Animal-Map/scraper.py at main · codingeologist/Animal-Map · GitHub

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
import os
import io
import sys
import json
import zipfile
import requests
import pandas as pd


def defined_postcode(query):

    url = "https://api.postcodes.io/postcodes/{}".format(query)

    response = requests.get(url)

    if response.status_code == 200:
        data = json.loads(response.text)
        data = data["result"]
        postcode = data["postcode"]
        lat = data["latitude"]
        lon = data["longitude"]
        print("Retreived Postcode: {}".format(postcode))
    else:
        print("Postcode API returned: {}".format(response.status_code))
        print("Exitting Process")
        sys.exit(0)

    return postcode, lat, lon


def random_postcode():

    url = "https://api.postcodes.io/random/postcodes"

    response = requests.get(url)

    if response.status_code == 200:
        data = json.loads(response.text)
        data = data["result"]
        postcode = data["postcode"]
        lat = data["latitude"]
        lon = data["longitude"]
        print("Retreived Postcode: {}".format(postcode))
    else:
        print("Postcode API returned: {}".format(response.status_code))
        print("Exitting Process")
        sys.exit(0)

    return postcode, lat, lon


def api_call(query, loc, lat, lon, radius):

    start_index = 0
    url = "https://records-ws.nbnatlas.org/occurrences/search?q={}&fq=genus:{}&lat={}&lon={}&radius=10.0".format(
        query, query, lat, lon, radius
    )

    columns = [
        "uuid",
        "speciesGuid",
        "scientificName",
        "vernacularName",
        "taxonRank",
        "stateProvince",
        "country",
        "decimalLatitude",
        "decimalLongitude"
    ]

    occurrences = []

    while True:
        response = requests.get(f"{url}&startIndex={start_index}&pageSize=100")

        if response.status_code != 200:
            # print("API returned error {} for {} query near {}".format(
            #     response.status_code, query, loc))
            data = pd.DataFrame(columns=columns)
            break

        new_occurrences = response.json()["occurrences"]
        occurrences.extend(new_occurrences)
        total_records = int(response.json()["totalRecords"])
        # print(f"query: {query}: start_index: {start_index} occurrences: {len(occurrences)}")

        if len(occurrences) >= total_records:
            break

        start_index += 100

    try:
        data = pd.json_normalize(occurrences)
        data = data[columns]
        return data
    except Exception:
        # print(f"No data returned by API")
        return pd.DataFrame(columns=columns)


def get_data(loc, lat, lon, rad):

    fox = api_call(query="Vulpes", loc=loc,
                   lat=lat, lon=lon, radius=rad)

    cat = api_call(query="Felis", loc=loc,
                   lat=lat, lon=lon, radius=rad)

    hedgehog = api_call(query="Erinaceus", loc=loc,
                        lat=lat, lon=lon, radius=rad)

    badger = api_call(query="Meles", loc=loc,
                      lat=lat, lon=lon, radius=rad)

    roe = api_call(query="Capreolus", loc=loc,
                   lat=lat, lon=lon, radius=rad)

    deer = api_call(query="Cervus", loc=loc,
                    lat=lat, lon=lon, radius=rad)

    hare = api_call(query="Lepus", loc=loc,
                    lat=lat, lon=lon, radius=rad)

    rabbit = api_call(query="Oryctolagus", loc=loc,
                      lat=lat, lon=lon, radius=rad)

    squirrel = api_call(query="Sciurus", loc=loc,
                        lat=lat, lon=lon, radius=rad)

    animal_lst = [fox, cat, hedgehog, badger,
                  roe, deer, hare, rabbit, squirrel]

    animal_lst = [df for df in animal_lst if not df.empty]

    data = pd.concat(animal_lst, axis=0, ignore_index=True, sort=False)

    return data


def defined_areas():

    postcodes = ["PH26 3HG", "CA11 0PU", "LL48 6LF", "GU29 9DH", "SO43 7BJ"]
    national_park = ["Cairngorms", "Lake District",
                     "Snowdonia", "South Downs", "New Forest"]

    for i in range(len(postcodes)):
        print("################################")
        postcode, lat, lon = defined_postcode(query=postcodes[i])

        get_data(loc=national_park[i], lat=lat, lon=lon)
        print("################################")


def rand_postcode():

    postcode, lat, lon = random_postcode()
    data = get_data(loc=postcode, lat=lat, lon=lon, rad=10.0)

    return data


def postcode_findr(lookup):

    postcode, lat, lon = defined_postcode(query=lookup)
    data = get_data(loc=postcode, lat=lat, lon=lon, rad=10.0)

    return data