webget-cli 0.7.2__tar.gz → 0.8.0__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.
- webget_cli-0.8.0/LICENSE +204 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/PKG-INFO +44 -13
- {webget_cli-0.7.2 → webget_cli-0.8.0}/README.md +40 -9
- {webget_cli-0.7.2 → webget_cli-0.8.0}/pyproject.toml +4 -4
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_adversarial_http.py +1 -1
- webget_cli-0.8.0/tests/test_extraction_markdown.py +97 -0
- webget_cli-0.8.0/tests/test_mcp_profile.py +115 -0
- webget_cli-0.8.0/tests/test_mcp_server.py +199 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_webget.py +41 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/webget_cli.egg-info/PKG-INFO +44 -13
- {webget_cli-0.7.2 → webget_cli-0.8.0}/webget_cli.egg-info/SOURCES.txt +2 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/webget_cli.egg-info/requires.txt +1 -1
- {webget_cli-0.7.2 → webget_cli-0.8.0}/webget_cli.py +51 -20
- {webget_cli-0.7.2 → webget_cli-0.8.0}/webget_mcp.py +46 -0
- webget_cli-0.7.2/LICENSE +0 -21
- webget_cli-0.7.2/tests/test_mcp_server.py +0 -102
- {webget_cli-0.7.2 → webget_cli-0.8.0}/setup.cfg +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_adversarial_auth.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_adversarial_cache.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_adversarial_concurrency.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_adversarial_mcp.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_adversarial_ssrf.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_auth_review.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_browser_ssrf.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_cache_review.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_concurrency_review.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_firecrawl_policy.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_integration_ladder.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_mcp_leak_review.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_mcp_smoke.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_security_review.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/tests/test_size_review.py +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/webget_cli.egg-info/dependency_links.txt +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/webget_cli.egg-info/entry_points.txt +0 -0
- {webget_cli-0.7.2 → webget_cli-0.8.0}/webget_cli.egg-info/top_level.txt +0 -0
webget_cli-0.8.0/LICENSE
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
|
|
4
|
+
Copyright (c) 2026 David Tarigan
|
|
5
|
+
|
|
6
|
+
http://www.apache.org/licenses/
|
|
7
|
+
|
|
8
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
9
|
+
|
|
10
|
+
1. Definitions.
|
|
11
|
+
|
|
12
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
13
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
14
|
+
|
|
15
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
16
|
+
the copyright owner that is granting the License.
|
|
17
|
+
|
|
18
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
19
|
+
other entities that control, are controlled by, or are under common
|
|
20
|
+
control with that entity. For the purposes of this definition,
|
|
21
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
22
|
+
direction or management of such entity, whether by contract or
|
|
23
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
24
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
25
|
+
|
|
26
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
27
|
+
exercising permissions granted by this License.
|
|
28
|
+
|
|
29
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
30
|
+
including but not limited to software source code, documentation
|
|
31
|
+
source, and configuration files.
|
|
32
|
+
|
|
33
|
+
"Object" form shall mean any form resulting from mechanical
|
|
34
|
+
transformation or translation of a Source form, including but
|
|
35
|
+
not limited to compiled object code, generated documentation,
|
|
36
|
+
and conversions to other media types.
|
|
37
|
+
|
|
38
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
39
|
+
Object form, made available under the License, as indicated by a
|
|
40
|
+
copyright notice that is included in or attached to the work
|
|
41
|
+
(an example is provided in the Appendix below).
|
|
42
|
+
|
|
43
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
44
|
+
form, that is based on (or derived from) the Work and for which the
|
|
45
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
46
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
47
|
+
of this License, Derivative Works shall not include works that remain
|
|
48
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
49
|
+
the Work and Derivative Works thereof.
|
|
50
|
+
|
|
51
|
+
"Contribution" shall mean any work of authorship, including
|
|
52
|
+
the original version of the Work and any modifications or additions
|
|
53
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
54
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
55
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
56
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
57
|
+
means any form of electronic, verbal, or written communication sent
|
|
58
|
+
to the Licensor or its representatives, including but not limited to
|
|
59
|
+
communication on electronic mailing lists, source code control systems,
|
|
60
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
61
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
62
|
+
excluding communication that is conspicuously marked or otherwise
|
|
63
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
64
|
+
|
|
65
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
66
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
67
|
+
subsequently incorporated within the Work.
