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
|
import json
from requests import get
from urllib import urlencode
from datetime import datetime
resultCount=2
urlSearch = 'https://www.wikidata.org/w/api.php?action=query&list=search&format=json&srnamespace=0&srprop=sectiontitle&{query}'
urlDetail = 'https://www.wikidata.org/w/api.php?action=wbgetentities&format=json&props=labels%7Cinfo%7Csitelinks%7Csitelinks%2Furls%7Cdescriptions%7Cclaims&{query}'
urlMap = 'https://www.openstreetmap.org/?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M'
def request(query, params):
params['url'] = urlSearch.format(query=urlencode({'srsearch': query, 'srlimit': resultCount}))
print params['url']
return params
def response(resp):
results = []
search_res = json.loads(resp.text)
wikidata_ids = set()
for r in search_res.get('query', {}).get('search', {}):
wikidata_ids.add(r.get('title', ''))
language = resp.search_params['language'].split('_')[0]
if language == 'all':
language = 'en'
url = urlDetail.format(query=urlencode({'ids': '|'.join(wikidata_ids), 'languages': language + '|en'}))
before = datetime.now()
htmlresponse = get(url)
print datetime.now() - before
jsonresponse = json.loads(htmlresponse.content)
for wikidata_id in wikidata_ids:
results = results + getDetail(jsonresponse, wikidata_id, language)
return results
def getDetail(jsonresponse, wikidata_id, language):
result = jsonresponse.get('entities', {}).get(wikidata_id, {})
title = result.get('labels', {}).get(language, {}).get('value', None)
if title == None:
title = result.get('labels', {}).get('en', {}).get('value', wikidata_id)
results = []
urls = []
attributes = []
description = result.get('descriptions', {}).get(language, {}).get('value', '')
if description == '':
description = result.get('descriptions', {}).get('en', {}).get('value', '')
claims = result.get('claims', {})
official_website = get_string(claims, 'P856', None)
if official_website != None:
urls.append({ 'title' : 'Official site', 'url': official_website })
results.append({ 'title': title, 'url' : official_website })
if language != 'en':
add_url(urls, 'Wikipedia (' + language + ')', get_wikilink(result, language + 'wiki'))
wikipedia_en_link = get_wikilink(result, 'enwiki')
add_url(urls, 'Wikipedia (en)', wikipedia_en_link)
if language != 'en':
add_url(urls, 'Wiki voyage (' + language + ')', get_wikilink(result, language + 'wikivoyage'))
add_url(urls, 'Wiki voyage (en)', get_wikilink(result, 'enwikivoyage'))
if language != 'en':
add_url(urls, 'Wikiquote (' + language + ')', get_wikilink(result, language + 'wikiquote'))
add_url(urls, 'Wikiquote (en)', get_wikilink(result, 'enwikiquote'))
add_url(urls, 'Commons wiki', get_wikilink(result, 'commonswiki'))
add_url(urls, 'Location', get_geolink(claims, 'P625', None))
add_url(urls, 'Wikidata', 'https://www.wikidata.org/wiki/' + wikidata_id + '?uselang='+ language)
musicbrainz_work_id = get_string(claims, 'P435')
if musicbrainz_work_id != None:
add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/work/' + musicbrainz_work_id)
musicbrainz_artist_id = get_string(claims, 'P434')
if musicbrainz_artist_id != None:
add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/artist/' + musicbrainz_artist_id)
musicbrainz_release_group_id = get_string(claims, 'P436')
if musicbrainz_release_group_id != None:
add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/release-group/' + musicbrainz_release_group_id)
musicbrainz_label_id = get_string(claims, 'P966')
if musicbrainz_label_id != None:
add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/label/' + musicbrainz_label_id)
# musicbrainz_area_id = get_string(claims, 'P982')
# P1407 MusicBrainz series ID
# P1004 MusicBrainz place ID
# P1330 MusicBrainz instrument ID
# P1407 MusicBrainz series ID
postal_code = get_string(claims, 'P281', None)
if postal_code != None:
attributes.append({'label' : 'Postal code(s)', 'value' : postal_code})
date_of_birth = get_time(claims, 'P569', None)
if date_of_birth != None:
attributes.append({'label' : 'Date of birth', 'value' : date_of_birth})
date_of_death = get_time(claims, 'P570', None)
if date_of_death != None:
attributes.append({'label' : 'Date of death', 'value' : date_of_death})
results.append({
'infobox' : title,
'id' : wikipedia_en_link,
'content' : description,
'attributes' : attributes,
'urls' : urls
})
return results
def add_url(urls, title, url):
if url != None:
urls.append({'title' : title, 'url' : url})
def get_mainsnak(claims, propertyName):
propValue = claims.get(propertyName, {})
if len(propValue) == 0:
return None
propValue = propValue[0].get('mainsnak', None)
return propValue
def get_string(claims, propertyName, defaultValue=None):
propValue = claims.get(propertyName, {})
if len(propValue) == 0:
return defaultValue
result = []
for e in propValue:
mainsnak = e.get('mainsnak', {})
datatype = mainsnak.get('datatype', '')
datavalue = mainsnak.get('datavalue', {})
if datavalue != None:
result.append(datavalue.get('value', ''))
if len(result) == 0:
return defaultValue
else:
return ', '.join(result)
def get_time(claims, propertyName, defaultValue=None):
propValue = claims.get(propertyName, {})
if len(propValue) == 0:
return defaultValue
result = []
for e in propValue:
mainsnak = e.get('mainsnak', {})
datatype = mainsnak.get('datatype', '')
datavalue = mainsnak.get('datavalue', {})
if datavalue != None:
value = datavalue.get('value', '')
result.append(value.get('time', ''))
if len(result) == 0:
return defaultValue
else:
return ', '.join(result)
def get_geolink(claims, propertyName, defaultValue=''):
mainsnak = get_mainsnak(claims, propertyName)
if mainsnak == None:
return defaultValue
datatype = mainsnak.get('datatype', '')
datavalue = mainsnak.get('datavalue', {})
if datatype != 'globe-coordinate':
return defaultValue
value = datavalue.get('value', {})
precision = value.get('precision', 0.0002)
# there is no zoom information, deduce from precision (error prone)
# samples :
# 13 --> 5
# 1 --> 6
# 0.016666666666667 --> 9
# 0.00027777777777778 --> 19
# wolframalpha : quadratic fit { {13, 5}, {1, 6}, {0.0166666, 9}, {0.0002777777,19}}
# 14.1186-8.8322 x+0.625447 x^2
if precision < 0.0003:
zoom = 19
else:
zoom = int(15 - precision*8.8322 + precision*precision*0.625447)
url = urlMap.replace('{latitude}', str(value.get('latitude',0))).replace('{longitude}', str(value.get('longitude',0))).replace('{zoom}', str(zoom))
return url
def get_wikilink(result, wikiid):
url = result.get('sitelinks', {}).get(wikiid, {}).get('url', None)
if url == None:
return url
elif url.startswith('http://'):
url = url.replace('http://', 'https://')
elif url.startswith('//'):
url = 'https:' + url
return url
|
