firecrawl-otel 0.1.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,10 @@
1
+ .venv/
2
+ __pycache__/
3
+ *.pyc
4
+ .env
5
+
6
+ # build artifacts
7
+ build/
8
+ dist/
9
+ *.egg-info/
10
+ .pytest_cache/
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
@@ -0,0 +1,334 @@
1
+ Metadata-Version: 2.4
2
+ Name: firecrawl-otel
3
+ Version: 0.1.0
4
+ Summary: OpenTelemetry instrumentation for the Firecrawl SDK — ship scrape/crawl/search traces and metrics to SigNoz or any OTLP backend.
5
+ Project-URL: Homepage, https://github.com/gkarthi-signoz/firecrawl-otel
6
+ Project-URL: Source, https://github.com/gkarthi-signoz/firecrawl-otel
7
+ Project-URL: Issues, https://github.com/gkarthi-signoz/firecrawl-otel/issues
8
+ Author-email: Goutham Karthi <goutham@signoz.io>
9
+ License:
10
+ Apache License
11
+ Version 2.0, January 2004
12
+ http://www.apache.org/licenses/
13
+
14
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
15
+
16
+ 1. Definitions.
17
+
18
+ "License" shall mean the terms and conditions for use, reproduction,
19
+ and distribution as defined by Sections 1 through 9 of this document.
20
+
21
+ "Licensor" shall mean the copyright owner or entity authorized by
22
+ the copyright owner that is granting the License.
23
+
24
+ "Legal Entity" shall mean the union of the acting entity and all
25
+ other entities that control, are controlled by, or are under common
26
+ control with that entity. For the purposes of this definition,
27
+ "control" means (i) the power, direct or indirect, to cause the
28
+ direction or management of such entity, whether by contract or
29
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
30
+ outstanding shares, or (iii) beneficial ownership of such entity.
31
+
32
+ "You" (or "Your") shall mean an individual or Legal Entity
33
+ exercising permissions granted by this License.
34
+
35
+ "Source" form shall mean the preferred form for making modifications,
36
+ including but not limited to software source code, documentation
37
+ source, and configuration files.
38
+
39
+ "Object" form shall mean any form resulting from mechanical
40
+ transformation or translation of a Source form, including but
41
+ not limited to compiled object code, generated documentation,
42
+ and conversions to other media types.
43
+
44
+ "Work" shall mean the work of authorship, whether in Source or
45
+ Object form, made available under the License, as indicated by a
46
+ copyright notice that is included in or attached to the work
47
+ (an example is provided in the Appendix below).
48
+
49
+ "Derivative Works" shall mean any work, whether in Source or Object
50
+ form, that is based on (or derived from) the Work and for which the
51
+ editorial revisions, annotations, elaborations, or other modifications
52
+ represent, as a whole, an original work of authorship. For the purposes
53
+ of this License, Derivative Works shall not include works that remain
54
+ separable from, or merely link (or bind by name) to the interfaces of,
55
+ the Work and Derivative Works thereof.
56
+
57
+ "Contribution" shall mean any work of authorship, including
58
+ the original version of the Work and any modifications or additions
59
+ to that Work or Derivative Works thereof, that is intentionally
60
+ submitted to Licensor for inclusion in the Work by the copyright owner
61
+ or by an individual or Legal Entity authorized to submit on behalf of
62
+ the copyright owner. For the purposes of this definition, "submitted"
63
+ means any form of electronic, verbal, or written communication sent
64
+ to the Licensor or its representatives, including but not limited to
65
+ communication on electronic mailing lists, source code control systems,
66
+ and issue tracking systems that are managed by, or on behalf of, the
67
+ Licensor for the purpose of discussing and improving the Work, but
68
+ excluding communication that is conspicuously marked or otherwise
69
+ designated in writing by the copyright owner as "Not a Contribution."
70
+
71
+ "Contributor" shall mean Licensor and any individual or Legal Entity
72
+ on behalf of whom a Contribution has been received by Licensor and
73
+ subsequently incorporated within the Work.
74
+
75
+ 2. Grant of Copyright License. Subject to the terms and conditions of
76
+ this License, each Contributor hereby grants to You a perpetual,
77
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
78
+ copyright license to reproduce, prepare Derivative Works of,
79
+ publicly display, publicly perform, sublicense, and distribute the
80
+ Work and such Derivative Works in Source or Object form.
81
+
82
+ 3. Grant of Patent License. Subject to the terms and conditions of
83
+ this License, each Contributor hereby grants to You a perpetual,
84
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
85
+ (except as stated in this section) patent license to make, have made,
86
+ use, offer to sell, sell, import, and otherwise transfer the Work,
87
+ where such license applies only to those patent claims licensable
88
+ by such Contributor that are necessarily infringed by their
89
+ Contribution(s) alone or by combination of their Contribution(s)
90
+ with the Work to which such Contribution(s) was submitted. If You
91
+ institute patent litigation against any entity (including a
92
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
93
+ or a Contribution incorporated within the Work constitutes direct
94
+ or contributory patent infringement, then any patent licenses
95
+ granted to You under this License for that Work shall terminate
96
+ as of the date such litigation is filed.
97
+
98
+ 4. Redistribution. You may reproduce and distribute copies of the
99
+ Work or Derivative Works thereof in any medium, with or without
100
+ modifications, and in Source or Object form, provided that You
101
+ meet the following conditions:
102
+
103
+ (a) You must give any other recipients of the Work or
104
+ Derivative Works a copy of this License; and
105
+
106
+ (b) You must cause any modified files to carry prominent notices
107
+ stating that You changed the files; and
108
+
109
+ (c) You must retain, in the Source form of any Derivative Works
110
+ that You distribute, all copyright, patent, trademark, and
111
+ attribution notices from the Source form of the Work,
112
+ excluding those notices that do not pertain to any part of
113
+ the Derivative Works; and
114
+
115
+ (d) If the Work includes a "NOTICE" text file as part of its
116
+ distribution, then any Derivative Works that You distribute must
117
+ include a readable copy of the attribution notices contained
118
+ within such NOTICE file, excluding those notices that do not
119
+ pertain to any part of the Derivative Works, in at least one
120
+ of the following places: within a NOTICE text file distributed
121
+ as part of the Derivative Works; within the Source form or
122
+ documentation, if provided along with the Derivative Works; or,
123
+ within a display generated by the Derivative Works, if and
124
+ wherever such third-party notices normally appear. The contents
125
+ of the NOTICE file are for informational purposes only and
126
+ do not modify the License. You may add Your own attribution
127
+ notices within Derivative Works that You distribute, alongside
128
+ or as an addendum to the NOTICE text from the Work, provided
129
+ that such additional attribution notices cannot be construed
130
+ as modifying the License.
