forked from WikiTeam/wikiteam
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdumpgenerator.py
executable file
·2084 lines (1858 loc) · 80.6 KB
/
dumpgenerator.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
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
97
98
99
100
101
102
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
# dumpgenerator.py A generator of dumps for wikis
# Copyright (C) 2011-2016 WikiTeam developers
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
# To learn more, read the documentation:
# https://github.com/WikiTeam/wikiteam/wiki
try:
from kitchen.text.converters import getwriter
except ImportError:
print "Please install the kitchen module."
import cookielib
import cPickle
import datetime
import sys
try:
import argparse
except ImportError:
print "Please install the argparse module."
sys.exit(1)
import json
try:
from hashlib import md5
except ImportError: # Python 2.4 compatibility
from md5 import new as md5
import os
import re
try:
import requests
except ImportError:
print "Please install or update the Requests module."
sys.exit(1)
import time
import urllib
UTF8Writer = getwriter('utf8')
sys.stdout = UTF8Writer(sys.stdout)
__VERSION__ = '0.3.0-alpha' # major, minor, micro: semver.org
class PageMissingError(Exception):
def __init__(self, title, xml):
self.title = title
self.xml = xml
def __str__(self):
return "page '%s' not found" % self.title
class ExportAbortedError(Exception):
def __init__(self, index):
self.index = index
def __str__(self):
return "Export from '%s' did not return anything." % self.index
def getVersion():
return(__VERSION__)
def truncateFilename(other={}, filename=''):
""" Truncate filenames when downloading images with large filenames """
return filename[:other['filenamelimit']] + \
md5(filename.encode('utf-8')).hexdigest() + '.' + filename.split('.')[-1]
def delay(config={}, session=None):
""" Add a delay if configured for that """
if config['delay'] > 0:
print 'Sleeping... %d seconds...' % (config['delay'])
time.sleep(config['delay'])
def cleanHTML(raw=''):
""" Extract only the real wiki content and remove rubbish """
""" This function is ONLY used to retrieve page titles and file names when no API is available """
""" DO NOT use this function to extract page content """
# different "tags" used by different MediaWiki versions to mark where
# starts and ends content
if re.search('<!-- bodytext -->', raw):
raw = raw.split('<!-- bodytext -->')[1].split('<!-- /bodytext -->')[0]
elif re.search('<!-- start content -->', raw):
raw = raw.split(
'<!-- start content -->')[1].split('<!-- end content -->')[0]
elif re.search('<!-- Begin Content Area -->', raw):
raw = raw.split(
'<!-- Begin Content Area -->')[1].split('<!-- End Content Area -->')[0]
elif re.search('<!-- content -->', raw):
raw = raw.split('<!-- content -->')[1].split('<!-- mw_content -->')[0]
elif re.search('<article id="WikiaMainContent" class="WikiaMainContent">', raw):
raw = raw.split('<article id="WikiaMainContent" class="WikiaMainContent">')[
1].split('</article>')[0]
elif re.search('<body class=', raw):
raw = raw.split('<body class=')[1].split(
'<div class="printfooter">')[0]
else:
print raw[:250]
print 'This wiki doesn\'t use marks to split content'
sys.exit()
return raw
def handleStatusCode(response):
statuscode = response.status_code
if statuscode >= 200 and statuscode < 300:
return
print "HTTP Error %d." % statuscode
if statuscode >= 300 and statuscode < 400:
print "Redirect should happen automatically: please report this as a bug."
print response.url
elif statuscode == 400:
print "Bad Request: The wiki may be malfunctioning."
print "Please try again later."
print response.url
sys.exit(1)
elif statuscode == 401 or statuscode == 403:
print "Authentication required."
print "Please use --userpass."
print response.url
elif statuscode == 404:
print "Not found. Is Special:Export enabled for this wiki?"
print response.url
sys.exit(1)
elif statuscode == 429 or (statuscode >= 500 and statuscode < 600):
print "Server error, max retries exceeded."
print "Please resume the dump later."
