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
|
# Copyright (c) 2007-2008 PediaPress GmbH
# See README.txt for additional licensing information.
"""main programs - installed via setuptools' entry_points"""
import optparse
def buildcdb():
parser = optparse.OptionParser(usage="%prog --input XMLDUMP --output OUTPUT")
parser.add_option("-i", "--input", help="input file")
parser.add_option("-o", "--output", help="write output to OUTPUT")
options, args = parser.parse_args()
if args:
parser.error("too many arguments.")
input = options.input
output = options.output
if not (input and output):
parser.error("missing argument.")
import os
from mwlib import cdbwiki
cdbwiki.BuildWiki(input, output)()
open(os.path.join(output, "wikiconf.txt"), "w").write("""
[wiki]
type = cdb
path = %s
[images]
type = download
url = http://upload.wikimedia.org/wikipedia/commons/
localpath = ~/images
""" % (os.path.abspath(output),))
def show():
parser = optparse.OptionParser(usage="%prog [-e|--expand] --conf CONF ARTICLE [...]")
parser.add_option("-c", "--conf", help="config file")
parser.add_option("-e", "--expand", action="store_true", help="expand templates")
parser.add_option("-t", "--template", action="store_true", help="show template")
options, args = parser.parse_args()
if not args:
parser.error("missing ARTICLE argument")
articles = [unicode(x, 'utf-8') for x in args]
conf = options.conf
if not conf:
parser.error("missing --conf argument")
from mwlib import wiki, expander
db = wiki.makewiki(conf)['wiki']
for a in articles:
if options.template:
raw=db.getTemplate(a)
else:
raw=db.getRawArticle(a)
if raw:
if options.expand:
te = expander.Expander(raw, pagename=a, wikidb=db)
raw = te.expandTemplates()
print raw.encode("utf-8")
def buildzip():
parser = optparse.OptionParser(usage="%prog [OPTIONS] [ARTICLE ...]")
parser.add_option("-c", "--conf", help="config file (required unless --baseurl is given)")
parser.add_option("-b", "--baseurl", help="base URL for mwapidb backend")
parser.add_option("-s", "--shared-baseurl", help="base URL for shared images for mwapidb backend")
parser.add_option("-m", "--metabook", help="JSON encoded text file with book structure")
parser.add_option('--collectionpage', help='Title of a collection page')
parser.add_option("-x", "--noimages", action="store_true", help="exclude images")
parser.add_option("-o", "--output", help="write output to OUTPUT")
parser.add_option("-p", "--posturl", help="http post to POSTURL")
parser.add_option("-i", "--imagesize",
help="max. pixel size (width or height) for images (default: 800)")
parser.add_option("-d", "--daemonize", action="store_true",
help='become daemon after collection articles (before POST request)')
parser.add_option("-l", "--logfile", help="log to logfile")
parser.add_option("--license", help="Title of article containing full license text")
parser.add_option("--template-blacklist", help="Title of article containing blacklisted templates")
options, args = parser.parse_args()
import tempfile
import os
import zipfile
from mwlib import utils
from mwlib.utils import daemonize
articles = [unicode(x, 'utf-8') for x in args]
baseurl = options.baseurl
conf = options.conf
if not baseurl and not options.conf:
parser.error("neither --conf nor --baseurl specified\nuse --help for all options")
posturl = None
def post_status(status):
print 'status:', status
if not posturl:
return
try:
return urllib2.urlopen(posturl, urllib.urlencode({'status': status})).read()
except Exception, e:
print 'ERROR posting status %r to %r' % (status, posturl)
def post_progress(progress):
print 'progress', progress
if not posturl:
return
try:
return urllib2.urlopen(posturl, urllib.urlencode({'progress': int(progress)})).read()
except Exception, e:
print 'ERROR posting progress %r to %r' % (progress, posturl)
try:
if options.logfile:
utils.start_logging(options.logfile)
output = options.output
from mwlib import wiki, recorddb, metabook
mb = metabook.MetaBook()
if conf:
from ConfigParser import ConfigParser
w = wiki.makewiki(conf)
cp = ConfigParser()
cp.read(conf)
license = {
'name': cp.get('wiki', 'defaultarticlelicense')
}
if license['name'] is not None:
license['wikitext'] = w['wiki'].getRawArticle(license['name'])
mb.source = {
'name': cp.get('wiki', 'name'),
'url': cp.get('wiki', 'url'),
'defaultarticlelicense': license,
}
else:
w = {
'wiki': wiki.wiki_mwapi(baseurl, options.license, options.template_blacklist),
'images': wiki.image_mwapi(baseurl, shared_base_url=options.shared_baseurl)
}
metadata = w['wiki'].getMetaData()
mb.source = {
'name': metadata['name'],
'url': metadata['url'],
'defaultarticlelicense': metadata['license'],
}
if options.noimages:
w['images'] = None
else:
if options.imagesize:
imagesize = int(options.imagesize)
else:
imagesize = 800
if output:
zipfilename = output
else:
fd, zipfilename = tempfile.mkstemp()
os.close(fd)
if options.collectionpage:
mwcollection = w['wiki'].getRawArticle(options.collectionpage)
mb.loadCollectionPage(mwcollection)
elif options.metabook:
mb.readJsonFile(options.metabook)
