API Documentation

This part of the project documentation focuses on an information-oriented approach. Use it as a reference for the technical implementation of the acdh_wikidata_pyutils project code.

For practical examples on how to use the code of this package we'd recommend to consult the tests folder

acdh_wikidata_pyutils

WikiDataEntity

A base class for wikidata entities

Source code in src/acdh_wikidata_pyutils/__init__.py 
 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
class WikiDataEntity:
    """A base class for wikidata entities"""

    def get_apis_entity(self: Self) -> dict:
        """returns a dict representing the wikidata entity

        Args:
            self (Self): A wikiDataEntity Object

        Returns:
            dict: a dict like `{"name": "some label"}
        """
        return {"name": self.label}

    def __init__(self, wikidata_url):
        self.wikidata_url = check_url(wikidata_url)
        self.wikidata_id = get_norm_id(self.wikidata_url)
        self.client = _make_client()
        self.entity = self.client.get(self.wikidata_id, load=True)
        self.label = str(self.entity.label)
        gnd_uri_property = GND_URI_PROPERTY or self.client.get("P227")
        wien_geschichte_wiki_property = (
            WIEN_GESCHICHTE_WIKI_PROPERTY or self.client.get("P7842")
        )
        try:
            gnd_uri = self.entity[gnd_uri_property]
            self.gnd_uri = get_normalized_uri(f"{GND_URL}{gnd_uri}")
        except KeyError:
            self.gnd_uri = False
        try:
            self.wien_geschichte_wiki = (
                f"{WIEN_G_URL}{self.entity[wien_geschichte_wiki_property]}"
            )
        except KeyError:
            self.wien_geschichte_wiki = False

get_apis_entity()

returns a dict representing the wikidata entity

Parameters:
  • self (Self) –

    A wikiDataEntity Object
Returns:
  • dict( dict ) –

    a dict like `{"name": "some label"}
Source code in src/acdh_wikidata_pyutils/__init__.py 
 93
 94
 95
 96
 97
 98
 99
100
101
102
def get_apis_entity(self: Self) -> dict:
    """returns a dict representing the wikidata entity

    Args:
        self (Self): A wikiDataEntity Object

    Returns:
        dict: a dict like `{"name": "some label"}
    """
    return {"name": self.label}

WikiDataPerson

Bases: WikiDataEntity

Class to fetch and return often used data from WikiData Person entries

Source code in src/acdh_wikidata_pyutils/__init__.py 
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
class WikiDataPerson(WikiDataEntity):
    """Class to fetch and return often used data from WikiData Person entries"""

    def get_apis_entity(self):
        return {
            "name": self.name,
            "first_name": self.first_name,
            "start_date_written": self.date_of_birth,
            "end_date_written": self.date_of_death,
            "gender": self.sex_or_gender,
        }

    def __init__(self, wikidata_url):
        super().__init__(wikidata_url)
        date_of_birth_prop = self.client.get("P569")
        date_of_death_prop = self.client.get("P570")
        place_of_birth_prop = self.client.get("P19")
        place_of_death_prop = self.client.get("P20")
        sex_or_gender_prop = self.client.get("P21")
        first_name_prop = self.client.get("P735")
        name_prop = self.client.get("P734")
        try:
            self.first_name = str(self.entity[first_name_prop].label)
        except KeyError:
            self.first_name = None
        try:
            self.name = str(self.entity[name_prop].label)
        except KeyError:
            self.name = self.label
        if self.first_name and self.name.startswith(f"{self.first_name} "):
            self.name = self.name.replace(f"{self.first_name} ", "")

        try:
            self.date_of_birth = str(self.entity[date_of_birth_prop])
        except (KeyError, ValueError):
            self.date_of_birth = None
        try:
            self.date_of_death = str(self.entity[date_of_death_prop])
        except (KeyError, ValueError):
            self.date_of_death = None
        try:
            self.sex_or_gender = str(self.entity[sex_or_gender_prop].label)
        except KeyError:
            self.sex_or_gender = None
        try:
            place_of_birth_id = str(self.entity[place_of_birth_prop].id)
            self.place_of_birth = get_normalized_uri(
                f"{WIKIDATA_URL}{place_of_birth_id}"
            )
        except KeyError:
            self.place_of_birth = None
        try:
            place_of_death_id = str(self.entity[place_of_death_prop].id)
            self.place_of_death = get_normalized_uri(
                f"{WIKIDATA_URL}{place_of_death_id}"
            )
        except KeyError:
            self.place_of_death = None

