-
Notifications
You must be signed in to change notification settings - Fork 8
/
enwp_find_commonscat.py
224 lines (197 loc) · 6.75 KB
/
enwp_find_commonscat.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
#!/usr/bin/python
# -*- coding: utf-8 -*-
# Check for consistency in commons category usage
# Mike Peel 01-Mar-2018 v1 - start
from __future__ import unicode_literals
import pywikibot
import numpy as np
import time
import string
from pywikibot import pagegenerators
import urllib
from database_login import *
import time
from pibot_functions import *
maxnum = 10000000
nummodified = 0
wikidata_site = pywikibot.Site("wikidata", "wikidata")
repo = wikidata_site.data_repository() # this is a DataSite object
commons = pywikibot.Site('commons', 'commons')
enwp = pywikibot.Site('en', 'wikipedia')
# enwp = pywikibot.Site('es', 'wikipedia')
debug = 1
trip = 1
# New style of category walker
numchecked = 0
catschecked = 0
do_articles = True
do_subcats = True
targetcats = []
# targetcats = ['Category:Aircraft by manufacturer']
# targetcats = ['Category:Astronomy']
# targetcats = ['Category:Science']
#targetcats = ['Category:Canary Islands']
#targetcats = ['Categoría:Canarias']
# targetcats = ['Category:2019–20 coronavirus pandemic']
# targetcats = ['Category:Commons category link is on Wikidata using P373']
targetcats = ['Category:Commons category link is locally defined']
# targetcats = ['Category:Commons link is the pagename','Category:Commons link is defined as the pagename']
# targetcats = ['Category:Commons link is locally defined']
targettemplates = []
# targettemplates = ['Commons']
subcats = False
catredirect_templates = ["category redirect", "Category redirect", "seecat", "Seecat", "see cat", "See cat", "categoryredirect", "Categoryredirect", "catredirect", "Catredirect", "cat redirect", "Cat redirect", "catredir", "Catredir", "redirect category", "Redirect category", "cat-red", "Cat-red", "redirect cat", "Redirect cat", "category Redirect", "Category Redirect", "cat-redirect", "Cat-redirect"]
def findmatch(page):
# Get the Wikidata entry
try:
wd_item = pywikibot.ItemPage.fromPage(page)
item_dict = wd_item.get()
qid = wd_item.title()
print('\n'+page.title())
print('http://www.wikidata.org/wiki/'+qid)
except:
# If that didn't work, go no further
print('\n'+page.title() + ' - no page found')
return 0
have_followed_p910 = False
try:
existing_id = item_dict['claims']['P910']
print('P910 exists, following that.')
for clm2 in existing_id:
wd_item = clm2.getTarget()
item_dict = wd_item.get()
print(wd_item.title())
have_followed_p910 = True
except:
null = 0
# Double-check that there is no a sitelink on Wikidata
try:
sitelink = get_sitelink_title(item_dict['sitelinks']['commonswiki'])
sitelink_check = 1
except:
sitelink_check = 0
print("sitelink: " + str(sitelink_check))
if sitelink_check == 1:
return 0
# See if we can get a Commons page with the same name
try:
if 'Category:' in page.title():
commonscat_page = pywikibot.Page(commons, page.title())
else:
commonscat_page = pywikibot.Page(commons, 'Category:'+page.title())
category_text = commonscat_page.get()
except:
try:
if 'Category:' in page.title():
commonscat_page = pywikibot.Page(commons, page.title()[:-1])
else:
commonscat_page = pywikibot.Page(commons, 'Category:'+page.title()[:-1])
category_text = commonscat_page.get()
except:
print('No match found')
return 0
if any(option in category_text for option in catredirect_templates):
print('Redirect page')
return 0
# See if it already has a Wikidata item
test = 0
try:
wd_item2 = pywikibot.ItemPage.fromPage(commonscat_page)
item_dict2 = wd_item2.get()
qid2 = wd_item2.title()
print('http://www.wikidata.org/wiki/'+qid)
test = 1
except:
# If that didn't work, go no further
print(commonscat_page.title() + ' - no linked Wikidata item found')
if test != 0:
print('http://commons.wikimedia.org/wiki/'+commonscat_page.title())
print('Commons has Wikidata ID already')
input('Check?')
return 0
print(' http://en.wikipedia.org/wiki/'+page.title().replace(' ','_'))
print(' http://commons.wikimedia.org/wiki/'+commonscat_page.title().replace(' ','_'))
print(category_text)
test = 'y'
# test = input("Continue? ")
if test != 'n':
# Add the sitelink
data = {'sitelinks': [{'site': 'commonswiki', 'title': commonscat_page.title()}]}
try:
print(data)
if debug == 1:
text = input("Save sitelink? ")
else:
text = 'y'
if text == 'y':
wd_item.editEntity(data, summary=u'Add Commons category sitelink from name matching')
except:
print('Edit failed')
if debug == 1:
# Remove any bad P373 values
try:
p373 = item_dict['claims']['P373']
for clm in p373:
val = clm.getTarget()
p373cat = u"Category:" + val
print('Remove P373?')
print(' http://www.wikidata.org/wiki/'+qid)
print(' ' + str(p373cat))
test = 'y'
savemessage = 'Remove incorrect P373 value'
if debug == 1:
print(savemessage)
test = input("Continue? ")
if test == 'y':
wd_item.removeClaims(clm,summary=savemessage)
except:
null = 0
return 1
if len(targetcats) > 0:
seen = set(targetcats)
active = set(targetcats)
while active:
next_active = set()
for item in sorted(active):
cat = pywikibot.Category(enwp,item)
if do_articles:
for result in pagegenerators.CategorizedPageGenerator(cat, recurse=False):
nummodified += findmatch(result)
nummodified += findmatch(cat)
numchecked += 1
print(str(nummodified) + " - " + str(numchecked) + "/" + str(len(seen)) + "/" + str(len(active)) + "/" + str(len(next_active)))
if do_subcats:
do_subcats = subcats
# See if there are subcategories that we want to check in the future
for result in pagegenerators.SubCategoriesPageGenerator(cat, recurse=False):
if result.title() not in seen:
seen.add(result.title())
next_active.add(result.title())
active = next_active
if nummodified >= maxnum:
print('Reached the maximum of ' + str(maxnum) + ' entries modified, quitting!')
break
elif len(targettemplates) > 0:
for tpl in targettemplates:
template = pywikibot.Page(enwp, 'Template:'+tpl)
# targetcats = template.embeddedin(namespaces='14')
targetcats = template.embeddedin(namespaces='0')
for target in targetcats:
nummodified += findmatch(target)
if nummodified >= maxnum:
print('Reached the maximum of ' + str(maxnum) + ' entries modified, quitting!')
break
else:
# Pick random categories
while nummodified < maxnum:
# targets = pagegenerators.RandomPageGenerator(total=100, site=enwp, namespaces='14')
targets = pagegenerators.RandomPageGenerator(total=100, site=enwp, namespaces='0')
for target in targets:
print(target.title())
nummodified += findmatch(target)
# print(nummodified)
if nummodified >= maxnum:
print('Reached the maximum of ' + str(maxnum) + ' entries modified, quitting!')
break
print('Done! Edited ' + str(nummodified) + ' entries')
# EOF