# do not daemonize earlier: Collection extension deletes input metabook file!
if options.daemonize:
daemonize()
posturl = options.posturl
if posturl:
posturl = posturl.encode('utf-8')
from mwlib.utils import get_multipart
import urllib
import urllib2
zf = zipfile.ZipFile(zipfilename, 'w')
z = recorddb.ZipfileCreator(zf, w['wiki'], w['images'])
post_status('parsing')
for x in articles:
z.addArticle(x)
mb.addArticles(articles)
z.addObject('metabook.json', mb.dumpJson())
articles = list(mb.getArticles())
if articles:
inc = 70/len(articles)
else:
inc = 0
p = 0
for title, revision in articles:
post_progress(p)
z.addArticle(title, revision=revision)
p += inc
post_status('packaging')
if not options.noimages:
z.writeImages(size=imagesize)
post_progress(80)
z.writeContent()
zf.close()
post_progress(90)
if posturl:
post_status('uploading')
zf = open(zipfilename, "rb")
ct, data = get_multipart('collection.zip', zf.read(), 'collection')
zf.close()
req = urllib2.Request(posturl, data=data, headers={"Content-Type": ct})
result = urllib2.urlopen(req).read()
if w['images']:
w['images'].clear()
if not output:
os.unlink(zipfilename)
post_status('finished')
post_progress(100)
except Exception, e:
post_status('error')
raise
def parse():
parser = optparse.OptionParser(usage="%prog [-a|--all] --conf CONF [ARTICLE1 ...]")
parser.add_option("-a", "--all", action="store_true", help="parse all articles")
parser.add_option("--tb", action="store_true", help="show traceback on error")
parser.add_option("-c", "--conf", help="config file")
options, args = parser.parse_args()
if not args and not options.all:
parser.error("missing option.")
if not options.conf:
parser.error("missing --conf argument")
articles = [unicode(x, 'utf-8') for x in args]
conf = options.conf
import traceback
from mwlib import wiki, uparser
w = wiki.makewiki(conf)
db = w['wiki']
if options.all:
if not hasattr(db, "articles"):
raise RuntimeError("%s does not support iterating over all articles" % (db, ))
articles = db.articles()
import time
for x in articles:
try:
raw = db.getRawArticle(x)
# yes, raw can be None, when we have a redirect to a non-existing article.
if raw is None:
continue
stime=time.time()
a=uparser.parseString(x, raw=raw, wikidb=db)
except Exception, err:
print "F", repr(x), err
if options.tb:
traceback.print_exc()
else:
print "G", time.time()-stime, repr(x)
def serve():
parser = optparse.OptionParser(usage="%prog --conf CONF ARTICLE [...]")
parser.add_option("-c", "--conf", help="config file")
options, args = parser.parse_args()
conf = options.conf
if not options.conf:
parser.error("missing --conf argument")
from mwlib import wiki, web
res = wiki.makewiki(conf)
db = res['wiki']
images = res['images']
from wsgiref.simple_server import make_server, WSGIServer
from SocketServer import ForkingMixIn
class MyServer(ForkingMixIn, WSGIServer):
pass
iface, port = '0.0.0.0', 8080
print "serving on %s:%s" % (iface, port)
http = make_server(iface, port, web.Serve(db, res['images']), server_class=MyServer)
http.serve_forever()
def html():
parser = optparse.OptionParser(usage="%prog --conf CONF ARTICLE [...]")
parser.add_option("-c", "--conf", help="config file")
options, args = parser.parse_args()
if not args:
parser.error("missing ARTICLE argument")
articles = [unicode(x, 'utf-8') for x in args]
conf = options.conf
if not options.conf:
parser.error("missing --conf argument")
import StringIO
import tempfile
import os
import webbrowser
from mwlib import wiki, uparser, htmlwriter
res = wiki.makewiki(conf)
db = res['wiki']
images = res['images']
for a in articles:
raw=db.getRawArticle(a)
if not raw:
continue
out=StringIO.StringIO()
out.write("""<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<meta http-equiv="content-type" content="text/html; charset="utf-8"></meta>
<link rel="stylesheet" href="pedia.css" />
</head>
<body>
""")
a=uparser.parseString(x, raw=raw, wikidb=db)
w=htmlwriter.HTMLWriter(out, images)
w.write(a)
fd, htmlfile = tempfile.mkstemp(".html")
os.close(fd)
open(htmlfile, "wb").write(out.getvalue().encode('utf-8'))
webbrowser.open("file://"+htmlfile)
|