131
+
132
+ You may add Your own copyright statement to Your modifications and
133
+ may provide additional or different license terms and conditions
134
+ for use, reproduction, or distribution of Your modifications, or
135
+ for any such Derivative Works as a whole, provided Your use,
136
+ reproduction, and distribution of the Work otherwise complies with
137
+ the conditions stated in this License.
138
+
139
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
140
+ any Contribution intentionally submitted for inclusion in the Work
141
+ by You to the Licensor shall be under the terms and conditions of
142
+ this License, without any additional terms or conditions.
143
+ Notwithstanding the above, nothing herein shall supersede or modify
144
+ the terms of any separate license agreement you may have executed
145
+ with Licensor regarding such Contributions.
146
+
147
+ 6. Trademarks. This License does not grant permission to use the trade
148
+ names, trademarks, service marks, or product names of the Licensor,
149
+ except as required for reasonable and customary use in describing the
150
+ origin of the Work and reproducing the content of the NOTICE file.
151
+
152
+ 7. Disclaimer of Warranty. Unless required by applicable law or
153
+ agreed to in writing, Licensor provides the Work (and each
154
+ Contributor provides its Contributions) on an "AS IS" BASIS,
155
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
156
+ implied, including, without limitation, any warranties or conditions
157
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
158
+ PARTICULAR PURPOSE. You are solely responsible for determining the
159
+ appropriateness of using or redistributing the Work and assume any
160
+ risks associated with Your exercise of permissions under this License.
161
+
162
+ 8. Limitation of Liability. In no event and under no legal theory,
163
+ whether in tort (including negligence), contract, or otherwise,
164
+ unless required by applicable law (such as deliberate and grossly
165
+ negligent acts) or agreed to in writing, shall any Contributor be
166
+ liable to You for damages, including any direct, indirect, special,
167
+ incidental, or consequential damages of any character arising as a
168
+ result of this License or out of the use or inability to use the
169
+ Work (including but not limited to damages for loss of goodwill,
170
+ work stoppage, computer failure or malfunction, or any and all
171
+ other commercial damages or losses), even if such Contributor
172
+ has been advised of the possibility of such damages.
173
+
174
+ 9. Accepting Warranty or Additional Liability. While redistributing
175
+ the Work or Derivative Works thereof, You may choose to offer,
176
+ and charge a fee for, acceptance of support, warranty, indemnity,
177
+ or other liability obligations and/or rights consistent with this
178
+ License. However, in accepting such obligations, You may act only
179
+ on Your own behalf and on Your sole responsibility, not on behalf
180
+ of any other Contributor, and only if You agree to indemnify,
181
+ defend, and hold each Contributor harmless for any liability
182
+ incurred by, or claims asserted against, such Contributor by reason
183
+ of your accepting any such warranty or additional liability.
184
+
185
+ END OF TERMS AND CONDITIONS
186
+
187
+ APPENDIX: How to apply the Apache License to your work.
188
+
189
+ To apply the Apache License to your work, attach the following
190
+ boilerplate notice, with the fields enclosed by brackets "[]"
191
+ replaced with your own identifying information. (Don't include
192
+ the brackets!) The text should be enclosed in the appropriate
193
+ comment syntax for the file format. We also recommend that a
194
+ file or class name and description of purpose be included on the
195
+ same "printed page" as the copyright notice for easier
196
+ identification within third-party archives.
197
+
198
+ Copyright [yyyy] [name of copyright owner]
199
+
200
+ Licensed under the Apache License, Version 2.0 (the "License");
201
+ you may not use this file except in compliance with the License.
202
+ You may obtain a copy of the License at
203
+
204
+ http://www.apache.org/licenses/LICENSE-2.0
205
+
206
+ Unless required by applicable law or agreed to in writing, software
207
+ distributed under the License is distributed on an "AS IS" BASIS,
208
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
209
+ See the License for the specific language governing permissions and
210
+ limitations under the License.
211
+ License-File: LICENSE
212
+ Keywords: firecrawl,instrumentation,metrics,observability,opentelemetry,otel,signoz,tracing,web-scraping
213
+ Classifier: Development Status :: 4 - Beta
214
+ Classifier: Intended Audience :: Developers
215
+ Classifier: License :: OSI Approved :: Apache Software License
216
+ Classifier: Operating System :: OS Independent
217
+ Classifier: Programming Language :: Python :: 3
218
+ Classifier: Programming Language :: Python :: 3.9
219
+ Classifier: Programming Language :: Python :: 3.10
220
+ Classifier: Programming Language :: Python :: 3.11
221
+ Classifier: Programming Language :: Python :: 3.12
222
+ Classifier: Topic :: System :: Monitoring
223
+ Requires-Python: >=3.9
224
+ Requires-Dist: opentelemetry-api>=1.20.0
225
+ Requires-Dist: opentelemetry-instrumentation>=0.41b0
226
+ Requires-Dist: wrapt>=1.14.0
227
+ Provides-Extra: dev
228
+ Requires-Dist: build; extra == 'dev'
229
+ Requires-Dist: firecrawl-py>=2.0.0; extra == 'dev'
230
+ Requires-Dist: opentelemetry-sdk>=1.20.0; extra == 'dev'
231
+ Requires-Dist: pytest>=7.0; extra == 'dev'
232
+ Requires-Dist: twine; extra == 'dev'
233
+ Provides-Extra: instruments
234
+ Requires-Dist: firecrawl-py>=2.0.0; extra == 'instruments'
235
+ Description-Content-Type: text/markdown
236
+
237
+ # firecrawl-otel
238
+
239
+ OpenTelemetry instrumentation for the [Firecrawl](https://firecrawl.dev) Python
240
+ SDK. Trace every `scrape` / `crawl` / `search` / `map` / `extract` call and ship
241
+ the traces and metrics to [SigNoz](https://signoz.io) — or any OTLP backend —
242
+ **without changing your Firecrawl call sites**.