print response.url
sys.exit(1)
def getNamespacesScraper(config={}, session=None):
""" Hackishly gets the list of namespaces names and ids from the dropdown in the HTML of Special:AllPages """
""" Function called if no API is available """
namespaces = config['namespaces']
namespacenames = {0: ''} # main is 0, no prefix
if namespaces:
r = session.post(
url=config['index'], data={'title': 'Special:Allpages'})
raw = r.text
delay(config=config, session=session)
# [^>]*? to include selected="selected"
m = re.compile(
r'<option [^>]*?value="(?P<namespaceid>\d+)"[^>]*?>(?P<namespacename>[^<]+)</option>').finditer(raw)
if 'all' in namespaces:
namespaces = []
for i in m:
namespaces.append(int(i.group("namespaceid")))
namespacenames[int(i.group("namespaceid"))] = i.group(
"namespacename")
else:
# check if those namespaces really exist in this wiki
namespaces2 = []
for i in m:
if int(i.group("namespaceid")) in namespaces:
namespaces2.append(int(i.group("namespaceid")))
namespacenames[int(i.group("namespaceid"))] = i.group(
"namespacename")
namespaces = namespaces2
else:
namespaces = [0]
namespaces = list(set(namespaces)) # uniques
print '%d namespaces found' % (len(namespaces))
return namespaces, namespacenames
def getNamespacesAPI(config={}, session=None):
""" Uses the API to get the list of namespaces names and ids """
namespaces = config['namespaces']
namespacenames = {0: ''} # main is 0, no prefix
if namespaces:
r = session.post(
url=config['api'],
data={
'action': 'query',
'meta': 'siteinfo',
'siprop': 'namespaces',
'format': 'json'}
)
result = getJSON(r)
delay(config=config, session=session)
if 'all' in namespaces:
namespaces = []
for i in result['query']['namespaces'].keys():
if int(i) < 0: # -1: Special, -2: Media, excluding
continue
namespaces.append(int(i))
namespacenames[int(i)] = result['query']['namespaces'][i]['*']
else:
# check if those namespaces really exist in this wiki
namespaces2 = []
for i in result['query']['namespaces'].keys():
bi = i
i = int(i)
if i < 0: # -1: Special, -2: Media, excluding
continue
if i in namespaces:
namespaces2.append(i)
namespacenames[i] = result['query']['namespaces'][bi]['*']
namespaces = namespaces2
else:
namespaces = [0]
namespaces = list(set(namespaces)) # uniques
print '%d namespaces found' % (len(namespaces))
return namespaces, namespacenames
def getPageTitlesAPI(config={}, session=None):
""" Uses the API to get the list of page titles """
titles = []
namespaces, namespacenames = getNamespacesAPI(
config=config, session=session)
for namespace in namespaces:
if namespace in config['exnamespaces']:
print ' Skipping namespace = %d' % (namespace)
continue
c = 0
print ' Retrieving titles in the namespace %d' % (namespace)
apfrom = '!'
while apfrom:
sys.stderr.write('.') # progress
params = {
'action': 'query',
'list': 'allpages',
'apnamespace': namespace,
'apfrom': apfrom.encode('utf-8'),
'format': 'json',
'aplimit': 500}
retryCount = 0
while retryCount < config["retries"]:
try:
r = session.post(url=config['api'], data=params)
break
except ConnectionError as err:
print "Connection error: %s" % (str(err),)
retryCount += 1
time.sleep(20)
handleStatusCode(r)
# FIXME Handle HTTP errors here!
jsontitles = getJSON(r)
apfrom = ''
if 'query-continue' in jsontitles and 'allpages' in jsontitles[
'query-continue']:
if 'apcontinue' in jsontitles['query-continue']['allpages']:
apfrom = jsontitles[
'query-continue']['allpages']['apcontinue']
elif 'apfrom' in jsontitles['query-continue']['allpages']:
apfrom = jsontitles['query-continue']['allpages']['apfrom']
elif 'continue' in jsontitles:
if 'apcontinue' in jsontitles['continue']:
apfrom = jsontitles['continue']['apcontinue']
elif 'apfrom' in jsontitles['continue']:
apfrom = jsontitles['continue']['apfrom']
# print apfrom
# print jsontitles
allpages = jsontitles['query']['allpages']
# Hack for old versions of MediaWiki API where result is dict
if isinstance(allpages, dict):
allpages = allpages.values()
for page in allpages:
yield page['title']
c += len(allpages)
if len(titles) != len(set(titles)):