|
|
68
|
+
|
|
69
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
70
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
71
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
72
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
73
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
74
|
+
Work and such Derivative Works in Source or Object form.
|
|
75
|
+
|
|
76
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
77
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
78
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
79
|
+
(except as stated in this section) patent license to make, have made,
|
|
80
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
81
|
+
where such license applies only to those patent claims licensable
|
|
82
|
+
by such Contributor that are necessarily infringed by their
|
|
83
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
84
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
85
|
+
institute patent litigation against any entity (including a
|
|
86
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
87
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
88
|
+
or contributory patent infringement, then any patent licenses
|
|
89
|
+
granted to You under this License for that Work shall terminate
|
|
90
|
+
as of the date such litigation is filed.
|
|
91
|
+
|
|
92
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
93
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
94
|
+
modifications, and in Source or Object form, provided that You
|
|
95
|
+
meet the following conditions:
|
|
96
|
+
|
|
97
|
+
(a) You must give any other recipients of the Work or
|
|
98
|
+
Derivative Works a copy of this License; and
|
|
99
|
+
|
|
100
|
+
(b) You must cause any modified files to carry prominent notices
|
|
101
|
+
stating that You changed the files; and
|
|
102
|
+
|
|
103
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
104
|
+
that You distribute, all copyright, patent, trademark, and
|
|
105
|
+
attribution notices from the Source form of the Work,
|
|
106
|
+
excluding those notices that do not pertain to any part of
|
|
107
|
+
the Derivative Works; and
|
|
108
|
+
|
|
109
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
110
|
+
distribution, then any Derivative Works that You distribute must
|
|
111
|
+
include a readable copy of the attribution notices contained
|
|
112
|
+
within such NOTICE file, excluding those notices that do not
|
|
113
|
+
pertain to any part of the Derivative Works, in at least one
|
|
114
|
+
of the following places: within a NOTICE text file distributed
|
|
115
|
+
as part of the Derivative Works; within the Source form or
|
|
116
|
+
documentation, if provided along with the Derivative Works; or,
|
|
117
|
+
within a display generated by the Derivative Works, if and
|
|
118
|
+
wherever such third-party notices normally appear. The contents
|
|
119
|
+
of the NOTICE file are for informational purposes only and
|
|
120
|
+
do not modify the License. You may add Your own attribution
|
|
121
|
+
notices within Derivative Works that You distribute, alongside
|
|
122
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
123
|
+
that such additional attribution notices cannot be construed
|
|
124
|
+
as modifying the License.
|
|
125
|
+
|
|
126
|
+
You may add Your own copyright statement to Your modifications and
|
|
127
|
+
may provide additional or different license terms and conditions
|
|
128
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
129
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
130
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
131
|
+
the conditions stated in this License.
|
|
132
|
+
|
|
133
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
134
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
135
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
136
|
+
this License, without any additional terms or conditions.
|
|
137
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
138
|
+
the terms of any separate license agreement you may have executed
|
|
139
|
+
with Licensor regarding such Contributions.
|
|
140
|
+
|
|
141
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
142
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
143
|
+
except as required for reasonable and customary use in describing the
|
|
144
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
145
|
+
|
|
146
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
147
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
148
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
149
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
150
|
+
implied, including, without limitation, any warranties or conditions
|
|
151
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
152
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
153
|
+
appropriateness of using or redistributing the Work and assume any
|
|
154
|
+
risks associated with Your exercise of permissions under this License.
|
|
155
|
+
|
|
156
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
157
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
158
|
+
unless required by applicable law (such as deliberate and grossly
|
|
159
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
160
|
+
liable to You for damages, including any direct, indirect, special,
|
|
161
|
+
incidental, or consequential damages of any character arising as a
|
|
162
|
+
result of this License or out of the use or inability to use the
|
|
163
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
164
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
165
|
+
other commercial damages or losses), even if such Contributor
|
|
166
|
+
has been advised of the possibility of such damages.
|
|
167
|
+
|
|
168
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
169
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
170
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
171
|
+
or other liability obligations and/or rights consistent with this
|
|
172
|
+
License. However, in accepting such obligations, You may act only
|
|
173
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
174
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
175
|
+
defend, and hold each Contributor harmless for any liability
|
|
176
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
177
|
+
of your accepting any such warranty or additional liability.
