59
60
'findarticles\.com',
66
'search\.earthlink\.net',
68
# Minor brazilian search engines
67
'search\.earthlink\.net',
69
# Minor brazilian search engines
69
70
'engine\.exe', 'miner\.bol\.com\.br',
70
71
# Minor chinese search engines
71
72
'baidu\.com','search\.sina\.com','search\.sohu\.com',
72
73
# Minor czech search engines
73
'atlas\.cz','seznam\.cz','quick\.cz','centrum\.cz','najdi\.to','redbox\.cz',
74
'atlas\.cz','seznam\.cz','quick\.cz','centrum\.cz','jyxo\.(cz|com)','najdi\.to','redbox\.cz',
74
75
# Minor danish search-engines
75
76
'opasia\.dk', 'danielsen\.com', 'sol\.dk', 'jubii\.dk', 'find\.dk', 'edderkoppen\.dk', 'netstjernen\.dk', 'orbis\.dk', 'tyfon\.dk', '1klik\.dk', 'ofir\.dk',
76
77
# Minor dutch search engines
77
78
'ilse\.','vindex\.',
78
79
# Minor english search engines
79
'(^|\.)ask\.co\.uk','bbc\.co\.uk/cgi-bin/search','ifind\.freeserve','looksmart\.co\.uk','mirago\.','splut\.','spotjockey\.','ukdirectory\.','ukindex\.co\.uk','ukplus\.','searchy\.co\.uk',
80
# Minor finnish search engines
80
'(^|\.)ask\.co\.uk','bbc\.co\.uk/cgi-bin/search','ifind\.freeserve','looksmart\.co\.uk','mirago\.','splut\.','spotjockey\.','ukdirectory\.','ukindex\.co\.uk','ukplus\.','searchy\.co\.uk',
81
# Minor finnish search engines
82
# Minor french search engines
83
'recherche\.aol\.fr','ctrouve\.','francite\.','\.lbb\.org','rechercher\.libertysurf\.fr', 'search[\w\-]+\.free\.fr', 'recherche\.club-internet\.fr',
84
# Minor german search engines
83
# Minor french search engines
84
'recherche\.aol\.fr','ctrouve\.','francite\.','\.lbb\.org','rechercher\.libertysurf\.fr', 'search[\w\-]+\.free\.fr', 'recherche\.club-internet\.fr',
85
# Minor german search engines
86
87
'fireball\.de','infoseek\.de','suche\d?\.web\.de','[a-z]serv\.rrzn\.uni-hannover\.de',
87
88
'suchen\.abacho\.de','brisbane\.t-online\.de','allesklar\.de','meinestadt\.de',
89
'(161\.58\.227\.204|161\.58\.247\.101|212\.40\.165\.90|213\.133\.108\.202|217\.160\.108\.151|217\.160\.111\.99|217\.160\.131\.108|217\.160\.142\.227|217\.160\.176\.42)',
90
'(161\.58\.227\.204|161\.58\.247\.101|212\.40\.165\.90|213\.133\.108\.202|217\.160\.108\.151|217\.160\.111\.99|217\.160\.131\.108|217\.160\.142\.227|217\.160\.176\.42)',
90
91
# Minor hungarian search engines
91
92
'heureka\.hu','vizsla\.origo\.hu','lapkereso\.hu','goliat\.hu','index\.hu','wahoo\.hu','webmania\.hu','search\.internetto\.hu',
92
93
# Minor italian search engines
94
95
# Minor norvegian search engines
96
# Minor polish search engines
97
# Minor polish search engines
98
99
# Minor russian search engines
99
100
'ya(ndex)?\.ru', 'aport\.ru', 'rambler\.ru', 'turtle\.ru', 'metabot\.ru',
100
101
# Minor swedish search engines
101
'evreka\.passagen\.se',
102
# Minor swiss search engines
103
'search\.ch', 'search\.bluewin\.ch'
102
'evreka\.passagen\.se',
103
# Minor swiss search engines
104
'search\.ch', 'search\.bluewin\.ch'
105
106
@SearchEnginesSearchIDOrder_listgen=(
106
# Generic search engines
107
# Generic search engines
107
108
'search\..*\.\w+'
159
161
'findarticles\.com','findarticles',
160
162
'infospace\.com','infospace',
161
163
'mamma\.','mamma',
162
'dejanews\.','dejanews',
163
'dogpile\.com','dogpile',
164
'dejanews\.','dejanews',
165
'dogpile\.com','dogpile',
164
166
'wisenut\.com','wisenut',
165
'ixquick\.com','ixquick',
166
'search\.earthlink\.net','earthlink',
168
# Minor brazilian search engines
167
'ixquick\.com','ixquick',
168
'search\.earthlink\.net','earthlink',
170
# Minor brazilian search engines
169
171
'engine\.exe','engine',
170
172
'miner\.bol\.com\.br','miner',
171
173
# Minor chinese search engines
205
208
'ukdirectory\.','ukdirectory',
206
209
'ukindex\.co\.uk','ukindex',
207
210
'ukplus\.','ukplus',
208
'searchy\.co\.uk','searchy',
209
# Minor finnish search engines
211
'searchy\.co\.uk','searchy',
212