# probably we are in a loop, server returning dupe titles, stop
# it
print 'Probably a loop, finishing'
titles = list(set(titles))
apfrom = ''
delay(config=config, session=session)
print ' %d titles retrieved in the namespace %d' % (c, namespace)
def getPageTitlesScraper(config={}, session=None):
""" Scrape the list of page titles from Special:Allpages """
titles = []
namespaces, namespacenames = getNamespacesScraper(
config=config, session=session)
for namespace in namespaces:
print ' Retrieving titles in the namespace', namespace
url = '%s?title=Special:Allpages&namespace=%s' % (
config['index'], namespace)
r = session.get(url=url)
raw = r.text
raw = cleanHTML(raw)
r_title = r'title="(?P<title>[^>]+)">'
r_suballpages = ''
r_suballpages1 = r'&from=(?P<from>[^>]+)&to=(?P<to>[^>]+)">'
r_suballpages2 = r'Special:Allpages/(?P<from>[^>]+)">'
r_suballpages3 = r'&from=(?P<from>[^>]+)" title="[^>]+">'
if re.search(r_suballpages1, raw):
r_suballpages = r_suballpages1
elif re.search(r_suballpages2, raw):
r_suballpages = r_suballpages2
elif re.search(r_suballpages3, raw):
r_suballpages = r_suballpages3
else:
pass # perhaps no subpages
# 3 is the current deep of English Wikipedia for Special:Allpages
deep = 3
c = 0
checked_suballpages = []
rawacum = raw
while r_suballpages and re.search(r_suballpages, raw) and c < deep:
# load sub-Allpages
m = re.compile(r_suballpages).finditer(raw)
for i in m:
fr = i.group('from')
if r_suballpages == r_suballpages1:
to = i.group('to')
name = '%s-%s' % (fr, to)
url = '%s?title=Special:Allpages&namespace=%s&from=%s&to=%s' % (
config['index'], namespace, fr, to) # do not put urllib.quote in fr or to
# fix, esta regexp no carga bien todas? o falla el r_title en
# este tipo de subpag? (wikiindex)
elif r_suballpages == r_suballpages2:
# clean &namespace=\d, sometimes happens
fr = fr.split('&namespace=')[0]
name = fr
url = '%s?title=Special:Allpages/%s&namespace=%s' % (
config['index'], name, namespace)
elif r_suballpages == r_suballpages3:
fr = fr.split('&namespace=')[0]
name = fr
url = '%s?title=Special:Allpages&from=%s&namespace=%s' % (
config['index'], name, namespace)
if name not in checked_suballpages:
# to avoid reload dupe subpages links
checked_suballpages.append(name)
delay(config=config, session=session)
r2 = session.get(url=url)
raw2 = r2.text
raw2 = cleanHTML(raw2)
rawacum += raw2 # merge it after removed junk
print ' Reading', name, len(raw2), 'bytes', \
len(re.findall(r_suballpages, raw2)), 'subpages', \
len(re.findall(r_title, raw2)), 'pages'
delay(config=config, session=session)
c += 1
c = 0
m = re.compile(r_title).finditer(rawacum)
for i in m:
t = undoHTMLEntities(text=i.group('title'))
if not t.startswith('Special:'):
if t not in titles:
titles.append(t)
c += 1
print ' %d titles retrieved in the namespace %d' % (c, namespace)
return titles
def getPageTitles(config={}, session=None):
""" Get list of page titles """
# http://en.wikipedia.org/wiki/Special:AllPages
# http://archiveteam.org/index.php?title=Special:AllPages
# http://www.wikanda.es/wiki/Especial:Todas
print 'Loading page titles from namespaces = %s' % (config['namespaces'] and ','.join([str(i) for i in config['namespaces']]) or 'None')
print 'Excluding titles from namespaces = %s' % (config['exnamespaces'] and ','.join([str(i) for i in config['exnamespaces']]) or 'None')
titles = []
if 'api' in config and config['api']:
r = session.post(config['api'], {'action': 'query', 'list': 'allpages', 'format': 'json'})
test = getJSON(r)
if ('warnings' in test and 'allpages' in test['warnings'] and '*' in test['warnings']['allpages']
and test['warnings']['allpages']['*'] == 'The "allpages" module has been disabled.'):
titles = getPageTitlesScraper(config=config, session=session)
else:
titles = getPageTitlesAPI(config=config, session=session)
elif 'index' in config and config['index']:
titles = getPageTitlesScraper(config=config, session=session)
titlesfilename = '%s-%s-titles.txt' % (
domain2prefix(config=config), config['date'])
titlesfile = open('%s/%s' % (config['path'], titlesfilename), 'wt')
c = 0
for title in titles:
titlesfile.write(title.encode('utf-8') + "\n")