|
|
178
|
+
|
|
179
|
+
END OF TERMS AND CONDITIONS
|
|
180
|
+
|
|
181
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
182
|
+
|
|
183
|
+
To apply the Apache License to your work, attach the following
|
|
184
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
185
|
+
replaced with your own identifying information. (Don't include
|
|
186
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
187
|
+
comment syntax for the file format. We also recommend that a
|
|
188
|
+
file or class name and description of purpose be included on the
|
|
189
|
+
same "printed page" as the copyright notice for easier
|
|
190
|
+
identification within third-party archives.
|
|
191
|
+
|
|
192
|
+
Copyright [yyyy] [name of copyright owner]
|
|
193
|
+
|
|
194
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
195
|
+
you may not use this file except in compliance with the License.
|
|
196
|
+
You may obtain a copy of the License at
|
|
197
|
+
|
|
198
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
199
|
+
|
|
200
|
+
Unless required by applicable law or agreed to in writing, software
|
|
201
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
202
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
203
|
+
See the License for the specific language governing permissions and
|
|
204
|
+
limitations under the License.
|
|
@@ -1,16 +1,16 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: webget-cli
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.8.0
|
|
4
4
|
Summary: Local search + scrape CLI with an HTTP fast path, optional browser fallback, and authenticated session profiles. Zero API keys.
|
|
5
5
|
Author-email: David Tarigan <tarigansdavid@gmail.com>
|
|
6
|
-
License:
|
|
6
|
+
License: Apache-2.0
|
|
7
7
|
Project-URL: Homepage, https://github.com/DavidPandleton/webget
|
|
8
8
|
Project-URL: Repository, https://github.com/DavidPandleton/webget
|
|
9
9
|
Project-URL: Changelog, https://github.com/DavidPandleton/webget/blob/main/CHANGELOG.md
|
|
10
10
|
Keywords: scraping,crawling,cli,search,duckduckgo,http
|
|
11
11
|
Classifier: Environment :: Console
|
|
12
12
|
Classifier: Intended Audience :: Developers
|
|
13
|
-
Classifier: License :: OSI Approved ::
|
|
13
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
14
14
|
Classifier: Programming Language :: Python :: 3
|
|
15
15
|
Classifier: Programming Language :: Python :: 3.11
|
|
16
16
|
Classifier: Programming Language :: Python :: 3.12
|
|
@@ -22,7 +22,7 @@ License-File: LICENSE
|
|
|
22
22
|
Requires-Dist: ddgs
|
|
23
23
|
Requires-Dist: httpx
|
|
24
24
|
Requires-Dist: trafilatura
|
|
25
|
-
Requires-Dist:
|
|
25
|
+
Requires-Dist: markdownify
|
|
26
26
|
Provides-Extra: browser
|
|
27
27
|
Requires-Dist: crawl4ai>=0.9; extra == "browser"
|
|
28
28
|
Provides-Extra: mcp
|
|
@@ -43,10 +43,10 @@ through a strategy ladder (HTTP fast path → Crawl4AI browser → optional
|
|
|
43
43
|
Firecrawl), and reports *provenance* - where the content came from and whether
|
|
44
44
|
the session that fetched it can be trusted.
