scrapfly-scrapers/similarweb-scraper/test.py at main · scrapfly/scrapfly-scrapers · 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
from cerberus import Validator as _Validator
import pytest
import similarweb
import pprint

pp = pprint.PrettyPrinter(indent=4)

similarweb.BASE_CONFIG["cache"] = False

class Validator(_Validator):
    def _validate_min_presence(self, min_presence, field, value):
        pass  # required for adding non-standard keys to schema


def validate_or_fail(item, validator):
    if not validator.validate(item):
        pp.pformat(item)
        pytest.fail(f"Validation failed for item: {pp.pformat(item)}\nErrors: {validator.errors}")


website_schema = {
    "interests": {
        "type": "dict",
        "schema": {
            "interestedWebsitesTotalCount": {"type": "integer"},
            "topInterestedCategories": {
                "type": "list",
                "schema": {"type": "string"}
            }
        }
    },
    "competitors": {
        "type": "dict",
        "schema": {
            "topSimilarityCompetitors": {
                "type": "list",
                "schema": {
                    "type": "dict",
                    "schema": {
                        "domain": {"type": "string"},
                        "icon": {"type": "string"},
                        "visitsTotalCount": {"type": "integer"},
                        "categoryId": {"type": "string"},
                        "categoryRank": {"type": "integer", "nullable": True},
                        "affinity": {"type": "float"},
                        "isDataFromGa": {"type": "boolean"},
                    }
                }
            }
        }
    },
    "searchesSource": {
        "type": "dict",
        "schema": {
            "organicSearchShare": {"type": "float"},
            "paidSearchShare": {"type": "float"},
            "keywordsTotalCount": {"type": "float"},
        }
    }
}

website_compare_schema = {
    "twitter.com": {
        "type": "dict",
        "schema": {
            "overview": {
                "type": "dict",
                "schema": {
                    "description": {"type": "string"},
                    "countryAlpha2Code": {"type": "string"},
                    "globalRank": {"type": "integer", "nullable": True},
                    "globalRankChange": {"type": "integer"},
                    "countryRank": {"type": "integer", "nullable": True},
                    "countryRankChange": {"type": "integer"},
                    "categoryRank": {"type": "integer", "nullable": True},
                }
            }
        }
    }
}

trends_schema = {
    "name": {"type": "string"},
    "url": {"type": "string"},
    "list": {
        "type": "list",
        "schema": {
            "type": "dict",
            "schema": {
                "@type": {"type": "string"},
                "position": {"type": "integer"},
                "item": {
                    "type": "dict",
                    "schema": {
                        "@type": {"type": "string"},
                        "name": {"type": "string"},
                        "url": {"type": "string"}
                    }
                }
            }
        }
    }
}


@pytest.mark.asyncio
@pytest.mark.flaky(reruns=3, reruns_delay=30)
async def test_website_scraping():
    website_data = await similarweb.scrape_website(
        domains=["google.com", "twitter.com", "youtube.com"]
    )
    validator = Validator(website_schema, allow_unknown=True)
    for item in website_data:
        validate_or_fail(item, validator)
    assert len(website_data) == 3


@pytest.mark.asyncio
@pytest.mark.flaky(reruns=3, reruns_delay=30)
async def test_website_compare_scraping():
    comparing_data = await similarweb.scrape_website_compare(
        first_domain="twitter.com",
        second_domain="instagram.com"
    )
    validator = Validator(website_compare_schema, allow_unknown=True)
    validate_or_fail(comparing_data, validator)
    assert len(comparing_data["twitter.com"]["overview"]) >= 10


@pytest.mark.asyncio
@pytest.mark.flaky(reruns=3, reruns_delay=30)
async def test_trend_scraping():
    trending_data = await similarweb.scrape_trendings(
        urls=[
            "https://www.similarweb.com/top-websites/computers-electronics-and-technology/programming-and-developer-software/",
            "https://www.similarweb.com/top-websites/computers-electronics-and-technology/social-networks-and-online-communities/",
            "https://www.similarweb.com/top-websites/finance/investing/"
        ]
    )
    validator = Validator(trends_schema, allow_unknown=True)
    for item in trending_data:
        validate_or_fail(item, validator)
    assert len(trending_data) == 3


@pytest.mark.asyncio
@pytest.mark.flaky(reruns=3, reruns_delay=30)
async def test_sitemap_scraping():
    sitemap_urls = await similarweb.scrape_sitemaps(
        url="https://www.similarweb.com/sitemaps/top-websites/top-websites-001.xml.gz"
    )
    assert len(sitemap_urls) > 100