c += 1
# TODO: Sort to remove dupes? In CZ, Widget:AddThis appears two times:
# main namespace and widget namespace.
# We can use sort -u in UNIX, but is it worth it?
titlesfile.write(u'--END--\n')
titlesfile.close()
print 'Titles saved at...', titlesfilename
print '%d page titles loaded' % (c)
return titlesfilename
def getImageNames(config={}, session=None):
""" Get list of image names """
print 'Retrieving image filenames'
images = []
if 'api' in config and config['api']:
images = getImageNamesAPI(config=config, session=session)
elif 'index' in config and config['index']:
images = getImageNamesScraper(config=config, session=session)
# images = list(set(images)) # it is a list of lists
images.sort()
print '%d image names loaded' % (len(images))
return images
def getXMLHeader(config={}, session=None):
""" Retrieve a random page to extract XML headers (namespace info, etc) """
# get the header of a random page, to attach it in the complete XML backup
# similar to: <mediawiki xmlns="http://www.mediawiki.org/xml/export-0.3/"
# xmlns:x....
randomtitle = 'Main_Page' # previously AMF5LKE43MNFGHKSDMRTJ
try:
xml = "".join([x for x in getXMLPage(config=config, title=randomtitle, verbose=False, session=session)])
except PageMissingError as pme:
# The <page> does not exist. Not a problem, if we get the <siteinfo>.
xml = pme.xml
# Issue 26: Account for missing "Special" namespace.
# Hope the canonical special name has not been removed.
# http://albens73.fr/wiki/api.php?action=query&meta=siteinfo&siprop=namespacealiases
except ExportAbortedError:
try:
if config['api']:
print "Trying the local name for the Special namespace instead"
r = session.post(
url=config['api'],
data={
'action': 'query',
'meta': 'siteinfo',
'siprop': 'namespaces',
'format': 'json'}
)
config['export'] = json.loads(r.text)['query']['namespaces']['-1']['*'] \
+ ':Export'
xml = "".join([x for x in getXMLPage(config=config, title=randomtitle, verbose=False, session=session)])
except PageMissingError as pme:
xml = pme.xml
except ExportAbortedError:
pass
header = xml.split('</mediawiki>')[0]
if not re.match(r"\s*<mediawiki", xml):
print 'XML export on this wiki is broken, quitting.'
logerror(u'XML export on this wiki is broken, quitting.')
sys.exit()
return header, config
def getXMLFileDesc(config={}, title='', session=None):
""" Get XML for image description page """
config['curonly'] = 1 # tricky to get only the most recent desc
return("".join([x for x in getXMLPage( config=config, title=title, verbose=False, session=session)]))
def getUserAgent():
""" Return a cool user-agent to hide Python user-agent """
useragents = [
# firefox
'Mozilla/5.0 (X11; Linux i686; rv:24.0) Gecko/20100101 Firefox/24.0',
'Mozilla/5.0 (X11; Linux x86_64; rv:28.0) Gecko/20100101 Firefox/28.0',
]
return useragents[0]
def logerror(config={}, text=''):
""" Log error in file """
if text:
with open('%s/errors.log' % (config['path']), 'a') as outfile:
output = u'%s: %s\n' % (
datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), text)
outfile.write(output.encode('utf-8'))
def getXMLPageCore(headers={}, params={}, config={}, session=None):
""" """
# returns a XML containing params['limit'] revisions (or current only), ending in </mediawiki>
# if retrieving params['limit'] revisions fails, returns a current only version
# if all fail, returns the empty string
xml = ''
c = 0
maxseconds = 100 # max seconds to wait in a single sleeping
maxretries = config['retries'] # x retries and skip
increment = 20 # increment every retry
while not re.search(r'</mediawiki>', xml):
if c > 0 and c < maxretries:
wait = increment * c < maxseconds and increment * \
c or maxseconds # incremental until maxseconds
print ' In attempt %d, XML for "%s" is wrong. Waiting %d seconds and reloading...'%(c, params['pages'], wait)
time.sleep(wait)
# reducing server load requesting smallest chunks (if curonly then
# limit = 1 from mother function)
if params['limit'] > 1:
params['limit'] = params['limit'] / 2 # half
if c >= maxretries:
print ' We have retried %d times' % (c)
print ' MediaWiki error for "%s", network error or whatever...' % (params['pages'])
# If it's not already what we tried: our last chance, preserve only the last revision...
# config['curonly'] means that the whole dump is configured to save only the last,
# params['curonly'] should mean that we've already tried this
# fallback, because it's set by the following if and passed to
# getXMLPageCore
if not config['curonly'] and not 'curonly' in params:
print ' Trying to save only the last revision for this page...'