|
|
45
45
|
|
|
46
|
-
[](https://pypi.org/project/webget-cli/)
|
|
46
|
+
[](https://github.com/DavidPandleton/webget/actions)
|
|
47
|
+
[](https://pypi.org/project/webget-cli/)
|
|
48
48
|
[](https://www.python.org/)
|
|
49
|
-
[](LICENSE)
|
|
50
50
|
[](https://github.com/DavidPandleton/webget)
|
|
51
51
|
|
|
52
52
|
</div>
|
|
@@ -59,7 +59,7 @@ Most scraping tools assume one engine. webget assumes the web is messy:
|
|
|
59
59
|
|
|
60
60
|
```text
|
|
61
61
|
FETCH_AUTO
|
|
62
|
-
├── http → fast path (httpx + trafilatura/
|
|
62
|
+
├── http → fast path (httpx + trafilatura/markdownify), no browser
|
|
63
63
|
├── crawl4ai → Playwright browser, JS rendering, persistent auth sessions
|
|
64
64
|
└── firecrawl → optional cloud fallback (needs WEBGET_FIRECRAWL_KEY)
|
|
65
65
|
```
|
|
@@ -86,7 +86,10 @@ pip install webget-cli
|
|
|
86
86
|
pip install "webget-cli[browser]"
|
|
87
87
|
|
|
88
88
|
# uv tool - isolated executable on your PATH
|
|
89
|
-
|
|
89
|
+
# (single spec with extras: do NOT use `--with "webget-cli[browser]"`,
|
|
90
|
+
# uv re-resolves the same package there and can clobber the main install
|
|
91
|
+
# with a stale version)
|
|
92
|
+
uv tool install "webget-cli[browser,mcp]"
|
|
90
93
|
```
|
|
91
94
|
|
|
92
95
|
After install, `webget` is available as a command:
|
|
@@ -220,6 +223,8 @@ without API keys:
|
|
|
220
223
|
|
|
221
224
|
```bash
|
|
222
225
|
pip install "webget-cli[mcp]"
|
|
226
|
+
# or as a uv tool with the MCP server + browser fallback:
|
|
227
|
+
uv tool install "webget-cli[browser,mcp]"
|
|
223
228
|
```
|
|
224
229
|
|
|
225
230
|
Register as a local MCP server in opencode:
|
|
@@ -239,9 +244,31 @@ Register as a local MCP server in opencode:
|
|
|
239
244
|
Then prompt with `use webget` for search and scrape tasks. Run the server
|
|
240
245
|
standalone with `webget-mcp` (stdio transport) or `python webget_mcp.py`.
|
|
241
246
|
|
|
242
|
-
|
|
243
|
-
|
|
244
|
-
|
|
247
|
+
### Authenticated sessions (profiles)
|
|
248
|
+
|
|
249
|
+
MCP tools can use locally stored login sessions. Create one first with the
|
|
250
|
+
CLI:
|
|
251
|
+
|
|
252
|
+
```bash
|
|
253
|
+
webget login https://portal.example.com --profile portal
|
|
254
|
+
```
|
|
255
|
+
|
|
256
|
+
Then the agent can discover sessions and fetch authenticated pages:
|
|
257
|
+
|
|
258
|
+
- `list_profiles` - lists available sessions (name, last used, size,
|
|
259
|
+
status). Cookie values are never returned.
|
|
260
|
+
- `fetch(..., profile="portal")` / `search_fetch(..., profile="portal")` -
|
|
261
|
+
scrape using that session.
|
|
262
|
+
|
|
263
|
+
```text
|
|
264
|
+
agent: "check my portal for new announcements"
|
|
265
|
+
1. list_profiles -> portal (authenticated)
|
|
266
|
+
2. fetch(url, profile="portal")
|
|
267
|
+
```
|
|
268
|
+
|
|
269
|
+
Invalid profile names and unknown profiles are hard errors (no silent
|
|
270
|
+
anonymous fallback). Sessions are local to the machine running the MCP
|
|
271
|
+
server.
|
|
245
272
|
|
|
246
273
|
## Development
|
|
247
274
|
|
|
@@ -262,4 +289,8 @@ Found a bug or have an idea? [Open an issue](https://github.com/DavidPandleton/w
|
|
|
262
289
|
|
|
263
290
|
## License
|
|
264
291
|
|
|
265
|
-
[
|
|
292
|
+
[Apache-2.0](LICENSE)
|
|
293
|
+
|
|
294
|
+
Note: dependency licenses are separate (e.g. certifi MPL-2.0, tqdm
|
|
295
|
+
MPL-2.0 AND MIT, scipy's bundled GCC-runtime GPL-with-exception via the
|
|
296
|
+
browser extra); each dependency keeps its own license/notice.
|
|
@@ -9,10 +9,10 @@ through a strategy ladder (HTTP fast path → Crawl4AI browser → optional
|
|
|
9
9
|
Firecrawl), and reports *provenance* - where the content came from and whether
|
|
10
10
|
the session that fetched it can be trusted.