243
+
244
+ Firecrawl does not emit OpenTelemetry itself, so this package instruments it on
245
+ the client side using the standard OpenTelemetry `BaseInstrumentor` pattern.
246
+
247
+ ## Install
248
+
249
+ ```bash
250
+ pip install firecrawl-otel
251
+ ```
252
+
253
+ ## Quickstart
254
+
255
+ ```python
256
+ from firecrawl import Firecrawl
257
+ from firecrawl_otel import FirecrawlInstrumentor
258
+
259
+ FirecrawlInstrumentor().instrument() # once, at startup
260
+
261
+ app = Firecrawl(api_key="fc-...") # your normal client — unchanged
262
+ doc = app.scrape("https://example.com") # automatically traced
263
+ ```
264
+
265
+ Point the telemetry at SigNoz with standard OpenTelemetry environment variables:
266
+
267
+ ```bash
268
+ # SigNoz Cloud (region = us | us2 | eu | eu2 | in | in2)
269
+ export OTEL_SERVICE_NAME=my-app
270
+ export OTEL_EXPORTER_OTLP_ENDPOINT=https://ingest.us.signoz.cloud:443
271
+ export OTEL_EXPORTER_OTLP_HEADERS=signoz-ingestion-key=<your-key>
272
+ ```
273
+
274
+ For self-hosted SigNoz use `http://localhost:4317` and no headers.
275
+
276
+ ### Zero-code option
277
+
278
+ Because the package registers an `opentelemetry_instrumentor` entry point, the
279
+ OpenTelemetry CLI can enable it with no code change at all:
280
+
281
+ ```bash
282
+ pip install firecrawl-otel opentelemetry-distro opentelemetry-exporter-otlp
283
+ opentelemetry-bootstrap -a install
284
+ opentelemetry-instrument python your_app.py
285
+ ```
286
+
287
+ ## What you get in SigNoz
288
+
289
+ **Traces** — one span per Firecrawl call:
290
+
291
+ | Span attribute | Example |
292
+ | --- | --- |
293
+ | `firecrawl.operation` | `scrape`, `crawl`, `search`, `map` |
294
+ | `url.full` | `https://example.com` |
295
+ | `firecrawl.query` | `what is opentelemetry` (search) |
296
+ | `firecrawl.formats` | `markdown,html` |
297
+ | `firecrawl.results` | `5` |
298
+ | `firecrawl.credits_used` | `12` |
299
+ | `firecrawl.status` | `completed` |
300
+
301
+ **Metrics:**
302
+
303
+ | Metric | Type | Description |
304
+ | --- | --- | --- |
305
+ | `firecrawl.requests` | counter | Calls, tagged by `firecrawl.operation` + `outcome` (ok/error) |
306
+ | `firecrawl.request.duration` | histogram (ms) | Latency per call |
307
+ | `firecrawl.credits.used` | counter | Firecrawl credits consumed |
308
+ | `firecrawl.results.returned` | histogram | Documents/pages/results returned |
309
+
310
+ ## Notes
311
+
312
+ - **Call `instrument()` before creating the `Firecrawl` client.** The unified
313
+ client binds its methods at construction time, so instrument at startup (as in
314
+ the quickstart) — clients created afterwards are traced.
315
+ - **This library configures no exporters.** Exporter setup stays with your app
316
+ (the `OTEL_*` env vars above, or `opentelemetry-instrument`). That keeps it
317
+ composable with the rest of your OpenTelemetry setup.
318
+ - Pass explicit providers if you don't use the globals:
319
+ `FirecrawlInstrumentor().instrument(tracer_provider=tp, meter_provider=mp)`.
320
+ - Disable again with `FirecrawlInstrumentor().uninstrument()`.
321
+ - A runnable end-to-end demo (scrape → search → crawl) lives in
322
+ [`examples/`](./examples).
323
+
324
+ ## Development
325
+
326
+ ```bash
327
+ pip install -e ".[dev]"
328
+ pytest
329
+ python -m build && twine check dist/*
330
+ ```
331
+
332
+ ## License
333
+
334
+ Apache-2.0
@@ -0,0 +1,98 @@
1
+ # firecrawl-otel
2
+
3
+ OpenTelemetry instrumentation for the [Firecrawl](https://firecrawl.dev) Python
4
+ SDK. Trace every `scrape` / `crawl` / `search` / `map` / `extract` call and ship
5
+ the traces and metrics to [SigNoz](https://signoz.io) — or any OTLP backend —
6
+ **without changing your Firecrawl call sites**.
7
+
8
+ Firecrawl does not emit OpenTelemetry itself, so this package instruments it on
9
+ the client side using the standard OpenTelemetry `BaseInstrumentor` pattern.
10
+
11
+ ## Install
12
+
13
+ ```bash
14
+ pip install firecrawl-otel
15
+ ```
16
+
17
+ ## Quickstart
18
+
19
+ ```python
20
+ from firecrawl import Firecrawl
21
+ from firecrawl_otel import FirecrawlInstrumentor
22
+
23
+ FirecrawlInstrumentor().instrument() # once, at startup
24
+
25
+ app = Firecrawl(api_key="fc-...") # your normal client — unchanged
26
+ doc = app.scrape("https://example.com") # automatically traced
27
+ ```
28
+
29
+ Point the telemetry at SigNoz with standard OpenTelemetry environment variables:
30
+
31
+ ```bash
32
+ # SigNoz Cloud (region = us | us2 | eu | eu2 | in | in2)
33
+ export OTEL_SERVICE_NAME=my-app
34
+ export OTEL_EXPORTER_OTLP_ENDPOINT=https://ingest.us.signoz.cloud:443
35
+ export OTEL_EXPORTER_OTLP_HEADERS=signoz-ingestion-key=<your-key>
36
+ ```
37
+
38
+ For self-hosted SigNoz use `http://localhost:4317` and no headers.