params['curonly'] = 1
logerror(
config=config,
text=u'Error while retrieving the full history of "%s". Trying to save only the last revision for this page' %
(params['pages'])
)
return getXMLPageCore(
headers=headers,
params=params,
config=config,
session=session
)
else:
print ' Saving in the errors log, and skipping...'
logerror(
config=config,
text=u'Error while retrieving the last revision of "%s". Skipping.' %
(params['pages']))
raise ExportAbortedError(config['index'])
return '' # empty xml
# FIXME HANDLE HTTP Errors HERE
try:
r = session.post(url=config['index'], data=params, headers=headers)
handleStatusCode(r)
xml = fixBOM(r)
except requests.exceptions.ConnectionError as e:
print ' Connection error: %s'%(str(e[0]))
xml = ''
c += 1
return xml
def getXMLPage(config={}, title='', verbose=True, session=None):
""" Get the full history (or current only) of a page """
# if server errors occurs while retrieving the full page history, it may return [oldest OK versions] + last version, excluding middle revisions, so it would be partialy truncated
# http://www.mediawiki.org/wiki/Manual_talk:Parameters_to_Special:Export#Parameters_no_longer_in_use.3F
limit = 1000
truncated = False
title_ = title
title_ = re.sub(' ', '_', title_)
# do not convert & into %26, title_ = re.sub('&', '%26', title_)
try:
params = {'title': config['export'], 'pages': title_, 'action': 'submit'}
except KeyError:
params = {'title': 'Special:Export', 'pages': title_, 'action': 'submit'}
if config['curonly']:
params['curonly'] = 1
params['limit'] = 1
else:
params['offset'] = '1' # 1 always < 2000s
params['limit'] = limit
# in other case, do not set params['templates']
if 'templates' in config and config['templates']:
params['templates'] = 1
xml = getXMLPageCore(params=params, config=config, session=session)
if xml == "":
raise ExportAbortedError(config['index'])
if not "</page>" in xml:
raise PageMissingError(params['title'], xml)
else:
# strip these sha1s sums which keep showing up in the export and
# which are invalid for the XML schema (they only apply to
# revisions)
xml = re.sub(r'\n\s*<sha1>\w+</sha1>\s*\n', r'\n', xml)
xml = re.sub(r'\n\s*<sha1/>\s*\n', r'\n', xml)
yield xml.split("</page>")[0]
# if complete history, check if this page history has > limit edits, if so, retrieve all using offset if available
# else, warning about Special:Export truncating large page histories
r_timestamp = r'<timestamp>([^<]+)</timestamp>'
numberofedits = 0
numberofedits += len(re.findall(r_timestamp, xml))
# search for timestamps in xml to avoid analysing empty pages like
# Special:Allpages and the random one
if not config['curonly'] and re.search(r_timestamp, xml):
while not truncated and params['offset']: # next chunk
# get the last timestamp from the acum XML
params['offset'] = re.findall(r_timestamp, xml)[-1]
try:
xml2 = getXMLPageCore(
params=params, config=config, session=session)
except MemoryError:
print "The page's history exceeds our memory, halving limit."
params['limit'] = params['limit'] / 2
continue
# are there more edits in this next XML chunk or no <page></page>?
if re.findall(r_timestamp, xml2):
if re.findall(r_timestamp, xml2)[-1] == params['offset']:
# again the same XML, this wiki does not support params in
# Special:Export, offer complete XML up to X edits (usually
# 1000)
print 'ATTENTION: This wiki does not allow some parameters in Special:Export, therefore pages with large histories may be truncated'
truncated = True
break
else:
""" </namespaces>
</siteinfo>
<page>
<title>Main Page</title>
<id>15580374</id>
<restrictions>edit=sysop:move=sysop</restrictions> (?)
<revision>
<id>418009832</id>
<timestamp>2011-03-09T19:57:06Z</timestamp>
<contributor>
"""
# offset is OK in this wiki, merge with the previous chunk
# of this page history and continue
try:
xml2 = xml2.split("</page>")[0]
yield ' <revision>' + ('<revision>'.join(xml2.split('<revision>')[1:]))
except MemoryError:
print "The page's history exceeds our memory, halving limit."