|
|
11
11
|
|
|
12
|
-
[](https://pypi.org/project/webget-cli/)
|
|
12
|
+
[](https://github.com/DavidPandleton/webget/actions)
|
|
13
|
+
[](https://pypi.org/project/webget-cli/)
|
|
14
14
|
[](https://www.python.org/)
|
|
15
|
-
[](LICENSE)
|
|
16
16
|
[](https://github.com/DavidPandleton/webget)
|
|
17
17
|
|
|
18
18
|
</div>
|
|
@@ -25,7 +25,7 @@ Most scraping tools assume one engine. webget assumes the web is messy:
|
|
|
25
25
|
|
|
26
26
|
```text
|
|
27
27
|
FETCH_AUTO
|
|
28
|
-
├── http → fast path (httpx + trafilatura/
|
|
28
|
+
├── http → fast path (httpx + trafilatura/markdownify), no browser
|
|
29
29
|
├── crawl4ai → Playwright browser, JS rendering, persistent auth sessions
|
|
30
30
|
└── firecrawl → optional cloud fallback (needs WEBGET_FIRECRAWL_KEY)
|
|
31
31
|
```
|
|
@@ -52,7 +52,10 @@ pip install webget-cli
|
|
|
52
52
|
pip install "webget-cli[browser]"
|
|
53
53
|
|
|
54
54
|
# uv tool - isolated executable on your PATH
|
|
55
|
-
|
|
55
|
+
# (single spec with extras: do NOT use `--with "webget-cli[browser]"`,
|
|
56
|
+
# uv re-resolves the same package there and can clobber the main install
|
|
57
|
+
# with a stale version)
|
|
58
|
+
uv tool install "webget-cli[browser,mcp]"
|
|
56
59
|
```
|
|
57
60
|
|
|
58
61
|
After install, `webget` is available as a command:
|
|
@@ -186,6 +189,8 @@ without API keys:
|
|
|
186
189
|
|
|
187
190
|
```bash
|
|
188
191
|
pip install "webget-cli[mcp]"
|
|
192
|
+
# or as a uv tool with the MCP server + browser fallback:
|
|
193
|
+
uv tool install "webget-cli[browser,mcp]"
|
|
189
194
|
```
|
|
190
195
|
|
|
191
196
|
Register as a local MCP server in opencode:
|
|
@@ -205,9 +210,31 @@ Register as a local MCP server in opencode:
|
|
|
205
210
|
Then prompt with `use webget` for search and scrape tasks. Run the server
|
|
206
211
|
standalone with `webget-mcp` (stdio transport) or `python webget_mcp.py`.
|
|
207
212
|
|
|
208
|
-
|
|
209
|
-
|
|
210
|
-
|
|
213
|
+
### Authenticated sessions (profiles)
|
|
214
|
+
|
|
215
|
+
MCP tools can use locally stored login sessions. Create one first with the
|
|
216
|
+
CLI:
|
|
217
|
+
|
|
218
|
+
```bash
|
|
219
|
+
webget login https://portal.example.com --profile portal
|
|
220
|
+
```
|
|
221
|
+
|
|
222
|
+
Then the agent can discover sessions and fetch authenticated pages:
|
|
223
|
+
|
|
224
|
+
- `list_profiles` - lists available sessions (name, last used, size,
|
|
225
|
+
status). Cookie values are never returned.
|
|
226
|
+
- `fetch(..., profile="portal")` / `search_fetch(..., profile="portal")` -
|
|
227
|
+
scrape using that session.
|
|
228
|
+
|
|
229
|
+
```text
|
|
230
|
+
agent: "check my portal for new announcements"
|
|
231
|
+
1. list_profiles -> portal (authenticated)
|
|
232
|
+
2. fetch(url, profile="portal")
|
|
233
|
+
```
|
|
234
|
+
|
|
235
|
+
Invalid profile names and unknown profiles are hard errors (no silent
|
|
236
|
+
anonymous fallback). Sessions are local to the machine running the MCP
|
|
237
|
+
server.
|
|
211
238
|
|
|
212
239
|
## Development
|
|
213
240
|
|
|
@@ -228,4 +255,8 @@ Found a bug or have an idea? [Open an issue](https://github.com/DavidPandleton/w
|
|
|
228
255
|
|
|
229
256
|
## License
|
|
230
257
|
|
|
231
|
-
[
|
|
258
|
+
[Apache-2.0](LICENSE)
|
|
259
|
+
|
|
260
|
+
Note: dependency licenses are separate (e.g. certifi MPL-2.0, tqdm
|
|
261
|
+
MPL-2.0 AND MIT, scipy's bundled GCC-runtime GPL-with-exception via the
|
|
262
|
+
browser extra); each dependency keeps its own license/notice.
|
|
@@ -4,17 +4,17 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "webget-cli"
|
|
7
|
-
version = "0.
|
|
7
|
+
version = "0.8.0"
|
|
8
8
|
description = "Local search + scrape CLI with an HTTP fast path, optional browser fallback, and authenticated session profiles. Zero API keys."