39
+
40
+ ### Zero-code option
41
+
42
+ Because the package registers an `opentelemetry_instrumentor` entry point, the
43
+ OpenTelemetry CLI can enable it with no code change at all:
44
+
45
+ ```bash
46
+ pip install firecrawl-otel opentelemetry-distro opentelemetry-exporter-otlp
47
+ opentelemetry-bootstrap -a install
48
+ opentelemetry-instrument python your_app.py
49
+ ```
50
+
51
+ ## What you get in SigNoz
52
+
53
+ **Traces** — one span per Firecrawl call:
54
+
55
+ | Span attribute | Example |
56
+ | --- | --- |
57
+ | `firecrawl.operation` | `scrape`, `crawl`, `search`, `map` |
58
+ | `url.full` | `https://example.com` |
59
+ | `firecrawl.query` | `what is opentelemetry` (search) |
60
+ | `firecrawl.formats` | `markdown,html` |
61
+ | `firecrawl.results` | `5` |
62
+ | `firecrawl.credits_used` | `12` |
63
+ | `firecrawl.status` | `completed` |
64
+
65
+ **Metrics:**
66
+
67
+ | Metric | Type | Description |
68
+ | --- | --- | --- |
69
+ | `firecrawl.requests` | counter | Calls, tagged by `firecrawl.operation` + `outcome` (ok/error) |
70
+ | `firecrawl.request.duration` | histogram (ms) | Latency per call |
71
+ | `firecrawl.credits.used` | counter | Firecrawl credits consumed |
72
+ | `firecrawl.results.returned` | histogram | Documents/pages/results returned |
73
+
74
+ ## Notes
75
+
76
+ - **Call `instrument()` before creating the `Firecrawl` client.** The unified
77
+ client binds its methods at construction time, so instrument at startup (as in
78
+ the quickstart) — clients created afterwards are traced.
79
+ - **This library configures no exporters.** Exporter setup stays with your app
80
+ (the `OTEL_*` env vars above, or `opentelemetry-instrument`). That keeps it
81
+ composable with the rest of your OpenTelemetry setup.
82
+ - Pass explicit providers if you don't use the globals:
83
+ `FirecrawlInstrumentor().instrument(tracer_provider=tp, meter_provider=mp)`.
84
+ - Disable again with `FirecrawlInstrumentor().uninstrument()`.
85
+ - A runnable end-to-end demo (scrape → search → crawl) lives in
86
+ [`examples/`](./examples).
87
+
88
+ ## Development
89
+
90
+ ```bash
91
+ pip install -e ".[dev]"
92
+ pytest
93
+ python -m build && twine check dist/*
94
+ ```
95
+
96
+ ## License
97
+
98
+ Apache-2.0
@@ -0,0 +1,19 @@
1
+ # ---- Firecrawl ----
2
+ # Get your key at https://www.firecrawl.dev/app/api-keys
3
+ FIRECRAWL_API_KEY=fc-YOUR_API_KEY
4
+
5
+ # ---- SigNoz / OpenTelemetry ----
6
+ OTEL_SERVICE_NAME=firecrawl-demo
7
+
8
+ # --- SigNoz Cloud ---
9
+ # Endpoint: https://ingest.<region>.signoz.cloud:443 (region = us | us2 | eu | eu2 | in | in2)
10
+ OTEL_EXPORTER_OTLP_ENDPOINT=https://ingest.us.signoz.cloud:443
11
+ # Ingestion key: SigNoz -> Settings -> Ingestion Settings
12
+ OTEL_EXPORTER_OTLP_HEADERS=signoz-ingestion-key=YOUR_INGESTION_KEY
13
+
14
+ # --- Self-hosted SigNoz (use these two instead of the pair above) ---
15
+ # OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
16
+ # OTEL_EXPORTER_OTLP_HEADERS=
17
+
18
+ # Optional resource attributes
19
+ OTEL_RESOURCE_ATTRIBUTES=deployment.environment=demo,service.version=0.1.0
@@ -0,0 +1,57 @@
1
+ """Firecrawl -> SigNoz starter demo, using the firecrawl-otel instrumentor.
2
+
3
+ Runs a small web-data workflow (scrape + search + crawl). Because the SDK is
4
+ instrumented, every call is traced and measured automatically and exported to
5
+ SigNoz over OTLP. Open SigNoz afterwards and look for the service named by
6
+ OTEL_SERVICE_NAME (default: firecrawl-demo).
7
+
8
+ Run:
9
+ cp .env.example .env # fill in FIRECRAWL_API_KEY and SigNoz values
10
+ pip install -r requirements.txt
11
+ python app.py
12
+ """
13
+
14
+ import os
15
+
16
+ from dotenv import load_dotenv
17
+ from firecrawl import Firecrawl
18
+ from opentelemetry import trace
19
+
20
+ from firecrawl_otel import FirecrawlInstrumentor
21
+ from otel_setup import init_otel, shutdown_otel
22
+
23
+ load_dotenv()
24
+ init_otel() # exporters first (app-side setup)
25
+ FirecrawlInstrumentor().instrument() # then patch the Firecrawl SDK
26
+
27
+ tracer = trace.get_tracer("firecrawl.demo")
28
+
29
+
30
+ def main() -> None:
31
+ # Plain Firecrawl client — no wrapper. Instrumentation is transparent.
32
+ app = Firecrawl(api_key=os.environ["FIRECRAWL_API_KEY"])
33
+
34
+ # A parent span groups the whole workflow into one trace in SigNoz.
35
+ with tracer.start_as_current_span("firecrawl.demo.workflow"):
36
+ print("Scraping a single page...")
37
+ doc = app.scrape(
38
+ "https://docs.firecrawl.dev/introduction", formats=["markdown"]
39
+ )
40
+ print(f" scraped {len(getattr(doc, 'markdown', None) or '')} chars\n")
41
+
42
+ print("Searching the web...")
43
+ results = app.search("what is OpenTelemetry", limit=3)
44
+ print(f" got {len(getattr(results, 'web', None) or [])} results\n")
45
+
46
+ print("Crawling a small site (depth-limited)...")
47
+ crawl = app.crawl("https://docs.firecrawl.dev", limit=5)
48
+ print(f" crawled {len(getattr(crawl, 'data', None) or [])} pages\n")
49
+
50
+ print("Done. Flushing telemetry to SigNoz...")
51
+
52
+
53
+ if __name__ == "__main__":
54
+ try:
55
+ main()
56
+ finally:
57
+ shutdown_otel() # ensure buffered spans/metrics are delivered
@@ -0,0 +1,52 @@
1
+ """OpenTelemetry exporter bootstrap for the demo (the *application* side).