params['limit'] = params['limit'] / 2
continue
xml = xml2
numberofedits += len(re.findall(r_timestamp, xml))
else:
params['offset'] = '' # no more edits in this page history
yield "</page>\n"
if verbose:
if (numberofedits == 1):
print ' %s, 1 edit' % (title.strip())
else:
print ' %s, %d edits' % (title.strip(), numberofedits)
def cleanXML(xml=''):
""" Trim redundant info """
# do not touch XML codification, leave AS IS
if re.search(r'</siteinfo>\n', xml):
xml = xml.split('</siteinfo>\n')[1]
if re.search(r'</mediawiki>', xml):
xml = xml.split('</mediawiki>')[0]
return xml
def generateXMLDump(config={}, titles=[], start=None, session=None):
""" Generates a XML dump for a list of titles """
# TODO: titles is now unused.
print 'Retrieving the XML for every page from "%s"' % (start and start or 'start')
header, config = getXMLHeader(config=config, session=session)
footer = '</mediawiki>\n' # new line at the end
xmlfilename = '%s-%s-%s.xml' % (domain2prefix(config=config),
config['date'],
config['curonly'] and 'current' or 'history')
xmlfile = ''
lock = True
if start:
print "Removing the last chunk of past XML dump: it is probably incomplete."
for i in reverse_readline('%s/%s' % (config['path'], xmlfilename), truncate=True):
pass
else:
# requested complete xml dump
lock = False
xmlfile = open('%s/%s' % (config['path'], xmlfilename), 'w')
xmlfile.write(header.encode('utf-8'))
xmlfile.close()
xmlfile = open('%s/%s' % (config['path'], xmlfilename), 'a')
c = 1
for title in readTitles(config, start):
if not title.strip():
continue
if title == start: # start downloading from start, included
lock = False
if lock:
continue
delay(config=config, session=session)
if c % 10 == 0:
print 'Downloaded %d pages' % (c)
try:
for xml in getXMLPage(config=config, title=title, session=session):
xml = cleanXML(xml=xml)
xmlfile.write(xml.encode('utf-8'))
except PageMissingError:
logerror(
config=config,
text=u'The page "%s" was missing in the wiki (probably deleted)' %
(title.decode('utf-8'))
)
# here, XML is a correct <page> </page> chunk or
# an empty string due to a deleted page (logged in errors log) or
# an empty string due to an error while retrieving the page from server
# (logged in errors log)
c += 1
xmlfile.write(footer)
xmlfile.close()
print 'XML dump saved at...', xmlfilename
def readTitles(config={}, start=None):
""" Read title list from a file, from the title "start" """
titlesfilename = '%s-%s-titles.txt' % (
domain2prefix(config=config), config['date'])
titlesfile = open('%s/%s' % (config['path'], titlesfilename), 'r')
seeking = False
if start:
seeking = True
with titlesfile as f:
for line in f:
if line.strip() == '--END--':
break
elif seeking and line.strip() != start:
continue
elif seeking and line.strip() == start:
seeking = False
yield line.strip()
else:
yield line.strip()
def reverse_readline(filename, buf_size=8192, truncate=False):
"""a generator that returns the lines of a file in reverse order"""
# Original code by srohde, abdus_salam: cc by-sa 3.0
# http://stackoverflow.com/a/23646049/718903
with open(filename, 'r+') as fh:
segment = None
offset = 0
fh.seek(0, os.SEEK_END)
total_size = remaining_size = fh.tell()
while remaining_size > 0:
offset = min(total_size, offset + buf_size)
fh.seek(-offset, os.SEEK_END)
buffer = fh.read(min(remaining_size, buf_size))
remaining_size -= buf_size
lines = buffer.split('\n')
# the first line of the buffer is probably not a complete line so
# we'll save it and append it to the last line of the next buffer
# we read
if segment is not None:
# if the previous chunk starts right from the beginning of line
# do not concat the segment to the last line of new chunk
# instead, yield the segment first
if buffer[-1] is not '\n':
lines[-1] += segment
else:
if truncate and '</page>' in segment:
pages = buffer.split('</page>')
fh.seek(-offset+buf_size-len(pages[-1]), os.SEEK_END)
fh.truncate
raise StopIteration
else:
yield segment
segment = lines[0]
for index in range(len(lines) - 1, 0, -1):
if truncate and '</page>' in segment:
pages = buffer.split('</page>')
fh.seek(-offset-len(pages[-1]), os.SEEK_END)
fh.truncate
raise StopIteration
else:
yield lines[index]
yield segment
def saveImageNames(config={}, images=[], session=None):
""" Save image list in a file, including filename, url and uploader """
imagesfilename = '%s-%s-images.txt' % (
domain2prefix(config=config), config['date'])
imagesfile = open('%s/%s' % (config['path'], imagesfilename), 'w')
imagesfile.write(
('\n'.join(
[
'%s\t%s\t%s' %
(filename,
url,
uploader) for filename,
url,
uploader in images]
).encode('utf-8')
)
)
imagesfile.write('\n--END--')
imagesfile.close()
print 'Image filenames and URLs saved at...', imagesfilename
def curateImageURL(config={}, url=''):
""" Returns an absolute URL for an image, adding the domain if missing """
if 'index' in config and config['index']:
# remove from :// (http or https) until the first / after domain
domainalone = config['index'].split(
'://')[0] + '://' + config['index'].split('://')[1].split('/')[0]
elif 'api' in config and config['api']:
domainalone = config['api'].split(
'://')[0] + '://' + config['api'].split('://')[1].split('/')[0]
else:
print 'ERROR: no index nor API'
sys.exit()
if url.startswith('//'): # Orain wikifarm returns URLs starting with //
url = u'%s:%s' % (domainalone.split('://')[0], url)