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
requires-python = ">=3.11"
|
|
11
|
-
license = { text = "
|
|
11
|
+
license = { text = "Apache-2.0" }
|
|
12
12
|
authors = [{ name = "David Tarigan", email = "tarigansdavid@gmail.com" }]
|
|
13
13
|
keywords = ["scraping", "crawling", "cli", "search", "duckduckgo", "http"]
|
|
14
14
|
classifiers = [
|
|
15
15
|
"Environment :: Console",
|
|
16
16
|
"Intended Audience :: Developers",
|
|
17
|
-
"License :: OSI Approved ::
|
|
17
|
+
"License :: OSI Approved :: Apache Software License",
|
|
18
18
|
"Programming Language :: Python :: 3",
|
|
19
19
|
"Programming Language :: Python :: 3.11",
|
|
20
20
|
"Programming Language :: Python :: 3.12",
|
|
@@ -25,7 +25,7 @@ dependencies = [
|
|
|
25
25
|
"ddgs",
|
|
26
26
|
"httpx",
|
|
27
27
|
"trafilatura",
|
|
28
|
-
"
|
|
28
|
+
"markdownify",
|
|
29
29
|
]
|
|
30
30
|
|
|
31
31
|
[project.urls]
|
|
@@ -126,7 +126,7 @@ class TestResponseBodies:
|
|
|
126
126
|
def test_malformed_html(self, fresh_cache):
|
|
127
127
|
server = fresh_cache
|
|
128
128
|
res = asyncio.run(_fetch(server.url("/malformed")))
|
|
129
|
-
#
|
|
129
|
+
# markdownify usually still extracts something; at minimum no crash
|
|
130
130
|
assert "status" in _one(res)
|
|
131
131
|
|
|
132
132
|
def test_binary_response(self, fresh_cache):
|
|
@@ -0,0 +1,97 @@
|
|
|
1
|
+
"""Extraction tests: trafilatura first, markdownify fallback (0.7.3).
|
|
2
|
+
|
|
3
|
+
0.7.3 swapped the HTML-to-Markdown fallback from html2text (GPL-3.0) to
|
|
4
|
+
markdownify (MIT) for license hygiene. These tests pin the SEMANTIC
|
|
5
|
+
behavior of the fallback: headings, paragraphs, links, lists, code,
|
|
6
|
+
malformed input, and the trafilatura-fail / too-thin fallback triggers.
|
|
7
|
+
Output does not need to be byte-identical to html2text, but links and
|
|
8
|
+
structure must be preserved.
|
|
9
|
+
"""
|
|
10
|
+
|
|
11
|
+
import webget_cli as webget
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
def _extract(html):
|
|
15
|
+
return webget._extract_markdown(html)
|
|
16
|
+
|
|
17
|
+
|
|
18
|
+
def _force_fallback(monkeypatch, result=None):
|
|
19
|
+
"""Make trafilatura fail (or return a too-thin result) so the
|
|
20
|
+
markdownify fallback path runs."""
|
|
21
|
+
import trafilatura
|
|
22
|
+
|
|
23
|
+
monkeypatch.setattr(trafilatura, "extract", lambda *a, **k: result)
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
class TestMarkdownifyFallback:
|
|
27
|
+
BODY = "<p>" + "x" * 60 + "</p>" # keep fixture output above the 50-char threshold
|
|
28
|
+
|
|
29
|
+
def test_heading(self, monkeypatch):
|
|
30
|
+
_force_fallback(monkeypatch)
|
|
31
|
+
out = _extract("<h1>Big Title</h1>" + self.BODY)
|
|
32
|
+
assert "# Big Title" in out
|
|
33
|
+
|
|
34
|
+
def test_paragraph_and_bold(self, monkeypatch):
|
|
35
|
+
_force_fallback(monkeypatch)
|
|
36
|
+
out = _extract("<p>Hello <b>world</b>!</p>" + self.BODY)
|
|
37
|
+
assert "Hello **world**!" in out
|
|
38
|
+
|
|
39
|
+
def test_link_preserved(self, monkeypatch):