WikiDataPlace

Bases: WikiDataEntity

Class to fetch and return often used data from WikiData Person entries

Source code in src/acdh_wikidata_pyutils/__init__.py 
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
class WikiDataPlace(WikiDataEntity):
    """Class to fetch and return often used data from WikiData Person entries"""

    def get_apis_entity(self):
        return {"name": self.label, "lat": self.lat, "lng": self.lng}

    def __init__(self, wikidata_url):
        super().__init__(wikidata_url)
        coordinates_prop = self.client.get("P625")
        geonames_uri_property = self.client.get("P1566")
        try:
            coordinates = self.entity[coordinates_prop]
        except KeyError:
            coordinates = False
        if coordinates:
            self.lat = coordinates.latitude
            self.lng = coordinates.longitude
        else:
            self.lat = None
            self.lng = None
        try:
            geonames_uri = self.entity[geonames_uri_property]
            self.geonames_uri = get_normalized_uri(f"{GEONAMES_URL}{geonames_uri}")
        except KeyError:
            self.geonames_uri = False

fetch_image(wikidata_id, thumb_width=250, headers=DEFAULT_REQUEST_HEADERS)

returns the URL of a wikimedia image related to the given wikidata id

Parameters:
  • wikidata_id (str) –

    a wikidata id e.g. 'Q2390830'

  • thumb_width (int, default: 250 ) –

    the requested image widh in pixels, defaults to 250

  • headers (dict, default: DEFAULT_REQUEST_HEADERS ) –

    optional headers to be sent with the request, defaults to DEFAULT_REQUEST_HEADERS
Returns:
  • str( str ) –

    the URL to the image, e.g. 'https://upload.wikimedia.org/wikipedia/commons/thumb/b/ba/Theo._Komisarjevsky_LCCN2014715267.jpg/250px-Theo._Komisarjevsky_LCCN2014715267.jpg'
Source code in src/acdh_wikidata_pyutils/__init__.py 
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
def fetch_image(
    wikidata_id: str, thumb_width: int = 250, headers: dict = DEFAULT_REQUEST_HEADERS
) -> str:
    """returns the URL of a wikimedia image related to the given wikidata id

    Args:
        wikidata_id (str): a wikidata id e.g. 'Q2390830'
        thumb_width (int): the requested image widh in pixels, defaults to 250
        headers (dict): optional headers to be sent with the request, defaults to DEFAULT_REQUEST_HEADERS

    Returns:
        str: the URL to the image, e.g. 'https://upload.wikimedia.org/wikipedia/commons/thumb/b/ba/Theo._Komisarjevsky_LCCN2014715267.jpg/250px-Theo._Komisarjevsky_LCCN2014715267.jpg'
    """  # noqa
    if wikidata_id.startswith("http"):
        wikidata_id = get_norm_id(wikidata_id)
    url = IMG_EP.format(wikidata_id)
    r = requests.get(url, headers=headers)
    try:
        img_name = r.json()["claims"]["P18"][0]["mainsnak"]["datavalue"]["value"]
    except KeyError:
        return ""
    if img_name is not None:
        img = URL_STUB.format(urllib.parse.quote(img_name))
        img_name = img.split("file/")[-1]
        api_url = JSON_API_STUB.format(img_name, thumb_width)
        data = requests.get(api_url, headers=headers).json()
        try:
            thumburl = next(iter(data["query"]["pages"].values()))["imageinfo"][0][
                "thumburl"
            ]
        except (KeyError, IndexError):
            return img
        return thumburl