# is it a relative URL?
elif url[0] == '/' or (not url.startswith('http://') and not url.startswith('https://')):
if url[0] == '/': # slash is added later
url = url[1:]
# concat http(s) + domain + relative url
url = u'%s/%s' % (domainalone, url)
url = undoHTMLEntities(text=url)
# url = urllib.unquote(url) #do not use unquote with url, it break some
# urls with odd chars
url = re.sub(' ', '_', url)
return url
def getImageNamesScraper(config={}, session=None):
""" Retrieve file list: filename, url, uploader """
# (?<! http://docs.python.org/library/re.html
r_next = r'(?<!&dir=prev)&offset=(?P<offset>\d+)&'
images = []
offset = '29990101000000' # january 1, 2999
limit = 5000
retries = config['retries']
while offset:
# 5000 overload some servers, but it is needed for sites like this with
# no next links
# http://www.memoryarchive.org/en/index.php?title=Special:Imagelist&sort=byname&limit=50&wpIlMatch=
r = session.post(
url=config['index'],
data={
'title': 'Special:Imagelist',
'limit': limit,
'offset': offset})
raw = r.text
delay(config=config, session=session)
# delicate wiki
if re.search(
ur'(?i)(allowed memory size of \d+ bytes exhausted|Call to a member function getURL)',
raw):
if limit > 10:
print 'Error: listing %d images in a chunk is not possible, trying tiny chunks' % (limit)
limit = limit / 10
continue
elif retries > 0: # waste retries, then exit
retries -= 1
print 'Retrying...'
continue
else:
print 'No more retries, exit...'
break
raw = cleanHTML(raw)
# archiveteam 1.15.1 <td class="TablePager_col_img_name"><a href="/index.php?title=File:Yahoovideo.jpg" title="File:Yahoovideo.jpg">Yahoovideo.jpg</a> (<a href="/images/2/2b/Yahoovideo.jpg">file</a>)</td>
# wikanda 1.15.5 <td class="TablePager_col_img_user_text"><a
# href="/w/index.php?title=Usuario:Fernandocg&action=edit&redlink=1"
# class="new" title="Usuario:Fernandocg (página no
# existe)">Fernandocg</a></td>
r_images1 = r'(?im)<td class="TablePager_col_img_name"><a href[^>]+title="[^:>]+:(?P<filename>[^>]+)">[^<]+</a>[^<]+<a href="(?P<url>[^>]+/[^>/]+)">[^<]+</a>[^<]+</td>\s*<td class="TablePager_col_img_user_text"><a[^>]+>(?P<uploader>[^<]+)</a></td>'
# wikijuegos 1.9.5
# http://softwarelibre.uca.es/wikijuegos/Especial:Imagelist old
# mediawiki version
r_images2 = r'(?im)<td class="TablePager_col_links"><a href[^>]+title="[^:>]+:(?P<filename>[^>]+)">[^<]+</a>[^<]+<a href="(?P<url>[^>]+/[^>/]+)">[^<]+</a></td>\s*<td class="TablePager_col_img_timestamp">[^<]+</td>\s*<td class="TablePager_col_img_name">[^<]+</td>\s*<td class="TablePager_col_img_user_text"><a[^>]+>(?P<uploader>[^<]+)</a></td>'
# gentoowiki 1.18
r_images3 = r'(?im)<td class="TablePager_col_img_name"><a[^>]+title="[^:>]+:(?P<filename>[^>]+)">[^<]+</a>[^<]+<a href="(?P<url>[^>]+)">[^<]+</a>[^<]+</td><td class="TablePager_col_thumb"><a[^>]+><img[^>]+></a></td><td class="TablePager_col_img_size">[^<]+</td><td class="TablePager_col_img_user_text"><a[^>]+>(?P<uploader>[^<]+)</a></td>'
# http://www.memoryarchive.org/en/index.php?title=Special:Imagelist&sort=byname&limit=50&wpIlMatch=
# (<a href="/en/Image:109_0923.JPG" title="Image:109 0923.JPG">desc</a>) <a href="/en/upload/c/cd/109_0923.JPG">109 0923.JPG</a> . . 885,713 bytes . . <a href="/en/User:Bfalconer" title="User:Bfalconer">Bfalconer</a> . . 18:44, 17 November 2005<br />
r_images4 = r'(?im)<a href=[^>]+ title="[^:>]+:(?P<filename>[^>]+)">[^<]+</a>[^<]+<a href="(?P<url>[^>]+)">[^<]+</a>[^<]+<a[^>]+>(?P<uploader>[^<]+)</a>'