|
|
40
|
+
# THE critical semantic: links must survive (html2text -> markdownify).
|
|
41
|
+
_force_fallback(monkeypatch)
|
|
42
|
+
out = _extract('<p><a href="https://example.com">Example</a></p>' + self.BODY)
|
|
43
|
+
assert "[Example](https://example.com)" in out
|
|
44
|
+
|
|
45
|
+
def test_list_items_preserved(self, monkeypatch):
|
|
46
|
+
_force_fallback(monkeypatch)
|
|
47
|
+
out = _extract("<ul><li>alpha</li><li>beta</li></ul>" + self.BODY)
|
|
48
|
+
assert "alpha" in out and "beta" in out
|
|
49
|
+
assert "- alpha" in out or "* alpha" in out # bullet marker present
|
|
50
|
+
|
|
51
|
+
def test_code_block_preserved(self, monkeypatch):
|
|
52
|
+
_force_fallback(monkeypatch)
|
|
53
|
+
out = _extract("<pre><code>def f():\n return 1</code></pre>" + self.BODY)
|
|
54
|
+
assert "def f():" in out and "return 1" in out
|
|
55
|
+
|
|
56
|
+
def test_table_cells_preserved(self, monkeypatch):
|
|
57
|
+
_force_fallback(monkeypatch)
|
|
58
|
+
out = _extract("<table><tr><td>cell1</td><td>cell2</td></tr></table>" + self.BODY)
|
|
59
|
+
assert "cell1" in out and "cell2" in out
|
|
60
|
+
|
|
61
|
+
def test_malformed_html_no_crash(self, monkeypatch):
|
|
62
|
+
_force_fallback(monkeypatch)
|
|
63
|
+
out = _extract("<div><p>unclosed <b>bold</div>")
|
|
64
|
+
assert isinstance(out, str) # never raises, never non-str
|
|
65
|
+
|
|
66
|
+
def test_empty_html_returns_empty(self, monkeypatch):
|
|
67
|
+
_force_fallback(monkeypatch)
|
|
68
|
+
assert _extract("") == ""
|
|
69
|
+
assert _extract("<html><head><title>x</title></head><body></body></html>") == ""
|
|
70
|
+
|
|
71
|
+
def test_trafilatura_failure_falls_back(self, monkeypatch):
|
|
72
|
+
# trafilatura raises -> markdownify must still produce output
|
|
73
|
+
import trafilatura
|
|
74
|
+
|
|
75
|
+
def boom(*a, **k):
|
|
76
|
+
raise RuntimeError("extraction backend down")
|
|
77
|
+
|
|
78
|
+
monkeypatch.setattr(trafilatura, "extract", boom)
|
|
79
|
+
html = '<p>Some <a href="https://example.com">linked</a> content here.</p>' + self.BODY
|
|
80
|
+
out = _extract(html)
|
|
81
|
+
assert out != ""
|
|
82
|
+
assert "linked" in out
|
|
83
|
+
|
|
84
|
+
def test_thin_trafilatura_result_falls_back(self, monkeypatch):
|
|
85
|
+
# trafilatura returns <100 chars -> markdownify fallback runs
|
|
86
|
+
_force_fallback(monkeypatch, result="too short")
|
|
87
|
+
html = '<p>Long enough content <a href="https://example.com">with link</a></p>' + self.BODY
|
|
88
|
+
out = _extract(html)
|
|
89
|
+
assert "with link" in out
|
|
90
|
+
assert out != "too short"
|
|
91
|
+
|
|
92
|
+
|
|
93
|
+
class TestTrafilaturaPrimary:
|
|
94
|
+
def test_trafilatura_wins_when_rich(self):
|
|
95
|
+
body = "<p>" + "The quick brown fox jumps over the lazy dog. " * 8 + "</p>"
|
|
96
|
+
out = _extract(f"<html><body><h1>Doc</h1>{body}</body></html>")
|
|
97
|
+
assert "quick brown fox" in out
|
|
@@ -0,0 +1,115 @@
|
|
|
1
|
+
"""Integration: MCP fetch with a real profile uses the stored session.
|
|
2
|
+
|
|
3
|
+
A cookie-gated local server returns 200 only when the request carries the
|
|
4
|
+
session cookie from a profile's storage_state.json:
|
|
5
|
+
- fetch(profile="testp") -> success (session used)
|
|
6
|
+
- fetch() (anonymous) -> blocked/login_required (no session)
|
|
7
|
+
|
|
8
|
+
Spawns webget_mcp.py as a stdio subprocess with WEBGET_PROFILE_DIR pointing
|
|
9
|
+
at a temp profile root and WEBGET_ALLOW_PRIVATE=1 (the test server lives on
|
|
10
|
+
127.0.0.1, which the SSRF guard blocks by default).
