File size: 7,031 Bytes
097eaf0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Tests for direct scrape kwargs on crawl() and start_crawl()."""

import asyncio
import inspect

import pytest

from firecrawl.v2.client import FirecrawlClient, _SCRAPE_OPTION_KEYS
from firecrawl.v2.client_async import AsyncFirecrawlClient
from firecrawl.v2.types import ScrapeOptions
import firecrawl.v2.methods.crawl as crawl_mod
from firecrawl.v2.methods.aio import crawl as async_crawl_mod


@pytest.fixture
def client():
    return FirecrawlClient(api_key="fc-test", api_url="http://localhost:9")


@pytest.fixture
def async_client():
    return AsyncFirecrawlClient(api_key="fc-test", api_url="http://localhost:9")


class TestSyncCrawlDirectKwargs:
    def test_crawl_signature_accepts_formats(self):
        sig = inspect.signature(FirecrawlClient.crawl)
        assert "formats" in sig.parameters

    def test_start_crawl_signature_accepts_formats(self):
        sig = inspect.signature(FirecrawlClient.start_crawl)
        assert "formats" in sig.parameters

    def test_direct_kwargs_build_scrape_options(self, client, monkeypatch):
        captured = {}

        def fake_start_crawl(http, request):
            captured["scrape_options"] = request.scrape_options
            raise ConnectionError("captured")

        monkeypatch.setattr(crawl_mod, "start_crawl", fake_start_crawl)

        with pytest.raises(ConnectionError):
            client.start_crawl("https://example.com", formats=["markdown"])

        assert captured["scrape_options"] is not None
        fmt_strs = [str(f) for f in captured["scrape_options"].formats]
        assert "markdown" in fmt_strs

    def test_explicit_scrape_options_wins(self, client, monkeypatch):
        captured = {}

        def fake_start_crawl(http, request):
            captured["scrape_options"] = request.scrape_options
            raise ConnectionError("captured")

        monkeypatch.setattr(crawl_mod, "start_crawl", fake_start_crawl)

        with pytest.raises(ConnectionError):
            client.start_crawl(
                "https://example.com",
                scrape_options=ScrapeOptions(formats=["html"]),
                formats=["markdown"],
            )

        fmt_strs = [str(f) for f in captured["scrape_options"].formats]
        assert "html" in fmt_strs
        assert "markdown" not in fmt_strs

    def test_no_scrape_kwargs_means_no_scrape_options(self, client, monkeypatch):
        captured = {}

        def fake_start_crawl(http, request):
            captured["scrape_options"] = request.scrape_options
            raise ConnectionError("captured")

        monkeypatch.setattr(crawl_mod, "start_crawl", fake_start_crawl)

        with pytest.raises(ConnectionError):
            client.start_crawl("https://example.com", limit=10)

        assert captured["scrape_options"] is None

    def test_crawl_also_builds_scrape_options(self, client, monkeypatch):
        captured = {}

        def fake_crawl(http, request, poll_interval=2, timeout=None, request_timeout=None):
            captured["scrape_options"] = request.scrape_options
            raise ConnectionError("captured")

        monkeypatch.setattr(crawl_mod, "crawl", fake_crawl)

        with pytest.raises(ConnectionError):
            client.crawl("https://example.com", formats=["markdown"], only_main_content=True)

        assert captured["scrape_options"] is not None
        assert captured["scrape_options"].only_main_content is True

    def test_start_crawl_accepts_scrape_timeout(self, client, monkeypatch):
        captured = {}

        def fake_start_crawl(http, request):
            captured["scrape_options"] = request.scrape_options
            raise ConnectionError("captured")

        monkeypatch.setattr(crawl_mod, "start_crawl", fake_start_crawl)

        with pytest.raises(ConnectionError):
            client.start_crawl("https://example.com", timeout=5000)

        assert captured["scrape_options"] is not None
        assert captured["scrape_options"].timeout == 5000

    def test_crawl_timeout_is_poll_timeout_not_scrape(self, client, monkeypatch):
        captured = {}

        def fake_crawl(http, request, poll_interval=2, timeout=None, request_timeout=None):
            captured["scrape_options"] = request.scrape_options
            captured["poll_timeout"] = timeout
            raise ConnectionError("captured")

        monkeypatch.setattr(crawl_mod, "crawl", fake_crawl)

        with pytest.raises(ConnectionError):
            client.crawl("https://example.com", timeout=60, formats=["markdown"])

        assert captured["poll_timeout"] == 60
        assert captured["scrape_options"] is not None
        assert captured["scrape_options"].timeout is None


class TestAsyncCrawlDirectKwargs:
    def test_async_direct_kwargs_build_scrape_options(self, async_client, monkeypatch):
        captured = {}

        async def fake_start_crawl(http, request):
            captured["scrape_options"] = request.scrape_options
            raise ConnectionError("captured")

        monkeypatch.setattr(async_crawl_mod, "start_crawl", fake_start_crawl)

        with pytest.raises(ConnectionError):
            asyncio.get_event_loop().run_until_complete(
                async_client.start_crawl("https://example.com", formats=["markdown"])
            )

        assert captured["scrape_options"] is not None
        fmt_strs = [str(f) for f in captured["scrape_options"].formats]
        assert "markdown" in fmt_strs

    def test_async_explicit_scrape_options_wins(self, async_client, monkeypatch):
        captured = {}

        async def fake_start_crawl(http, request):
            captured["scrape_options"] = request.scrape_options
            raise ConnectionError("captured")

        monkeypatch.setattr(async_crawl_mod, "start_crawl", fake_start_crawl)

        with pytest.raises(ConnectionError):
            asyncio.get_event_loop().run_until_complete(
                async_client.start_crawl(
                    "https://example.com",
                    scrape_options=ScrapeOptions(formats=["html"]),
                    formats=["markdown"],
                )
            )

        fmt_strs = [str(f) for f in captured["scrape_options"].formats]
        assert "html" in fmt_strs

    def test_async_integration_preserved_as_crawl_param(self, async_client, monkeypatch):
        captured = {}

        async def fake_start_crawl(http, request):
            captured["scrape_options"] = request.scrape_options
            captured["integration"] = request.integration
            raise ConnectionError("captured")

        monkeypatch.setattr(async_crawl_mod, "start_crawl", fake_start_crawl)

        with pytest.raises(ConnectionError):
            asyncio.get_event_loop().run_until_complete(
                async_client.start_crawl(
                    "https://example.com",
                    formats=["markdown"],
                    integration="test-int",
                )
            )

        assert captured["integration"] == "test-int"
        assert captured["scrape_options"] is not None