# Minor finnish search engines
210
213
'haku\.www\.fi','haku',
211
# Minor french search engines
214
# Minor french search engines
212
215
'recherche\.aol\.fr','aolfr',
213
216
'ctrouve\.','ctrouve',
214
217
'francite\.','francite',
215
218
'\.lbb\.org','lbb',
216
219
'rechercher\.libertysurf\.fr','libertysurf',
217
220
'search[\w\-]+\.free\.fr','free',
218
'recherche\.club-internet\.fr','clubinternet',
219
# Minor german search engines
220
'sucheaol\.aol\.de','aolde',
221
'recherche\.club-internet\.fr','clubinternet',
222
# Minor german search engines
223
'sucheaol\.aol\.de','aolde',
221
224
'fireball\.de','fireball',
222
225
'infoseek\.de','infoseek',
223
'suche\d?\.web\.de','webde',
224
'[a-z]serv\.rrzn\.uni-hannover\.de','meta',
226
'suche\d?\.web\.de','webde',
227
'[a-z]serv\.rrzn\.uni-hannover\.de','meta',
225
228
'suchen\.abacho\.de','abacho',
226
229
'brisbane\.t-online\.de','t-online',
227
230
'allesklar\.de','allesklar',
228
231
'meinestadt\.de','meinestadt',
229
'212\.227\.33\.241','metaspinner',
230
'(161\.58\.227\.204|161\.58\.247\.101|212\.40\.165\.90|213\.133\.108\.202|217\.160\.108\.151|217\.160\.111\.99|217\.160\.131\.108|217\.160\.142\.227|217\.160\.176\.42)','metacrawler_de',
232
'212\.227\.33\.241','metaspinner',
233
'(161\.58\.227\.204|161\.58\.247\.101|212\.40\.165\.90|213\.133\.108\.202|217\.160\.108\.151|217\.160\.111\.99|217\.160\.131\.108|217\.160\.142\.227|217\.160\.176\.42)','metacrawler_de',
231
234
# Minor hungarian search engines
232
235
'heureka\.hu','heureka',
233
236
'vizsla\.origo\.hu','origo',
250
253
'turtle\.ru','turtle',
251
254
'metabot\.ru','metabot',
252
255
# Minor swedish search engines
253
'evreka\.passagen\.se','passagen',
254
# Minor swiss search engines
256
'evreka\.passagen\.se','passagen',
257
# Minor swiss search engines
255
258
'search\.ch','searchch',
256
'search\.bluewin\.ch','bluewin',
257
# Generic search engines
259
'search\.bluewin\.ch','bluewin',
260
# Generic search engines
258
261
'search\..*\.\w+','search'
265
# SearchEnginesWithKeysNotInQuery
266
# List of search engines that store keyword as page instead of query parameter
267
#------------------------------------------------------------------------------
268
%SearchEnginesWithKeysNotInQuery=(
269
'a9',1 # www.a9.com/searckey1%20searchkey2
262
272
# SearchEnginesKnownUrl
263
273
# Known rules to extract keywords from a referrer search engine URL
264
274
#------------------------------------------------------------------------------
295
306
'metacrawler','general=',
296
307
'nbci','keyword=',
297
308
'northernlight','qr=',
298
'overture','keywords=',
299
'dogpile', 'q(|kw)=',
309
'overture','keywords=',
310
'dogpile', 'q(|kw)=',
302
313
'virgilio','qs=',
303
'webcrawler','searchText=',
307
'iune','(keywords|q)=',
308
# Minor brazilian search engines
314
'webcrawler','searchText=',
318
'iune','(keywords|q)=',
319
# Minor brazilian search engines
309
320
'engine','p1=', 'miner','q=',
310
321
# Minor chinese search engines
311
322
'baidu','word=', 'sina', 'word=', 'sohu','word=',
312
323
# Minor czech search engines
313
'atlas','searchtext=', 'seznam','w=', 'quick','query=', 'centrum','q=', 'najdi','dotaz=', 'redbox','srch=',
324
'atlas','searchtext=', 'seznam','w=', 'quick','query=', 'centrum','q=', 'jyxo','s=', 'najdi','dotaz=', 'redbox','srch=',
314
325
# Minor danish search engines
315
326
'opasia','q=', 'danielsen','q=', 'sol','q=', 'jubii','soegeord=', 'finddk','words=', 'edderkoppen','query=', 'orbis','search_field=', '1klik','query=', 'ofir','querytext=',
316
327
# Minor dutch search engines
321
332
# Minor finnish search engines
323
334
# Minor french search engines
324
'francite','name=', 'clubinternet', 'q=',
335
'francite','name=', 'clubinternet', 'q=',
325
336
# Minor german search engines
327
338
'fireball','q=', 'infoseek','qt=', 'webde','su=',