2
+
3
+ Note this lives in `examples/`, not in the `firecrawl_otel` package: a good
4
+ instrumentation library instruments but does not configure exporters. Your app
5
+ (or the `opentelemetry-instrument` CLI) owns exporter setup. Endpoint, headers
6
+ and service name are read from the standard OTEL_* environment variables, so the
7
+ same code targets SigNoz Cloud or a self-hosted SigNoz with no change.
8
+ """
9
+
10
+ import os
11
+
12
+ from opentelemetry import metrics, trace
13
+ from opentelemetry.exporter.otlp.proto.grpc.metric_exporter import OTLPMetricExporter
14
+ from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter
15
+ from opentelemetry.sdk.metrics import MeterProvider
16
+ from opentelemetry.sdk.metrics.export import PeriodicExportingMetricReader
17
+ from opentelemetry.sdk.resources import Resource
18
+ from opentelemetry.sdk.trace import TracerProvider
19
+ from opentelemetry.sdk.trace.export import BatchSpanProcessor
20
+
21
+ _INITIALIZED = False
22
+
23
+
24
+ def init_otel() -> None:
25
+ """Wire up trace + metric exporters to SigNoz. Idempotent."""
26
+ global _INITIALIZED
27
+ if _INITIALIZED:
28
+ return
29
+
30
+ resource = Resource.create() # reads OTEL_SERVICE_NAME / OTEL_RESOURCE_ATTRIBUTES
31
+
32
+ tracer_provider = TracerProvider(resource=resource)
33
+ tracer_provider.add_span_processor(BatchSpanProcessor(OTLPSpanExporter()))
34
+ trace.set_tracer_provider(tracer_provider)
35
+
36
+ reader = PeriodicExportingMetricReader(
37
+ OTLPMetricExporter(), export_interval_millis=15000
38
+ )
39
+ metrics.set_meter_provider(MeterProvider(resource=resource, metric_readers=[reader]))
40
+
41
+ _INITIALIZED = True
42
+ print(
43
+ f"[otel] exporting service "
44
+ f"'{os.getenv('OTEL_SERVICE_NAME', 'unknown_service')}' to "
45
+ f"{os.getenv('OTEL_EXPORTER_OTLP_ENDPOINT', '<unset>')}"
46
+ )
47
+
48
+
49
+ def shutdown_otel() -> None:
50
+ """Flush buffered spans/metrics before the process exits."""
51
+ trace.get_tracer_provider().shutdown()
52
+ metrics.get_meter_provider().shutdown()
@@ -0,0 +1,8 @@
1
+ # The instrumentation package (installs firecrawl-py via the extra)
2
+ firecrawl-otel[instruments]
3
+
4
+ # App-side OpenTelemetry SDK + OTLP exporter (owned by the app, not the library)
5
+ opentelemetry-sdk>=1.20.0
6
+ opentelemetry-exporter-otlp>=1.20.0
7
+
8
+ python-dotenv>=1.0.0
@@ -0,0 +1,70 @@
1
+ [build-system]
2
+ requires = ["hatchling"]
3
+ build-backend = "hatchling.build"
4
+
5
+ [project]
6
+ name = "firecrawl-otel"
7
+ dynamic = ["version"]
8
+ description = "OpenTelemetry instrumentation for the Firecrawl SDK — ship scrape/crawl/search traces and metrics to SigNoz or any OTLP backend."
9
+ readme = "README.md"
10
+ requires-python = ">=3.9"
11
+ license = { file = "LICENSE" }
12
+ authors = [{ name = "Goutham Karthi", email = "goutham@signoz.io" }]
13
+ keywords = [
14
+ "firecrawl",
15
+ "opentelemetry",
16
+ "otel",
17
+ "observability",
18
+ "signoz",
19
+ "tracing",
20
+ "metrics",
21
+ "web-scraping",
22
+ "instrumentation",
23
+ ]
24
+ classifiers = [
25
+ "Development Status :: 4 - Beta",
26
+ "Intended Audience :: Developers",
27
+ "License :: OSI Approved :: Apache Software License",
28
+ "Operating System :: OS Independent",
29
+ "Programming Language :: Python :: 3",
30
+ "Programming Language :: Python :: 3.9",
31
+ "Programming Language :: Python :: 3.10",
32
+ "Programming Language :: Python :: 3.11",
33
+ "Programming Language :: Python :: 3.12",
34
+ "Topic :: System :: Monitoring",
35
+ ]
36
+ dependencies = [
37
+ "opentelemetry-api >= 1.20.0",
38
+ "opentelemetry-instrumentation >= 0.41b0",
39
+ "wrapt >= 1.14.0",
40
+ ]
41
+
42
+ [project.optional-dependencies]
43
+ # `instruments` mirrors the OpenTelemetry-contrib convention: the library this
44
+ # package instruments, pulled only when you actually want to run it.
45
+ instruments = ["firecrawl-py >= 2.0.0"]
46
+ dev = [
47
+ "firecrawl-py >= 2.0.0",
48
+ "opentelemetry-sdk >= 1.20.0",
49
+ "pytest >= 7.0",
50
+ "build",
51
+ "twine",
52
+ ]
53
+
54
+ # Makes `opentelemetry-instrument python app.py` auto-discover and enable this.
55
+ [project.entry-points.opentelemetry_instrumentor]
56
+ firecrawl = "firecrawl_otel.instrumentor:FirecrawlInstrumentor"
57
+
58
+ [project.urls]
59
+ Homepage = "https://github.com/gkarthi-signoz/firecrawl-otel"
60
+ Source = "https://github.com/gkarthi-signoz/firecrawl-otel"
61
+ Issues = "https://github.com/gkarthi-signoz/firecrawl-otel/issues"
62
+
63
+ [tool.hatch.version]
64
+ path = "src/firecrawl_otel/version.py"
65
+
66
+ [tool.hatch.build.targets.wheel]
67
+ packages = ["src/firecrawl_otel"]
68
+
69
+ [tool.hatch.build.targets.sdist]
70
+ include = ["/src", "/tests", "/examples", "/README.md", "/LICENSE"]
@@ -0,0 +1,11 @@
1
+ """OpenTelemetry instrumentation for the Firecrawl SDK.
2
+
3
+ Import ``FirecrawlInstrumentor`` and call ``.instrument()`` once at startup to
4
+ trace every Firecrawl scrape/crawl/search/map/extract call and export it to
5
+ SigNoz (or any OTLP backend).
6
+ """
7
+
8
+ from firecrawl_otel.version import __version__
9
+ from firecrawl_otel.instrumentor import FirecrawlInstrumentor
10
+
11
+ __all__ = ["FirecrawlInstrumentor", "__version__"]
@@ -0,0 +1,250 @@
1
+ """OpenTelemetry instrumentation for the Firecrawl Python SDK.
2
+
3
+ Patches the Firecrawl v2 client so every scrape / crawl / search / map / extract
4
+ / batch_scrape call emits an OpenTelemetry span and metrics, with no change to
5
+ your Firecrawl call sites:
6
+
7
+ from firecrawl import Firecrawl
8
+ from firecrawl_otel import FirecrawlInstrumentor
9
+
10
+ FirecrawlInstrumentor().instrument() # call before creating the client
11
+ app = Firecrawl(api_key="fc-...")
12
+ app.scrape("https://example.com") # now traced
13
+
14
+ The unified ``firecrawl.Firecrawl`` client binds its methods from
15
+ ``firecrawl.v2.client.FirecrawlClient`` at construction time, so instrumentation
16
+ must be enabled *before* the client is created (the normal "instrument at
17
+ startup" pattern).
18
+
19
+ This library only *instruments*; it does not configure exporters. Point your
20
+ telemetry at SigNoz (or any OTLP backend) with the standard ``OTEL_*``
21
+ environment variables, or run under the ``opentelemetry-instrument`` CLI.
22
+ """
23
+
24
+ import importlib
25
+ import time
26
+ from typing import Any, Collection, Dict, Optional
27
+
28
+ from opentelemetry import metrics, trace
29
+ from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
30
+ from opentelemetry.instrumentation.utils import unwrap
31
+ from opentelemetry.trace import SpanKind, Status, StatusCode
32
+ from wrapt import wrap_function_wrapper
33
+
34
+ from firecrawl_otel.version import __version__
35
+
36
+ # The v2 client class is where these methods are actually defined; the unified
37
+ # `firecrawl.Firecrawl` client delegates to an instance of it.
38
+ _MODULE = "firecrawl.v2.client"
39
+ _CLASS = "FirecrawlClient"
40
+
41
+ # Methods we wrap. Methods absent from the installed SDK version are skipped.
42
+ _INSTRUMENTED_METHODS = (
43
+ "scrape",
44
+ "crawl",
45
+ "search",
46
+ "map",
47
+ "extract",
48
+ "batch_scrape",
49
+ )
50
+
51
+
52
+ class FirecrawlInstrumentor(BaseInstrumentor):
53
+ """Instruments the Firecrawl SDK with OpenTelemetry traces and metrics."""
54
+
55
+ def instrumentation_dependencies(self) -> Collection[str]:
56
+ return ("firecrawl-py >= 2.0.0",)
57
+
58
+ def _instrument(self, **kwargs: Any) -> None:
59
+ tracer = trace.get_tracer(
60
+ __name__, __version__, kwargs.get("tracer_provider")
61
+ )
62
+ meter = metrics.get_meter(
63
+ __name__, __version__, kwargs.get("meter_provider")
64
+ )
65
+ instruments = _build_instruments(meter)
66
+
67
+ try:
68
+ importlib.import_module(_MODULE)
69
+ except ImportError:
70
+ # Unsupported/old SDK layout; instrument nothing rather than crash.
71
+ return
72
+
73
+ for method in _INSTRUMENTED_METHODS:
74
+ try:
75
+ wrap_function_wrapper(
76
+ _MODULE,
77
+ f"{_CLASS}.{method}",
78
+ _make_wrapper(method, tracer, instruments),
79
+ )
80
+ except (AttributeError, ImportError):
81
+ continue
82
+
83
+ def _uninstrument(self, **kwargs: Any) -> None:
84
+ try:
85
+ module = importlib.import_module(_MODULE)
86
+ except ImportError:
87
+ return
88
+ client_cls = getattr(module, _CLASS, None)
89
+ if client_cls is None:
90
+ return
91
+ for method in _INSTRUMENTED_METHODS:
92
+ if hasattr(client_cls, method):
93
+ unwrap(client_cls, method)
94
+
95
+
96
+ # --------------------------------------------------------------------------- #
97
+ # Span / metric wrapping
98
+ # --------------------------------------------------------------------------- #
99
+ def _build_instruments(meter) -> Dict[str, Any]:
100
+ return {
101
+ "requests": meter.create_counter(
102
+ "firecrawl.requests",
103
+ unit="1",
104
+ description="Firecrawl API calls, tagged by operation and outcome",
105
+ ),
106
+ "duration": meter.create_histogram(
107
+ "firecrawl.request.duration",
108
+ unit="ms",
109
+ description="Wall-clock duration of a Firecrawl API call",
110
+ ),
111
+ "credits": meter.create_counter(
112
+ "firecrawl.credits.used",
113
+ unit="1",
114
+ description="Firecrawl credits consumed (when reported by the API)",
115
+ ),
116
+ "results": meter.create_histogram(
117
+ "firecrawl.results.returned",
118
+ unit="1",
119
+ description="Documents/pages/results returned by an operation",
120
+ ),
121
+ }
122
+
123
+
124
+ def _make_wrapper(operation: str, tracer, instruments: Dict[str, Any]):
125
+ """Build a wrapt wrapper for one Firecrawl method."""
126
+
127
+ def wrapper(wrapped, instance, args, kwargs):
128
+ base = {"firecrawl.operation": operation}
129
+ span_attrs = dict(base)
130
+ span_attrs.update(_target_attributes(operation, args, kwargs))
131
+ formats = kwargs.get("formats")
132
+ if formats:
133
+ span_attrs["firecrawl.formats"] = ",".join(map(str, formats))
134
+
135
+ start = time.monotonic()
136
+ with tracer.start_as_current_span(
137
+ f"firecrawl.{operation}", kind=SpanKind.CLIENT, attributes=span_attrs
138
+ ) as span:
139
+ try:
140
+ result = wrapped(*args, **kwargs)
141
+ except Exception as exc:
142
+ elapsed_ms = (time.monotonic() - start) * 1000
143
+ span.set_status(Status(StatusCode.ERROR, str(exc)))
144
+ span.record_exception(exc)
145
+ _record_request(instruments, base, "error", elapsed_ms)
146
+ raise
147
+
148
+ elapsed_ms = (time.monotonic() - start) * 1000
149
+ _annotate(span, base, result, instruments)
150
+ _record_request(instruments, base, "ok", elapsed_ms)
151
+ return result
152
+
153
+ return wrapper
154
+
155
+
156
+ def _record_request(
157
+ instruments: Dict[str, Any], base: Dict[str, str], outcome: str, elapsed_ms: float
158
+ ) -> None:
159
+ attrs = {**base, "outcome": outcome}
160
+ instruments["requests"].add(1, attrs)
161
+ instruments["duration"].record(elapsed_ms, attrs)
162
+
163
+
164
+ def _annotate(
165
+ span, base: Dict[str, str], result: Any, instruments: Dict[str, Any]
166
+ ) -> None:
167
+ payload = _as_dict(result)
168
+
169
+ count = _result_count(payload)
170
+ if count is not None:
171
+ span.set_attribute("firecrawl.results", count)
172
+ instruments["results"].record(count, base)
173
+
174
+ credits = _extract_credits(payload)
175
+ if credits is not None:
176
+ span.set_attribute("firecrawl.credits_used", credits)
177
+ instruments["credits"].add(credits, base)
178
+
179
+ status = payload.get("status")
180
+ if status:
181
+ span.set_attribute("firecrawl.status", str(status))
182
+
183
+ # Crawl jobs also report progress counters.
184
+ for key, attr in (("total", "firecrawl.total"), ("completed", "firecrawl.completed")):
185
+ value = payload.get(key)
186
+ if isinstance(value, int):
187
+ span.set_attribute(attr, value)
188
+
189
+ span.set_status(Status(StatusCode.OK))
190
+
191
+
192
+ # --------------------------------------------------------------------------- #
193
+ # Attribute extraction helpers
194
+ # --------------------------------------------------------------------------- #
195
+ def _target_attributes(operation: str, args, kwargs) -> Dict[str, Any]:
196
+ """The URL (scrape/crawl/map) or query (search) the call targets."""
197
+ key = "query" if operation == "search" else "url"
198
+ target = kwargs.get(key)
199
+ if target is None and args:
200
+ target = args[0]
201
+
202
+ if isinstance(target, str):
203
+ attr = "firecrawl.query" if operation == "search" else "url.full"
204
+ return {attr: target}
205
+ if isinstance(target, (list, tuple)): # batch_scrape / extract url lists
206
+ return {"firecrawl.url_count": len(target)}
207
+ return {}
208
+
209
+
210
+ def _result_count(payload: dict) -> Optional[int]:
211
+ data = payload.get("data")
212
+ if isinstance(data, list): # crawl / batch_scrape
213
+ return len(data)
214
+ if isinstance(payload.get("links"), list): # map
215
+ return len(payload["links"])
216
+ if payload.get("markdown") or payload.get("html"): # scrape (single doc)
217
+ return 1
218
+ # search responses expose web/news/images lists instead of `data`
219
+ result_lists = [
220
+ payload[k] for k in ("web", "news", "images") if isinstance(payload.get(k), list)
221
+ ]
222
+ if result_lists:
223
+ return sum(len(lst) for lst in result_lists)
224
+ return None
225
+
226
+
227
+ def _extract_credits(payload: dict) -> Optional[int]:
228
+ for key in ("creditsUsed", "credits_used"):
229
+ if payload.get(key) is not None:
230
+ return int(payload[key])
231
+ meta = payload.get("metadata")
232
+ if isinstance(meta, dict):
233
+ for key in ("creditsUsed", "credits_used"):
234
+ if meta.get(key) is not None:
235
+ return int(meta[key])
236
+ return None
237
+
238
+
239
+ def _as_dict(obj: Any) -> dict:
240
+ """Firecrawl SDK returns pydantic models; normalize to a plain dict."""
241
+ if isinstance(obj, dict):
242
+ return obj
243
+ for attr in ("model_dump", "dict"):
244
+ fn = getattr(obj, attr, None)
245
+ if callable(fn):
246
+ try:
247
+ return fn()
248
+ except Exception:
249
+ pass
250
+ return {}
@@ -0,0 +1 @@
1
+ __version__ = "0.1.0"
@@ -0,0 +1,188 @@
1
+ """Tests for FirecrawlInstrumentor.
2
+
3
+ We inject a fake `firecrawl` package that mirrors the real SDK layout: the v2
4
+ methods live on ``firecrawl.v2.client.FirecrawlClient``, and the unified
5
+ ``firecrawl.Firecrawl`` client binds them onto each instance in ``__init__``
6
+ (exactly like firecrawl-py 4.x). This lets us drive the real patching path with
7
+ no network or real SDK.
8
+
9
+ We call `_instrument` rather than `.instrument()` so the test does not depend on
10
+ firecrawl-py being installed as a distribution (the public `.instrument()` does
11
+ a dependency check that would skip a fake module).
12
+ """
13
+
14
+ import sys
15
+ import types
16
+
17
+ import pytest
18
+ from opentelemetry.sdk.metrics import MeterProvider
19
+ from opentelemetry.sdk.metrics.export import InMemoryMetricReader
20
+ from opentelemetry.sdk.trace import TracerProvider
21
+ from opentelemetry.sdk.trace.export import SimpleSpanProcessor
22
+ from opentelemetry.sdk.trace.export.in_memory_span_exporter import (
23
+ InMemorySpanExporter,
24
+ )
25
+
26
+
27
+ class MockDoc:
28
+ def __init__(self, **kw):
29
+ self.__dict__.update(kw)
30
+
31
+ def model_dump(self):
32
+ return dict(self.__dict__)
33
+
34
+
35
+ class _FirecrawlClient:
36
+ """Stand-in for firecrawl.v2.client.FirecrawlClient."""
37
+
38
+ def __init__(self, api_key=None):
39
+ self.api_key = api_key
40
+
41
+ def scrape(self, url, formats=None):
42
+ return MockDoc(markdown="# hello world", metadata={"credits_used": 3})
43
+
44
+ def search(self, query, limit=None):
45
+ return MockDoc(web=[{"url": "a"}, {"url": "b"}], news=[{"url": "c"}])
46
+
47
+ def crawl(self, url, limit=None):
48
+ return MockDoc(
49
+ status="completed",
50
+ total=2,
51
+ completed=2,
52
+ credits_used=12,
53
+ data=[{"markdown": "p1"}, {"markdown": "p2"}],
54
+ )
55
+
56
+ def map(self, url): # used to exercise the error path
57
+ raise RuntimeError("kaboom")
58
+
59
+
60
+ def _install_fake_firecrawl():
61
+ """Register a fake firecrawl package tree in sys.modules; return the root."""
62
+ root = types.ModuleType("firecrawl")
63
+ v2 = types.ModuleType("firecrawl.v2")
64
+ client_mod = types.ModuleType("firecrawl.v2.client")
65
+ client_mod.FirecrawlClient = _FirecrawlClient
66
+ v2.client = client_mod
67
+
68
+ class Firecrawl:
69
+ """Unified client that binds v2 methods per-instance, like the real SDK."""
70
+
71
+ def __init__(self, api_key=None):
72
+ self._v2 = client_mod.FirecrawlClient(api_key=api_key)
73
+ self.scrape = self._v2.scrape
74
+ self.search = self._v2.search
75
+ self.crawl = self._v2.crawl
76
+ self.map = self._v2.map
77
+
78
+ root.Firecrawl = Firecrawl
79
+ root.v2 = v2
80
+
81
+ sys.modules["firecrawl"] = root
82
+ sys.modules["firecrawl.v2"] = v2
83
+ sys.modules["firecrawl.v2.client"] = client_mod
84
+ return root
85
+
86
+
87
+ @pytest.fixture
88
+ def instrumented():
89
+ span_exporter = InMemorySpanExporter()
90
+ tracer_provider = TracerProvider()
91
+ tracer_provider.add_span_processor(SimpleSpanProcessor(span_exporter))
92
+
93
+ metric_reader = InMemoryMetricReader()
94
+ meter_provider = MeterProvider(metric_readers=[metric_reader])
95
+
96
+ firecrawl = _install_fake_firecrawl()
97
+
98
+ from firecrawl_otel import FirecrawlInstrumentor
99
+
100
+ instr = FirecrawlInstrumentor()
101
+ instr._instrument(
102
+ tracer_provider=tracer_provider, meter_provider=meter_provider
103
+ )
104
+
105
+ # Client is created AFTER instrument(), mirroring the documented order.
106
+ yield firecrawl, span_exporter, metric_reader, instr
107
+
108
+ instr._uninstrument()
109
+ for name in ("firecrawl.v2.client", "firecrawl.v2", "firecrawl"):
110
+ sys.modules.pop(name, None)
111
+
112
+
113
+ def _spans_by_name(exporter):
114
+ return {s.name: s for s in exporter.get_finished_spans()}
115
+
116
+
117
+ def test_scrape_span_attributes(instrumented):
118
+ firecrawl, spans_exporter, _, _ = instrumented
119
+ app = firecrawl.Firecrawl(api_key="fc-test")
120
+ app.scrape("https://example.com", formats=["markdown", "html"])
121
+
122
+ span = _spans_by_name(spans_exporter)["firecrawl.scrape"]
123
+ assert span.attributes["firecrawl.operation"] == "scrape"
124
+ assert span.attributes["firecrawl.formats"] == "markdown,html"
125
+ assert span.attributes["url.full"] == "https://example.com"
126
+ assert span.attributes["firecrawl.results"] == 1
127
+ assert span.attributes["firecrawl.credits_used"] == 3 # from metadata
128
+ assert span.status.status_code.name == "OK"
129
+
130
+
131
+ def test_search_and_crawl(instrumented):
132
+ firecrawl, spans_exporter, _, _ = instrumented
133
+ app = firecrawl.Firecrawl(api_key="fc-test")
134
+ app.search("what is otel", limit=2)
135
+ app.crawl("https://example.com", limit=5)
136
+
137
+ spans = _spans_by_name(spans_exporter)
138
+ search = spans["firecrawl.search"]
139
+ assert search.attributes["firecrawl.query"] == "what is otel"
140
+ assert search.attributes["firecrawl.results"] == 3 # 2 web + 1 news
141
+
142
+ crawl = spans["firecrawl.crawl"]
143
+ assert crawl.attributes["firecrawl.results"] == 2
144
+ assert crawl.attributes["firecrawl.credits_used"] == 12 # from credits_used
145
+ assert crawl.attributes["firecrawl.status"] == "completed"
146
+ assert crawl.attributes["firecrawl.total"] == 2
147
+
148
+
149
+ def test_error_path_sets_error_status(instrumented):
150
+ firecrawl, spans_exporter, _, _ = instrumented
151
+ app = firecrawl.Firecrawl(api_key="fc-test")
152
+ with pytest.raises(RuntimeError):
153
+ app.map("https://example.com")
154
+
155
+ span = _spans_by_name(spans_exporter)["firecrawl.map"]
156
+ assert span.status.status_code.name == "ERROR"
157
+ assert len(span.events) >= 1 # recorded exception
158
+
159
+
160
+ def test_metrics_recorded(instrumented):
161
+ firecrawl, _, metric_reader, _ = instrumented
162
+ app = firecrawl.Firecrawl(api_key="fc-test")
163
+ app.scrape("https://example.com", formats=["markdown"])
164
+ app.crawl("https://example.com", limit=5)
165
+
166
+ metric_names = set()
167
+ total_requests = 0
168
+ for rm in metric_reader.get_metrics_data().resource_metrics:
169
+ for sm in rm.scope_metrics:
170
+ for metric in sm.metrics:
171
+ metric_names.add(metric.name)
172
+ if metric.name == "firecrawl.requests":
173
+ total_requests += sum(p.value for p in metric.data.data_points)
174
+
175
+ assert "firecrawl.requests" in metric_names
176
+ assert "firecrawl.request.duration" in metric_names
177
+ assert "firecrawl.credits.used" in metric_names
178
+ assert total_requests == 2
179
+
180
+
181
+ def test_uninstrument_stops_tracing(instrumented):
182
+ firecrawl, spans_exporter, _, instr = instrumented
183
+ instr._uninstrument()
184
+
185
+ # A client created after uninstrument binds the original, unwrapped methods.
186
+ app = firecrawl.Firecrawl(api_key="fc-test")
187
+ app.scrape("https://example.com")
188
+ assert "firecrawl.scrape" not in _spans_by_name(spans_exporter)