<kluby.length
|
287
|
+
|
288
|
+
wikidata=OrderedHash.new
|
289
|
+
kluby.each_index do |i|
|
290
|
+
wystepygole[i]=~/(\d+)\s*\((\d+)\)/
|
291
|
+
wikidata[kluby[i]]=[$1.to_i, $2.to_i]
|
292
|
+
end
|
293
|
+
|
294
|
+
# puts data.inspect
|
295
|
+
# puts wikidata.inspect
|
296
|
+
|
297
|
+
data.each_pair do |scbclub, scb, teamid|
|
298
|
+
min=[999, 'null']
|
299
|
+
wikidata.each_pair do |wikiclub, wiki|
|
300
|
+
if wikiclub.index scbclub || scbclub.index wikiclub
|
301
|
+
min=[0, wikiclub]
|
302
|
+
break
|
303
|
+
end
|
304
|
+
if wikiclub.index id2team[teamid] || id2team[teamid].index wikiclub
|
305
|
+
min=[0, wikiclub]
|
306
|
+
break
|
307
|
+
end
|
308
|
+
|
309
|
+
d=Levenshtein.distance(scbclub, wikiclub)
|
310
|
+
min=[d, wikiclub] if d<min[0]
|
311
|
+
|
312
|
+
d=Levenshtein.distance(id2team[teamid], wikiclub)
|
313
|
+
min=[d, wikiclub] if d<min[0]
|
314
|
+
end
|
315
|
+
club=min[1]
|
316
|
+
|
317
|
+
wikidata[club]=data[scbclub]
|
318
|
+
end
|
319
|
+
|
320
|
+
infoboxwystepygole=[]
|
321
|
+
infoboxkluby=[]
|
322
|
+
|
323
|
+
wikidata.each do |club, info|
|
324
|
+
infoboxkluby<<resolve[club]
|
325
|
+
infoboxwystepygole<<"#{info[0]} (#{info[1]})"
|
326
|
+
end
|
327
|
+
|
328
|
+
infoboxkluby=infoboxkluby.join('<br />')
|
329
|
+
infoboxwystepygole=infoboxwystepygole.join('<br />')
|
330
|
+
|
331
|
+
pPl.text=pPl.text.sub(/(występy\(gole\)\s*=\s*)([^\|]+?)(\s*\|)/){$1+infoboxwystepygole+$3}
|
332
|
+
pPl.text=pPl.text.sub(/(kluby\s*=\s*)([^\|]+?)(\s*\|)/){$1+infoboxkluby+$3}
|
333
|
+
pPl.text=pPl.text.sub(/(data1\s*=\s*)([^\|]+?)(\s*\|)/, '\1{{subst:CURRENTDAY}} {{subst:CURRENTMONTHNAMEGEN}} {{subst:CURRENTYEAR}}\3')
|
334
|
+
|
335
|
+
$edits+=1
|
336
|
+
pPl.save
|
337
|
+
end
|
338
|
+
end
|
339
|
+
|
@@ -0,0 +1,36 @@
|
|
1
|
+
#!/usr/bin/ruby
|
2
|
+
print "Content-type: text/html; charset=utf8\n\r\n"
|
3
|
+
$stderr=$stdout
|
4
|
+
|
5
|
+
require 'sunflower-core.rb'
|
6
|
+
|
7
|
+
s=Sunflower.new('pl.wikipedia.org')
|
8
|
+
s.log=false
|
9
|
+
s.login
|
10
|
+
cgi=CGI.new
|
11
|
+
|
12
|
+
|
13
|
+
puts ''
|
14
|
+
puts '<p>Get list for: <form action="author-list.rb" method="GET"><input name="title"> <input type="submit" value="Go!"></form></p>'
|
15
|
+
|
16
|
+
if cgi['title'] && cgi['title']!=''
|
17
|
+
puts '<p>List of authors of '+cgi['title']+':</p>'
|
18
|
+
|
19
|
+
users=[]
|
20
|
+
hash=s.API("action=query&prop=revisions&titles=#{CGI.escape(cgi['title'])}&rvprop=user&rvlimit=5000")
|
21
|
+
hash['query']['pages'].values[0]['revisions'].each do |r|
|
22
|
+
users<<r['user']
|
23
|
+
end
|
24
|
+
while hash['query-continue']
|
25
|
+
hash=s.API("action=query&prop=revisions&titles=#{CGI.escape(cgi['title'])}&rvprop=user&rvlimit=5000&rvstartid=#{hash['query-continue']['revisions']['rvstartid']}")
|
26
|
+
hash['query']['pages'].values[0]['revisions'].each do |r|
|
27
|
+
users<<r['user']
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
users.uniq!