328
339
'abacho','q=', 't-online','q=',
329
'metaspinner','qry=',
330
'metacrawler_de','qry=',
340
'metaspinner','qry=',
341
'metacrawler_de','qry=',
331
342
# Minor hungarian search engines
332
343
'heureka','heureka=', 'origo','(q|search)=', 'goliat','KERESES=', 'wahoo','q=', 'internetto','searchstr=',
333
344
# Minor norvegian search engines
335
# Minor polish search engines
346
# Minor polish search engines
337
348
# Minor russian search engines
338
349
'yandex', 'text=', 'rambler','words=', 'aport', 'r=', 'metabot', 'st=',
339
# Minor swedish search engines
341
# Minor swiss search engines
342
'searchch', 'q=', 'bluewin', 'qry='
350
# Minor swedish search engines
352
# Minor swiss search engines
353
'searchch', 'q=', 'bluewin', 'qry='
345
356
# SearchEnginesKnownUrlNotFound
405
417
'metacrawler','MetaCrawler (Metamoteur)',
407
419
'northernlight','NorthernLight',
408
'overture','Overture', # Replace 'goto\.com','Goto.com',
420
'overture','Overture', # Replace 'goto\.com','Goto.com',
411
423
'teoma','Teoma', # Replace 'directhit\.com','DirectHit',
412
'webcrawler','WebCrawler',
414
'ixquick', 'ix quick',
415
'earthlink', 'Earth Link',
424
'webcrawler','WebCrawler',
426
'ixquick', 'ix quick',
427
'earthlink', 'Earth Link',
417
429
# Minor brazilian search engines
418
430
'engine','Cade', 'miner','Meta Miner',
419
431
# Minor chinese search engines
420
432
'baidu','Baidu', 'sina','Sina', 'sohu','Sohu',
421
433
# Minor czech search engines
422
'atlas','Atlas.cz', 'seznam','Seznam', 'quick','Quick.cz', 'centrum','Centrum.cz','najdi','Najdi.to','redbox','RedBox.cz',
434
'atlas','Atlas.cz', 'seznam','Seznam', 'quick','Quick.cz', 'centrum','Centrum.cz', 'jyxo','Jyxo.cz', 'najdi','Najdi.to', 'redbox','RedBox.cz',
423
435
# Minor danish search-engines
424
436
'opasia','Opasia', 'danielsen','Thor (danielsen.com)', 'sol','SOL', 'jubii','Jubii', 'finddk','Find', 'edderkoppen','Edderkoppen', 'netstjernen','Netstjernen', 'orbis','Orbis', 'tyfon','Tyfon', '1klik','1Klik', 'ofir','Ofir',
425
437
# Minor dutch search engines
430
442
# Minor finnish search engines
431
443
'haku','Ihmemaa',
432
444
# Minor french search engines
433
'aolfr','AOL (fr)', 'ctrouve','C\'est trouv�', 'francite','Francit�', 'lbb', 'LBB', 'libertysurf', 'Libertysurf', 'free', 'Free.fr', 'clubinternet', 'Club-internet',
445
'aolfr','AOL (fr)', 'ctrouve','C\'est trouv�', 'francite','Francit�', 'lbb', 'LBB', 'libertysurf', 'Libertysurf', 'free', 'Free.fr', 'clubinternet', 'Club-internet',
434
446
# Minor german search engines
436
448
'fireball','Fireball', 'infoseek','Infoseek', 'webde','Web.de',
437
449
'abacho','Abacho', 't-online','T-Online',
438
450
'allesklar','allesklar.de', 'meinestadt','meinestadt.de',
439
'metaspinner','metaspinner',
440
'metacrawler_de','metacrawler.de',
451
'metaspinner','metaspinner',
452
'metacrawler_de','metacrawler.de',
441
453
# Minor hungarian search engines
442
454
'heureka','Heureka', 'origo','Origo-Vizsla', 'lapkereso','Startlapkeres�', 'goliat','G�li�t', 'indexhu','Index', 'wahoo','Wahoo', 'webmania','webmania.hu', 'internetto','Internetto Keres�',
443
455
# Minor italian search engines
444
456
'virgilio','Virgilio',
445
457
# Minor norvegian search engines
446
458
'start','start.no',
447
# Minor polish search engines
459
# Minor polish search engines
449
461
# Minor russian search engines
450
462
'yandex', 'Yandex', 'aport', 'Aport', 'rambler', 'Rambler', 'turtle', 'Turtle', 'metabot', 'MetaBot',
451
# Minor swedish search engines
453
# Minor Swiss search engines
454
'searchch', 'search.ch', 'bluewin', 'search.bluewin.ch',
455
# Generic search engines
463
# Minor swedish search engines
465
# Minor Swiss search engines
466
'searchch', 'search.ch', 'bluewin', 'search.bluewin.ch',
467
# Generic search engines
456
468
'search','Unknown search engines'