rightmove-parser/test_rm.py at master · ahmetbersoz/rightmove-parser · 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

import pandas as pd
import pytest

from rightmove_webscraper import RightmoveData


base_url = "https://www.rightmove.co.uk/"
required_columns = {
    "address",
    "agent_url",
    "number_bedrooms",
    "postcode",
    "price",
    "search_date",
    "type",
    "url",
    "let_available_date",
    "let_type",
    "furnish_type",
    "council_tax",
    "minimum_tenancy_months",
    "deposit",
    "description",
    "property_type",
    "key_features",
    "utilities_rights_restrictions",
    "location",
    "latitude",
    "longitude",
}


def test_sale_residential():
    """Test a search on residential properties for sale."""
    url = f"{base_url}property-for-sale/find.html?searchType=SALE&locationIdentifier=REGION%5E94346&insId=1"
    rm = RightmoveData(url)
    assert isinstance(rm.average_price, float)
    assert isinstance(rm.get_results, pd.DataFrame)
    assert required_columns.issubset(set(rm.get_results.columns))
    assert len(rm.get_results) > 0
    assert isinstance(rm.page_count, int)
    assert rm.rent_or_sale == "sale"
    assert isinstance(rm.results_count, int)
    assert isinstance(rm.results_count_display, int)
    assert url == rm.url
    df = rm.summary()
    assert isinstance(df, pd.DataFrame)
    assert {"number_bedrooms", "count", "mean"}.issubset(set(df.columns))
    assert len(df) > 0
    for c in required_columns:
        if rm.get_results[c].dropna().empty:
            continue
        df = rm.summary(by=c)
        assert isinstance(df, pd.DataFrame)
        assert {c, "count", "mean"}.issubset(set(df.columns))
        assert len(df) > 0


def test_rent_residential():
    """Test a search on residential properties for rent."""
    url = f"{base_url}property-to-rent/find.html?searchType=RENT&locationIdentifier=REGION%5E94346"
    rm = RightmoveData(url)
    assert isinstance(rm.average_price, float)
    assert isinstance(rm.get_results, pd.DataFrame)
    assert required_columns.issubset(set(rm.get_results.columns))
    assert len(rm.get_results) > 0
    assert isinstance(rm.page_count, int)
    assert rm.rent_or_sale == "rent"
    assert isinstance(rm.results_count, int)
    assert isinstance(rm.results_count_display, int)
    assert url == rm.url
    df = rm.summary()
    assert isinstance(df, pd.DataFrame)
    assert {"number_bedrooms", "count", "mean"}.issubset(set(df.columns))
    assert len(df) > 0
    for c in required_columns:
        if rm.get_results[c].dropna().empty:
            continue
        df = rm.summary(by=c)
        assert isinstance(df, pd.DataFrame)
        assert {c, "count", "mean"}.issubset(set(df.columns))
        assert len(df) > 0


def test_sale_commercial():
    """Test a search on commercial properties for sale."""
    url = f"{base_url}commercial-property-for-sale/find.html?searchType=SALE&locationIdentifier=REGION%5E70417"
    rm = RightmoveData(url)
    assert isinstance(rm.average_price, float)
    assert isinstance(rm.get_results, pd.DataFrame)
    assert required_columns.issubset(set(rm.get_results.columns))
    assert len(rm.get_results) > 0
    assert isinstance(rm.page_count, int)
    assert rm.rent_or_sale == "sale-commercial"
    assert isinstance(rm.results_count, int)
    assert isinstance(rm.results_count_display, int)
    assert url == rm.url
    df = rm.summary()
    assert isinstance(df, pd.DataFrame)
    assert {"type", "count", "mean"}.issubset(set(df.columns))
    assert len(df) > 0
    for c in required_columns:
        if c == "number_bedrooms":
            continue
        if rm.get_results[c].dropna().empty:
            continue
        df = rm.summary(by=c)
        assert isinstance(df, pd.DataFrame)
        assert {c, "count", "mean"}.issubset(set(df.columns))
        assert len(df) > 0


def test_rent_commercial():
    """Test a search on commercial properties for rent."""
    url = f"{base_url}commercial-property-to-let/find.html?searchType=RENT&locationIdentifier=REGION%5E70417"
    rm = RightmoveData(url)
    assert isinstance(rm.average_price, float)
    assert isinstance(rm.get_results, pd.DataFrame)
    assert required_columns.issubset(set(rm.get_results.columns))
    assert len(rm.get_results) > 0
    assert isinstance(rm.page_count, int)
    assert rm.rent_or_sale == "rent-commercial"
    assert isinstance(rm.results_count, int)
    assert isinstance(rm.results_count_display, int)
    assert url == rm.url
    df = rm.summary()
    assert isinstance(df, pd.DataFrame)
    assert {"type", "count", "mean"}.issubset(set(df.columns))
    assert len(df) > 0
    for c in required_columns:
        if c == "number_bedrooms":
            continue
        if rm.get_results[c].dropna().empty:
            continue
        df = rm.summary(by=c)
        assert isinstance(df, pd.DataFrame)
        assert {c, "count", "mean"}.issubset(set(df.columns))
        assert len(df) > 0


def test_bad_url():
    """Test a bad URL raises a value error."""
    bad_url = "https://www.rightmove.co.uk/property"
    with pytest.raises(ValueError):
        _ = RightmoveData(bad_url)