r_images5 = (
r'(?im)<td class="TablePager_col_img_name">\s*<a href[^>]*?>(?P<filename>[^>]+)</a>\s*\(<a href="(?P<url>[^>]+)">[^<]*?</a>\s*\)\s*</td>\s*'
'<td class="TablePager_col_thumb">[^\n\r]*?</td>\s*'
'<td class="TablePager_col_img_size">[^<]*?</td>\s*'
'<td class="TablePager_col_img_user_text">\s*(<a href="[^>]*?" title="[^>]*?">)?(?P<uploader>[^<]+?)(</a>)?\s*</td>')
# Select the regexp that returns more results
regexps = [r_images1, r_images2, r_images3, r_images4, r_images5]
count = 0
i = 0
regexp_best = 0
for regexp in regexps:
if len(re.findall(regexp, raw)) > count:
count = len(re.findall(regexp, raw))
regexp_best = i
i += 1
m = re.compile(regexps[regexp_best]).finditer(raw)
# Iter the image results
for i in m:
url = i.group('url')
url = curateImageURL(config=config, url=url)
filename = re.sub('_', ' ', i.group('filename'))
filename = undoHTMLEntities(text=filename)
filename = urllib.unquote(filename)
uploader = re.sub('_', ' ', i.group('uploader'))
uploader = undoHTMLEntities(text=uploader)
uploader = urllib.unquote(uploader)
images.append([filename, url, uploader])
# print filename, url
if re.search(r_next, raw):
new_offset = re.findall(r_next, raw)[0]
# Avoid infinite loop
if new_offset != offset:
offset = new_offset
retries += 5 # add more retries if we got a page with offset
else:
offset = ''
else:
offset = ''
if (len(images) == 1):
print ' Found 1 image'
else:
print ' Found %d images' % (len(images))
images.sort()
return images
def getImageNamesAPI(config={}, session=None):
""" Retrieve file list: filename, url, uploader """
oldAPI = False
aifrom = '!'
images = []
while aifrom:
sys.stderr.write('.') # progress
params = {
'action': 'query',
'list': 'allimages',
'aiprop': 'url|user',
'aifrom': aifrom,
'format': 'json',
'ailimit': 500}
# FIXME Handle HTTP Errors HERE
r = session.post(url=config['api'], data=params)
handleStatusCode(r)
jsonimages = getJSON(r)
delay(config=config, session=session)
if 'query' in jsonimages:
aifrom = ''
if 'query-continue' in jsonimages and 'allimages' in jsonimages[
'query-continue']:
if 'aicontinue' in jsonimages['query-continue']['allimages']:
aifrom = jsonimages[
'query-continue']['allimages']['aicontinue']
elif 'aifrom' in jsonimages['query-continue']['allimages']:
aifrom = jsonimages[
'query-continue']['allimages']['aifrom']
elif 'continue' in jsonimages:
if 'aicontinue' in jsonimages['continue']:
aifrom = jsonimages['continue']['aicontinue']
elif 'aifrom' in jsonimages['continue']:
aifrom = jsonimages['continue']['aifrom']
# print aifrom
for image in jsonimages['query']['allimages']:
url = image['url']
url = curateImageURL(config=config, url=url)
# encoding to ascii is needed to work around this horrible bug:
# http://bugs.python.org/issue8136
if 'api' in config and '.wikia.com' in config['api']:
#to avoid latest?cb=20120816112532 in filenames
filename = unicode(urllib.unquote((re.sub('_', ' ', url.split('/')[-3])).encode('ascii', 'ignore')), 'utf-8')
else: