pyunbrowser 0.0.1__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.
- pyunbrowser-0.0.1/.gitignore +28 -0
- pyunbrowser-0.0.1/LICENSE +202 -0
- pyunbrowser-0.0.1/PKG-INFO +80 -0
- pyunbrowser-0.0.1/README.md +53 -0
- pyunbrowser-0.0.1/pyproject.toml +64 -0
- pyunbrowser-0.0.1/unbrowser/__init__.py +333 -0
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
# Rust build artifacts
|
|
2
|
+
/target
|
|
3
|
+
**/*.rs.bk
|
|
4
|
+
|
|
5
|
+
# Editor / OS
|
|
6
|
+
.DS_Store
|
|
7
|
+
*.swp
|
|
8
|
+
*.swo
|
|
9
|
+
.idea/
|
|
10
|
+
.vscode/
|
|
11
|
+
|
|
12
|
+
# Local-only artifacts
|
|
13
|
+
*.log
|
|
14
|
+
/tmp/
|
|
15
|
+
|
|
16
|
+
# Secrets — never commit. .env* covers .env, .env.local, .env.production, etc.
|
|
17
|
+
.env
|
|
18
|
+
.env.*
|
|
19
|
+
!.env.example
|
|
20
|
+
|
|
21
|
+
# Python package build artifacts (the binary lands in _bin/ at CI time
|
|
22
|
+
# only — we never want it in git; the .gitkeep placeholder is preserved)
|
|
23
|
+
/python/dist/
|
|
24
|
+
/python/build/
|
|
25
|
+
/python/*.egg-info/
|
|
26
|
+
/python/unbrowser/__pycache__/
|
|
27
|
+
/python/unbrowser/_bin/*
|
|
28
|
+
!/python/unbrowser/_bin/.gitkeep
|
|
@@ -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 +1,80 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: pyunbrowser
|
|
3
|
+
Version: 0.0.1
|
|
4
|
+
Summary: Web access for LLM agents. One static binary. No Chrome.
|
|
5
|
+
Project-URL: Homepage, https://github.com/protostatis/unbrowser
|
|
6
|
+
Project-URL: Repository, https://github.com/protostatis/unbrowser
|
|
7
|
+
Project-URL: Issues, https://github.com/protostatis/unbrowser/issues
|
|
8
|
+
Author: protostatis
|
|
9
|
+
License: Apache-2.0
|
|
10
|
+
License-File: LICENSE
|
|
11
|
+
Keywords: agent,automation,browser,headless,llm,scraping
|
|
12
|
+
Classifier: Development Status :: 3 - Alpha
|
|
13
|
+
Classifier: Intended Audience :: Developers
|
|
14
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
15
|
+
Classifier: Operating System :: MacOS
|
|
16
|
+
Classifier: Operating System :: POSIX :: Linux
|
|
17
|
+
Classifier: Programming Language :: Python :: 3
|
|
18
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
19
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
20
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
21
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
22
|
+
Classifier: Programming Language :: Rust
|
|
23
|
+
Classifier: Topic :: Internet :: WWW/HTTP :: Browsers
|
|
24
|
+
Classifier: Topic :: Software Development :: Libraries
|
|
25
|
+
Requires-Python: >=3.10
|
|
26
|
+
Description-Content-Type: text/markdown
|
|
27
|
+
|
|
28
|
+
# unbrowser
|
|
29
|
+
|
|
30
|
+
**Web access for LLM agents. One static binary. No Chrome.**
|
|
31
|
+
|
|
32
|
+
Single-file native headless browser optimized for LLM agents. Runs JavaScript via QuickJS, returns a low-token page summary on every navigate, and gives you stable element refs for click/type/submit. Tens of MB RAM per session, no Chrome dependency.
|
|
33
|
+
|
|
34
|
+
```bash
|
|
35
|
+
pip install unbrowser
|
|
36
|
+
```
|
|
37
|
+
|
|
38
|
+
The wheel ships the native binary for your platform — there's nothing else to install.
|
|
39
|
+
|
|
40
|
+
## Quick start
|
|
41
|
+
|
|
42
|
+
```python
|
|
43
|
+
from unbrowser import Client
|
|
44
|
+
|
|
45
|
+
with Client() as ub:
|
|
46
|
+
r = ub.navigate("https://news.ycombinator.com")
|
|
47
|
+
for s in ub.query(".titleline > a")[:3]:
|
|
48
|
+
print(s["text"], s["attrs"]["href"])
|
|
49
|
+
```
|
|
50
|
+
|
|
51
|
+
## Why
|
|
52
|
+
|
|
53
|
+
| | curl | This | Playwright / headless Chrome |
|
|
54
|
+
|---|---|---|---|
|
|
55
|
+
| Static / SSR pages | ✅ but token-heavy | ✅ low-token BlockMap | overkill |
|
|
56
|
+
| SPA-shell sites (with `exec_scripts`) | ❌ | ⚠️ partial | ✅ |
|
|
57
|
+
| Bot-walled (cookie handoff) | ❌ | ✅ | ✅ |
|
|
58
|
+
| Run in Lambda / Workers / edge | ✅ | ✅ | ❌ Chrome too big |
|
|
59
|
+
| Per-page cost at 100K/day | ~free | ~free | $$$ |
|
|
60
|
+
| LLM-shaped output | DIY parse | ✅ inline BlockMap | DIY parse |
|
|
61
|
+
|
|
62
|
+
## What it does
|
|
63
|
+
|
|
64
|
+
- **`navigate(url)`** — fetch, parse, return `{status, url, bytes, headers, blockmap, challenge}`. With `exec_scripts=True`, runs page JS in QuickJS (bounded by a 30s watchdog so it can't wedge).
|
|
65
|
+
- **`query(selector)`** — CSS query → `[{ref, tag, attrs, text}]`. Refs are stable handles for click/type/submit.
|
|
66
|
+
- **`extract()`** — auto-strategy structured data: tries JSON-LD → `__NEXT_DATA__` → Nuxt → OpenGraph → microdata → text fallback, returns highest-confidence hit.
|
|
67
|
+
- **`click(ref)` / `type(ref, text)` / `submit(ref)`** — interaction. POST and GET forms supported. Checkboxes/radios tracked.
|
|
68
|
+
- **`cookies_set(...)`** — paste cookies from a real Chrome session to bypass bot detection (Cloudflare, PerimeterX, Datadome). Solve once, replay forever.
|
|
69
|
+
|
|
70
|
+
Full RPC reference, BlockMap shape, challenge detection, profile system, and architecture: [github.com/protostatis/unbrowser](https://github.com/protostatis/unbrowser).
|
|
71
|
+
|
|
72
|
+
## Honest limits
|
|
73
|
+
|
|
74
|
+
- Heavy framework SPAs (Ember/React) often don't auto-mount inside QuickJS even with `exec_scripts=True` — the watchdog ensures it returns, check `density.likely_js_filled` to decide whether to escalate.
|
|
75
|
+
- No screenshots (out of scope by design).
|
|
76
|
+
- Hardest-tier anti-bot (FingerprintJS Pro, Kasada, advanced Akamai BMP) needs the cookie handoff path. The binary detects and labels the challenge for you.
|
|
77
|
+
|
|
78
|
+
## License
|
|
79
|
+
|
|
80
|
+
Apache-2.0.
|
|
@@ -0,0 +1,53 @@
|
|
|
1
|
+
# unbrowser
|
|
2
|
+
|
|
3
|
+
**Web access for LLM agents. One static binary. No Chrome.**
|
|
4
|
+
|
|
5
|
+
Single-file native headless browser optimized for LLM agents. Runs JavaScript via QuickJS, returns a low-token page summary on every navigate, and gives you stable element refs for click/type/submit. Tens of MB RAM per session, no Chrome dependency.
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
pip install unbrowser
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
The wheel ships the native binary for your platform — there's nothing else to install.
|
|
12
|
+
|
|
13
|
+
## Quick start
|
|
14
|
+
|
|
15
|
+
```python
|
|
16
|
+
from unbrowser import Client
|
|
17
|
+
|
|
18
|
+
with Client() as ub:
|
|
19
|
+
r = ub.navigate("https://news.ycombinator.com")
|
|
20
|
+
for s in ub.query(".titleline > a")[:3]:
|
|
21
|
+
print(s["text"], s["attrs"]["href"])
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
## Why
|
|
25
|
+
|
|
26
|
+
| | curl | This | Playwright / headless Chrome |
|
|
27
|
+
|---|---|---|---|
|
|
28
|
+
| Static / SSR pages | ✅ but token-heavy | ✅ low-token BlockMap | overkill |
|
|
29
|
+
| SPA-shell sites (with `exec_scripts`) | ❌ | ⚠️ partial | ✅ |
|
|
30
|
+
| Bot-walled (cookie handoff) | ❌ | ✅ | ✅ |
|
|
31
|
+
| Run in Lambda / Workers / edge | ✅ | ✅ | ❌ Chrome too big |
|
|
32
|
+
| Per-page cost at 100K/day | ~free | ~free | $$$ |
|
|
33
|
+
| LLM-shaped output | DIY parse | ✅ inline BlockMap | DIY parse |
|
|
34
|
+
|
|
35
|
+
## What it does
|
|
36
|
+
|
|
37
|
+
- **`navigate(url)`** — fetch, parse, return `{status, url, bytes, headers, blockmap, challenge}`. With `exec_scripts=True`, runs page JS in QuickJS (bounded by a 30s watchdog so it can't wedge).
|
|
38
|
+
- **`query(selector)`** — CSS query → `[{ref, tag, attrs, text}]`. Refs are stable handles for click/type/submit.
|
|
39
|
+
- **`extract()`** — auto-strategy structured data: tries JSON-LD → `__NEXT_DATA__` → Nuxt → OpenGraph → microdata → text fallback, returns highest-confidence hit.
|
|
40
|
+
- **`click(ref)` / `type(ref, text)` / `submit(ref)`** — interaction. POST and GET forms supported. Checkboxes/radios tracked.
|
|
41
|
+
- **`cookies_set(...)`** — paste cookies from a real Chrome session to bypass bot detection (Cloudflare, PerimeterX, Datadome). Solve once, replay forever.
|
|
42
|
+
|
|
43
|
+
Full RPC reference, BlockMap shape, challenge detection, profile system, and architecture: [github.com/protostatis/unbrowser](https://github.com/protostatis/unbrowser).
|
|
44
|
+
|
|
45
|
+
## Honest limits
|
|
46
|
+
|
|
47
|
+
- Heavy framework SPAs (Ember/React) often don't auto-mount inside QuickJS even with `exec_scripts=True` — the watchdog ensures it returns, check `density.likely_js_filled` to decide whether to escalate.
|
|
48
|
+
- No screenshots (out of scope by design).
|
|
49
|
+
- Hardest-tier anti-bot (FingerprintJS Pro, Kasada, advanced Akamai BMP) needs the cookie handoff path. The binary detects and labels the challenge for you.
|
|
50
|
+
|
|
51
|
+
## License
|
|
52
|
+
|
|
53
|
+
Apache-2.0.
|
|
@@ -0,0 +1,64 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["hatchling>=1.18"]
|
|
3
|
+
build-backend = "hatchling.build"
|
|
4
|
+
|
|
5
|
+
[project]
|
|
6
|
+
# Distribution name `pyunbrowser` (not `unbrowser`) because PyPI's name
|
|
7
|
+
# moderation blocked `unbrowser` on typosquat-prevention grounds (it's too
|
|
8
|
+
# close to `browser`). The `py-` prefix is the established PyPI workaround
|
|
9
|
+
# (cf. python-dateutil → `from dateutil import ...`); the import name and
|
|
10
|
+
# binary stay `unbrowser` everywhere else.
|
|
11
|
+
name = "pyunbrowser"
|
|
12
|
+
version = "0.0.1"
|
|
13
|
+
description = "Web access for LLM agents. One static binary. No Chrome."
|
|
14
|
+
readme = "README.md"
|
|
15
|
+
license = { text = "Apache-2.0" }
|
|
16
|
+
requires-python = ">=3.10"
|
|
17
|
+
authors = [{ name = "protostatis" }]
|
|
18
|
+
keywords = ["browser", "scraping", "llm", "agent", "headless", "automation"]
|
|
19
|
+
classifiers = [
|
|
20
|
+
"Development Status :: 3 - Alpha",
|
|
21
|
+
"Intended Audience :: Developers",
|
|
22
|
+
"License :: OSI Approved :: Apache Software License",
|
|
23
|
+
"Operating System :: MacOS",
|
|
24
|
+
"Operating System :: POSIX :: Linux",
|
|
25
|
+
"Programming Language :: Python :: 3",
|
|
26
|
+
"Programming Language :: Python :: 3.10",
|
|
27
|
+
"Programming Language :: Python :: 3.11",
|
|
28
|
+
"Programming Language :: Python :: 3.12",
|
|
29
|
+
"Programming Language :: Python :: 3.13",
|
|
30
|
+
"Programming Language :: Rust",
|
|
31
|
+
"Topic :: Internet :: WWW/HTTP :: Browsers",
|
|
32
|
+
"Topic :: Software Development :: Libraries",
|
|
33
|
+
]
|
|
34
|
+
|
|
35
|
+
[project.urls]
|
|
36
|
+
Homepage = "https://github.com/protostatis/unbrowser"
|
|
37
|
+
Repository = "https://github.com/protostatis/unbrowser"
|
|
38
|
+
Issues = "https://github.com/protostatis/unbrowser/issues"
|
|
39
|
+
|
|
40
|
+
# The wheel ships the platform-specific native binary inside unbrowser/_bin/.
|
|
41
|
+
# CI builds the binary first (cargo build --release for each target), copies
|
|
42
|
+
# it into unbrowser/_bin/, then runs `python -m build --wheel` to produce a
|
|
43
|
+
# platform-tagged wheel. The sdist intentionally excludes _bin/ — a source
|
|
44
|
+
# distribution should be platform-neutral.
|
|
45
|
+
[tool.hatch.build.targets.wheel]
|
|
46
|
+
packages = ["unbrowser"]
|
|
47
|
+
# pure-python = false flips the wheel from py3-none-any to a platform-tagged
|
|
48
|
+
# wheel based on the host (macosx_*, linux_*, etc.). CI cross-compiles by
|
|
49
|
+
# post-processing the wheel name via `wheel tags --platform <target>`.
|
|
50
|
+
pure-python = false
|
|
51
|
+
# Even though _bin/* is gitignored (binary is a build artifact, never in git),
|
|
52
|
+
# hatchling's package auto-discovery picks up the binary if it's physically
|
|
53
|
+
# present at build time — exactly what we want. CI drops the per-platform
|
|
54
|
+
# binary into _bin/ before running `python -m build --wheel`. Sdist build
|
|
55
|
+
# explicitly excludes _bin/ (see [tool.hatch.build.targets.sdist] below)
|
|
56
|
+
# because a source distribution must be platform-neutral.
|
|
57
|
+
# Suppress hatchling's "did you mean to mark this as platform-specific?"
|
|
58
|
+
# nag — yes, we did, deliberately, for the bundled binary.
|
|
59
|
+
[tool.hatch.metadata]
|
|
60
|
+
allow-direct-references = true
|
|
61
|
+
|
|
62
|
+
[tool.hatch.build.targets.sdist]
|
|
63
|
+
include = ["unbrowser/", "README.md", "LICENSE"]
|
|
64
|
+
exclude = ["unbrowser/_bin/"]
|
|
@@ -0,0 +1,333 @@
|
|
|
1
|
+
"""unbrowser — Python client for the unbrowser binary.
|
|
2
|
+
|
|
3
|
+
`pip install unbrowser` ships the native binary inside the wheel for your
|
|
4
|
+
platform — there's nothing else to install. Use it like:
|
|
5
|
+
|
|
6
|
+
from unbrowser import Client
|
|
7
|
+
|
|
8
|
+
with Client() as ub:
|
|
9
|
+
r = ub.navigate("https://news.ycombinator.com")
|
|
10
|
+
for s in ub.query(".titleline > a")[:3]:
|
|
11
|
+
print(s["text"], s["attrs"]["href"])
|
|
12
|
+
|
|
13
|
+
For the `extract` / auto-strategy command, watchdog-bounded `exec_scripts`,
|
|
14
|
+
the cookie handoff for bot-walled sites, and the BlockMap shape: see the
|
|
15
|
+
project README at https://github.com/protostatis/unbrowser.
|
|
16
|
+
"""
|
|
17
|
+
|
|
18
|
+
from __future__ import annotations
|
|
19
|
+
|
|
20
|
+
import atexit
|
|
21
|
+
import json
|
|
22
|
+
import os
|
|
23
|
+
import shutil
|
|
24
|
+
import subprocess
|
|
25
|
+
import sys
|
|
26
|
+
from pathlib import Path
|
|
27
|
+
from typing import Any
|
|
28
|
+
from urllib.parse import quote_plus, urljoin, urlparse
|
|
29
|
+
|
|
30
|
+
__version__ = "0.0.1"
|
|
31
|
+
|
|
32
|
+
__all__ = ["Client", "UnbrowserError", "find_binary", "navigate", "__version__"]
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
class UnbrowserError(Exception):
|
|
36
|
+
"""Raised when the binary returns a JSON-RPC error or can't be spawned."""
|
|
37
|
+
|
|
38
|
+
|
|
39
|
+
def find_binary() -> str:
|
|
40
|
+
"""Resolve the unbrowser binary path.
|
|
41
|
+
|
|
42
|
+
Resolution order, most-explicit first:
|
|
43
|
+
|
|
44
|
+
1. ``UNBROWSER_BIN`` env var (overrides everything; right escape hatch
|
|
45
|
+
for testing a one-off build or vendored copy).
|
|
46
|
+
2. Bundled binary inside this package (the wheel ships one for your
|
|
47
|
+
platform — this is what end users hit).
|
|
48
|
+
3. ``unbrowser`` on ``$PATH`` (covers ``cargo install`` / ``brew install``
|
|
49
|
+
users who didn't install the wheel).
|
|
50
|
+
4. The local debug build at ``target/debug/unbrowser`` relative to the
|
|
51
|
+
repo root (developer convenience — only fires when running from a
|
|
52
|
+
checkout without an installed wheel).
|
|
53
|
+
|
|
54
|
+
Raises UnbrowserError with a helpful message if none of the above resolve.
|
|
55
|
+
"""
|
|
56
|
+
env = os.environ.get("UNBROWSER_BIN")
|
|
57
|
+
if env:
|
|
58
|
+
if not Path(env).is_file():
|
|
59
|
+
raise UnbrowserError(
|
|
60
|
+
f"UNBROWSER_BIN points to {env!r}, which doesn't exist"
|
|
61
|
+
)
|
|
62
|
+
return env
|
|
63
|
+
|
|
64
|
+
bundled = Path(__file__).parent / "_bin" / _binary_name()
|
|
65
|
+
if bundled.is_file():
|
|
66
|
+
return str(bundled)
|
|
67
|
+
|
|
68
|
+
on_path = shutil.which("unbrowser")
|
|
69
|
+
if on_path:
|
|
70
|
+
return on_path
|
|
71
|
+
|
|
72
|
+
# Dev fallback: target/debug/unbrowser two dirs up from this file
|
|
73
|
+
# (python/unbrowser/__init__.py -> python/unbrowser -> python -> repo root).
|
|
74
|
+
dev = Path(__file__).resolve().parents[2] / "target" / "debug" / "unbrowser"
|
|
75
|
+
if dev.is_file():
|
|
76
|
+
return str(dev)
|
|
77
|
+
|
|
78
|
+
raise UnbrowserError(
|
|
79
|
+
"Could not locate the unbrowser binary. Tried: $UNBROWSER_BIN, "
|
|
80
|
+
"package-bundled binary, $PATH, target/debug/unbrowser. "
|
|
81
|
+
"Install via `pip install unbrowser` (ships the binary), "
|
|
82
|
+
"`cargo install unbrowser`, or `brew install unbrowser`."
|
|
83
|
+
)
|
|
84
|
+
|
|
85
|
+
|
|
86
|
+
def _binary_name() -> str:
|
|
87
|
+
return "unbrowser.exe" if sys.platform == "win32" else "unbrowser"
|
|
88
|
+
|
|
89
|
+
|
|
90
|
+
class Client:
|
|
91
|
+
"""Synchronous JSON-RPC client for the unbrowser binary.
|
|
92
|
+
|
|
93
|
+
One subprocess per Client. The session (cookies, last_url, last_body)
|
|
94
|
+
persists across calls until close().
|
|
95
|
+
"""
|
|
96
|
+
|
|
97
|
+
def __init__(self, binary: str | None = None):
|
|
98
|
+
self._proc = subprocess.Popen(
|
|
99
|
+
[binary or find_binary()],
|
|
100
|
+
stdin=subprocess.PIPE,
|
|
101
|
+
stdout=subprocess.PIPE,
|
|
102
|
+
stderr=subprocess.DEVNULL,
|
|
103
|
+
text=True,
|
|
104
|
+
bufsize=1,
|
|
105
|
+
)
|
|
106
|
+
self._next_id = 0
|
|
107
|
+
self._closed = False
|
|
108
|
+
# Track the last successful navigate URL Python-side so make_absolute_url
|
|
109
|
+
# can resolve relative hrefs without round-tripping to the binary. Updated
|
|
110
|
+
# after every successful navigate / submit / click-with-follow.
|
|
111
|
+
self._last_url: str | None = None
|
|
112
|
+
# Belt-and-braces orphan prevention: if the interpreter exits before
|
|
113
|
+
# __exit__ runs (unhandled exception, sys.exit, heredoc-wrapped
|
|
114
|
+
# invocation killed mid-flight), atexit reaps the subprocess. The
|
|
115
|
+
# binary's own watchdog bounds JS execution; this covers the
|
|
116
|
+
# subprocess-lifecycle layer.
|
|
117
|
+
atexit.register(self._reap)
|
|
118
|
+
|
|
119
|
+
# ---- core RPC --------------------------------------------------------
|
|
120
|
+
|
|
121
|
+
def call(self, method: str, **params) -> Any:
|
|
122
|
+
"""Send one JSON-RPC request, return the result. Raises UnbrowserError on RPC error."""
|
|
123
|
+
self._next_id += 1
|
|
124
|
+
req = {"id": self._next_id, "method": method, "params": params}
|
|
125
|
+
assert self._proc.stdin is not None and self._proc.stdout is not None
|
|
126
|
+
self._proc.stdin.write(json.dumps(req) + "\n")
|
|
127
|
+
self._proc.stdin.flush()
|
|
128
|
+
line = self._proc.stdout.readline()
|
|
129
|
+
if not line:
|
|
130
|
+
raise UnbrowserError(f"binary closed stdout while waiting for {method}")
|
|
131
|
+
resp = json.loads(line)
|
|
132
|
+
if "error" in resp:
|
|
133
|
+
raise UnbrowserError(f"{method}: {resp['error']}")
|
|
134
|
+
return resp.get("result")
|
|
135
|
+
|
|
136
|
+
# ---- typed wrappers (don't add behavior; just discoverability) -------
|
|
137
|
+
|
|
138
|
+
def navigate(self, url: str, exec_scripts: bool = False) -> dict:
|
|
139
|
+
r = self.call("navigate", url=url, exec_scripts=exec_scripts)
|
|
140
|
+
if isinstance(r, dict) and r.get("url"):
|
|
141
|
+
self._last_url = r["url"]
|
|
142
|
+
return r
|
|
143
|
+
|
|
144
|
+
def query(self, selector: str) -> list[dict]:
|
|
145
|
+
return self.call("query", selector=selector)
|
|
146
|
+
|
|
147
|
+
def text(self, selector: str = "body") -> str | None:
|
|
148
|
+
return self.call("text", selector=selector)
|
|
149
|
+
|
|
150
|
+
def text_main(self) -> str | None:
|
|
151
|
+
"""textContent of the main content area (excludes header/nav/footer/aside)."""
|
|
152
|
+
return self.call("text_main")
|
|
153
|
+
|
|
154
|
+
def query_text(self, text: str, selector: str | None = None,
|
|
155
|
+
exact: bool = False, limit: int = 20) -> list[dict]:
|
|
156
|
+
"""Find elements by visible text content (chrome-stripped, deepest match).
|
|
157
|
+
|
|
158
|
+
Use when CSS selectors are unstable (React-rendered pages) but the
|
|
159
|
+
visible label is reliable, e.g. r.query_text('Sign in')[0].
|
|
160
|
+
"""
|
|
161
|
+
params: dict = {"text": text, "exact": exact, "limit": limit}
|
|
162
|
+
if selector is not None:
|
|
163
|
+
params["selector"] = selector
|
|
164
|
+
return self.call("query_text", **params)
|
|
165
|
+
|
|
166
|
+
def click(self, ref: str) -> dict:
|
|
167
|
+
r = self.call("click", ref=ref)
|
|
168
|
+
# click on <a href> auto-follows and returns navigate-shape result;
|
|
169
|
+
# update last_url so make_absolute_url stays accurate.
|
|
170
|
+
if isinstance(r, dict) and r.get("url"):
|
|
171
|
+
self._last_url = r["url"]
|
|
172
|
+
return r
|
|
173
|
+
|
|
174
|
+
def type(self, ref: str, text: str) -> dict:
|
|
175
|
+
return self.call("type", ref=ref, text=text)
|
|
176
|
+
|
|
177
|
+
def submit(self, ref: str) -> dict:
|
|
178
|
+
r = self.call("submit", ref=ref)
|
|
179
|
+
if isinstance(r, dict) and r.get("url"):
|
|
180
|
+
self._last_url = r["url"]
|
|
181
|
+
return r
|
|
182
|
+
|
|
183
|
+
def search(self, query: str, engine: str = "ddg") -> dict:
|
|
184
|
+
"""Search via the named engine; return the navigate result.
|
|
185
|
+
|
|
186
|
+
Engines:
|
|
187
|
+
ddg — DuckDuckGo HTML (default; reliable, returns SSR'd results
|
|
188
|
+
that the cheap path can extract directly via query()).
|
|
189
|
+
bing — Bing search (also works without exec_scripts).
|
|
190
|
+
|
|
191
|
+
Google is intentionally NOT supported via the cheap path — Google's
|
|
192
|
+
search page returns ~no useful HTML without JS, so it would silently
|
|
193
|
+
fail. Use the cookie-handoff escalation path or one of the supported
|
|
194
|
+
engines instead.
|
|
195
|
+
|
|
196
|
+
Use after navigate(), or as the first call: it kicks off its own
|
|
197
|
+
navigate. The returned dict is the same shape as Client.navigate.
|
|
198
|
+
"""
|
|
199
|
+
if engine == "ddg":
|
|
200
|
+
url = "https://duckduckgo.com/html/?q=" + quote_plus(query)
|
|
201
|
+
elif engine == "bing":
|
|
202
|
+
url = "https://www.bing.com/search?q=" + quote_plus(query)
|
|
203
|
+
else:
|
|
204
|
+
raise UnbrowserError(
|
|
205
|
+
f"unknown search engine '{engine}'. Supported: ddg, bing. "
|
|
206
|
+
"Google is intentionally unsupported via the cheap path."
|
|
207
|
+
)
|
|
208
|
+
return self.navigate(url)
|
|
209
|
+
|
|
210
|
+
def make_absolute_url(self, href: str) -> str:
|
|
211
|
+
"""Resolve a relative href against the current page URL.
|
|
212
|
+
|
|
213
|
+
Use after navigate to expand `<a href="/foo">` or `href="../bar"`
|
|
214
|
+
into a full URL. If `href` is already absolute (has scheme + host),
|
|
215
|
+
it's returned unchanged — preventing the double-prefix class of bug
|
|
216
|
+
you get from naive ``current_url + href`` concatenation.
|
|
217
|
+
|
|
218
|
+
Raises UnbrowserError if no page has been navigated yet.
|
|
219
|
+
"""
|
|
220
|
+
if not href:
|
|
221
|
+
raise UnbrowserError("empty href")
|
|
222
|
+
parsed = urlparse(href)
|
|
223
|
+
if parsed.scheme and parsed.netloc:
|
|
224
|
+
return href
|
|
225
|
+
if not self._last_url:
|
|
226
|
+
raise UnbrowserError("no current page — call navigate first")
|
|
227
|
+
return urljoin(self._last_url, href)
|
|
228
|
+
|
|
229
|
+
def blockmap(self) -> dict:
|
|
230
|
+
return self.call("blockmap")
|
|
231
|
+
|
|
232
|
+
def extract(self, strategy: str | None = None) -> dict:
|
|
233
|
+
"""Auto-strategy structured-data extraction.
|
|
234
|
+
|
|
235
|
+
Tries JSON-LD → __NEXT_DATA__ → Nuxt → OpenGraph/meta → microdata →
|
|
236
|
+
text_main fallback, returns the highest-confidence hit as
|
|
237
|
+
{strategy, confidence, data, tried}. Pass strategy='json_ld' (etc.)
|
|
238
|
+
to force a specific extractor.
|
|
239
|
+
"""
|
|
240
|
+
if strategy is None:
|
|
241
|
+
return self.call("extract")
|
|
242
|
+
return self.call("extract", strategy=strategy)
|
|
243
|
+
|
|
244
|
+
def settle(self, max_ms: int = 2000, max_iters: int = 50) -> dict:
|
|
245
|
+
"""Drain the JS event loop: microtasks + setTimeout/setInterval.
|
|
246
|
+
|
|
247
|
+
Returns when queue empty, max_ms elapses, or max_iters hit. Result:
|
|
248
|
+
{iters, elapsed_ms, microtasks_run, timers_fired, pending_timers,
|
|
249
|
+
pending_microtasks, timed_out}.
|
|
250
|
+
"""
|
|
251
|
+
return self.call("settle", max_ms=max_ms, max_iters=max_iters)
|
|
252
|
+
|
|
253
|
+
def body(self) -> str:
|
|
254
|
+
return self.call("body")
|
|
255
|
+
|
|
256
|
+
def eval(self, code: str) -> Any:
|
|
257
|
+
"""Run arbitrary JS in the session.
|
|
258
|
+
|
|
259
|
+
Returns the JS expression's result already JSON-decoded into a Python
|
|
260
|
+
value (dict / list / str / int / float / bool / None). DO NOT call
|
|
261
|
+
json.loads() on the return value — the wrapper already did. The Rust
|
|
262
|
+
side runs JSON.stringify on the JS value, the JSON-RPC framing parses
|
|
263
|
+
it once, and the result is the Python equivalent.
|
|
264
|
+
|
|
265
|
+
Errors surface the real JS exception name + message
|
|
266
|
+
(`TypeError: cannot read property 'foo' of null` etc.) so iteration
|
|
267
|
+
is fast.
|
|
268
|
+
"""
|
|
269
|
+
return self.call("eval", code=code)
|
|
270
|
+
|
|
271
|
+
def cookies_set(self, cookies: list[dict], url: str | None = None) -> dict:
|
|
272
|
+
if url is None:
|
|
273
|
+
return self.call("cookies_set", cookies=cookies)
|
|
274
|
+
return self.call("cookies_set", cookies=cookies, url=url)
|
|
275
|
+
|
|
276
|
+
def cookies_get(self) -> list[dict]:
|
|
277
|
+
return self.call("cookies_get")
|
|
278
|
+
|
|
279
|
+
def cookies_clear(self) -> dict:
|
|
280
|
+
return self.call("cookies_clear")
|
|
281
|
+
|
|
282
|
+
def close(self) -> None:
|
|
283
|
+
if self._closed:
|
|
284
|
+
return
|
|
285
|
+
self._closed = True
|
|
286
|
+
try:
|
|
287
|
+
self.call("close")
|
|
288
|
+
except (UnbrowserError, BrokenPipeError, OSError):
|
|
289
|
+
pass
|
|
290
|
+
self._reap()
|
|
291
|
+
|
|
292
|
+
def _reap(self) -> None:
|
|
293
|
+
# Idempotent: stdin EOF first (binary's reader returns None and the
|
|
294
|
+
# RPC loop exits cleanly), then escalate via terminate → kill if it
|
|
295
|
+
# doesn't respond. Always wait() at the end so we don't leave a
|
|
296
|
+
# zombie. Called from both close() and atexit.
|
|
297
|
+
if self._proc.poll() is not None:
|
|
298
|
+
return
|
|
299
|
+
try:
|
|
300
|
+
if self._proc.stdin and not self._proc.stdin.closed:
|
|
301
|
+
self._proc.stdin.close()
|
|
302
|
+
except (BrokenPipeError, OSError):
|
|
303
|
+
pass
|
|
304
|
+
try:
|
|
305
|
+
self._proc.wait(timeout=2)
|
|
306
|
+
return
|
|
307
|
+
except subprocess.TimeoutExpired:
|
|
308
|
+
pass
|
|
309
|
+
self._proc.terminate()
|
|
310
|
+
try:
|
|
311
|
+
self._proc.wait(timeout=2)
|
|
312
|
+
return
|
|
313
|
+
except subprocess.TimeoutExpired:
|
|
314
|
+
pass
|
|
315
|
+
self._proc.kill()
|
|
316
|
+
try:
|
|
317
|
+
self._proc.wait(timeout=2)
|
|
318
|
+
except subprocess.TimeoutExpired:
|
|
319
|
+
pass
|
|
320
|
+
|
|
321
|
+
# ---- context manager -------------------------------------------------
|
|
322
|
+
|
|
323
|
+
def __enter__(self) -> "Client":
|
|
324
|
+
return self
|
|
325
|
+
|
|
326
|
+
def __exit__(self, *exc) -> None:
|
|
327
|
+
self.close()
|
|
328
|
+
|
|
329
|
+
|
|
330
|
+
def navigate(url: str) -> dict:
|
|
331
|
+
"""One-shot: fetch a URL and return the navigate result. Closes immediately."""
|
|
332
|
+
with Client() as ub:
|
|
333
|
+
return ub.navigate(url)
|