|
32
|
+
|
33
|
+
|
34
|
+
puts '<ul><li>'+users.join('</li><li>')+'</li></ul>'
|
35
|
+
end
|
36
|
+
|
@@ -0,0 +1,42 @@
|
|
1
|
+
require 'sunflower-commontasks.rb'
|
2
|
+
require 'sunflower-listmaker.rb'
|
3
|
+
|
4
|
+
image='Plik:Obiekt zabytkowy znak.svg'
|
5
|
+
|
6
|
+
# EDIT WIKI URL BELOW
|
7
|
+
s=Sunflower.new('pl.wikipedia.org')
|
8
|
+
|
9
|
+
print "Logging in to #{s.wikiURL}... "
|
10
|
+
# EDIT USERNAME AND PASSWORD BELOW
|
11
|
+
s.login
|
12
|
+
print "done!\n"
|
13
|
+
|
14
|
+
print "Reading articles list... "
|
15
|
+
# EDIT FILENAME BELOW
|
16
|
+
list=s.make_list('image', image).sort
|
17
|
+
print "done!\n\n"
|
18
|
+
|
19
|
+
# EDIT SUMMARY BELOW
|
20
|
+
$summary='podmiana grafiki, [[WP:SK]]'
|
21
|
+
|
22
|
+
list.each do |title|
|
23
|
+
print "Reading page #{title}... "
|
24
|
+
page=Page.get(title)
|
25
|
+
print "done.\n"
|
26
|
+
print "Modifying... "
|
27
|
+
|
28
|
+
page.codeCleanup
|
29
|
+
|
30
|
+
page.text.gsub!(/\[\[#{Regexp.escape image} *\|(?:left\||)[1-6]\dpx(?:\|left|)(\|[^\]\|]+|)\]\]( *(?:\r?\n|) *|)/) do
|
31
|
+
next if $~[0].index('thumb') || $~[0].index('right')
|
32
|
+
"[[Plik:Obiekt zabytkowy.svg|20px#{$1}]] "
|
33
|
+
end
|
34
|
+
|
35
|
+
print "done.\n"
|
36
|
+
print "Saving... "
|
37
|
+
page.save unless page.orig_text.downcase==page.text.downcase
|
38
|
+
print "done!\n\n"
|
39
|
+
end
|
40
|
+
|
41
|
+
print 'Finished! Press any key to close.'
|
42
|
+
gets
|
@@ -0,0 +1,53 @@
|
|
1
|
+
require "algorithm/diff"
|
2
|
+
require 'sunflower-commontasks.rb'
|
3
|
+
require 'sunflower-listmaker.rb'
|
4
|
+
|
5
|
+
# EDIT WIKI URL BELOW
|
6
|
+
s=Sunflower.new
|
7
|
+
|
8
|
+
print "Logging in to #{s.wikiURL}... "
|
9
|
+
# EDIT USERNAME AND PASSWORD BELOW
|
10
|
+
s.login
|
11
|
+
print "done!\n"
|
12
|
+
|
13
|
+
print "Reading articles list... "
|
14
|
+
# EDIT FILENAME BELOW
|
15
|
+
list=s.make_list('file', 'list2.txt')
|
16
|
+
print "done!\n\n"
|
17
|
+
|
18
|
+
# EDIT SUMMARY BELOW
|
19
|
+
$summary='usuwanie pogrubień z nagłówków, [[WP:SK]]'
|
20
|
+
|
21
|
+
list.each do |title|
|
22
|
+
print "Reading page #{title}... "
|
23
|
+
page=Page.get(title)
|
24
|
+
print "done.\n"
|
25
|
+
print "Modifying... "
|
26
|
+
|
27
|
+
oldtxt=page.read
|
28
|
+
|
29
|
+
page.replace(/(==+)\s*'''\s*(.+?)\s*'''\s*\1/, '\1 \2 \1') #simplest fix
|
30
|
+
page.replace(/(==+)([^']*)'''([^']*)\1/, '\1\2\3\1') #broken bolds - opened, but not closed, remove them
|
31
|
+
page.write page.text.gsub(/(==+)\s*(Znan.+? (?:osoby|ludzie) (?:nosz|o imien).+?)\s*\1/){h=$1; "#{h} #{$2.gsub("'''", '')} #{h}"} #pl.wiki specific
|
32
|
+
page.write page.text.gsub(/(==+)\s*(.+?(?:\[\[imieniny\]\]|imieniny) obchodzi)\s*\1/){h=$1; "#{h} #{$2.gsub("'''", '')} #{h}"} #pl.wiki specific
|
33
|
+
|
34
|
+
if oldtxt==page.read
|
35
|
+
print "No changes.\n\n"
|
36
|
+
next
|
37
|
+
end
|
38
|
+
|
39
|
+
page.codeCleanup
|
40
|
+
|
41
|
+
# diffs = oldtxt.diff(page.read)
|
42
|
+
|
43
|
+
# puts diffs
|
44
|
+
# gets
|
45
|
+
|
46
|
+
print "done.\n"
|
47
|
+
print "Saving... "
|
48
|
+
page.save
|
49
|
+
print "done!\n\n"
|
50
|
+
end
|
51
|
+
|
52
|
+
print 'Finished! Press any key to close.'
|
53
|
+
gets
|