|
|
11
|
+
"""
|
|
12
|
+
|
|
13
|
+
import asyncio
|
|
14
|
+
import json
|
|
15
|
+
import os
|
|
16
|
+
import sys
|
|
17
|
+
from pathlib import Path
|
|
18
|
+
|
|
19
|
+
from mcp import ClientSession, StdioServerParameters
|
|
20
|
+
from mcp.client.stdio import stdio_client
|
|
21
|
+
|
|
22
|
+
ROOT = Path(__file__).resolve().parent.parent
|
|
23
|
+
MCP = ROOT / "webget_mcp.py"
|
|
24
|
+
sys.path.insert(0, str(ROOT))
|
|
25
|
+
|
|
26
|
+
from tests.http_server import TestServer
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
def _spawn(profile_root):
|
|
30
|
+
env = {
|
|
31
|
+
**os.environ,
|
|
32
|
+
"WEBGET_PROFILE_DIR": str(profile_root),
|
|
33
|
+
"WEBGET_ALLOW_PRIVATE": "1",
|
|
34
|
+
}
|
|
35
|
+
return StdioServerParameters(command=sys.executable, args=[str(MCP)], env=env)
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
def _make_profile(root, name):
|
|
39
|
+
d = root / name
|
|
40
|
+
(d / "Default").mkdir(parents=True)
|
|
41
|
+
(d / "storage_state.json").write_text(
|
|
42
|
+
json.dumps(
|
|
43
|
+
{
|
|
44
|
+
"cookies": [
|
|
45
|
+
{
|
|
46
|
+
"name": "s",
|
|
47
|
+
"value": "1",
|
|
48
|
+
"domain": "127.0.0.1",
|
|
49
|
+
"path": "/",
|
|
50
|
+
"expires": 9999999999,
|
|
51
|
+
}
|
|
52
|
+
]
|
|
53
|
+
}
|
|
54
|
+
)
|
|
55
|
+
)
|
|
56
|
+
|
|
57
|
+
|
|
58
|
+
def test_mcp_fetch_with_profile_uses_session(tmp_path):
|
|
59
|
+
server = TestServer().start()
|
|
60
|
+
try:
|
|
61
|
+
root = tmp_path / "profiles"
|
|
62
|
+
_make_profile(root, "testp")
|
|
63
|
+
url = server.url("/cookie-gated")
|
|
64
|
+
|
|
65
|
+
async def run():
|
|
66
|
+
async with (
|
|
67
|
+
stdio_client(_spawn(root)) as (read, write),
|
|
68
|
+
ClientSession(read, write) as session,
|
|
69
|
+
):
|
|
70
|
+
await session.initialize()
|
|
71
|
+
ok = await session.call_tool(
|
|
72
|
+
"fetch", {"url": url, "strategy": "http", "no_cache": True, "profile": "testp"}
|
|
73
|
+
)
|
|
74
|
+
anon = await session.call_tool(
|
|
75
|
+
"fetch", {"url": url, "strategy": "http", "no_cache": True}
|
|
76
|
+
)
|
|
77
|
+
return ok, anon
|
|
78
|
+
|
|
79
|
+
ok, anon = asyncio.run(asyncio.wait_for(run(), timeout=60))
|
|
80
|
+
ok_text = ok.content[0].text if ok.content else ""
|
|
81
|
+
anon_text = anon.content[0].text if anon.content else ""
|
|
82
|
+
assert not ok.isError, ok_text
|
|
83
|
+
assert '"status":"success"' in ok_text, ok_text
|
|
84
|
+
assert "you are authenticated" in ok_text, ok_text
|
|
85
|
+
assert '"authenticated":true' in ok_text, ok_text # session was used
|
|
86
|
+
# anonymous fetch must NOT succeed on the gated page
|
|
87
|
+
assert ok_text != anon_text
|
|
88
|
+
assert '"status":"success"' not in anon_text, f"anonymous fetch leaked: {anon_text}"
|
|
89
|
+
finally:
|
|
90
|
+
server.stop()
|
|
91
|
+
|
|
92
|
+
|
|
93
|
+
def test_mcp_fetch_unknown_profile_is_hard_error(tmp_path):
|
|
94
|
+
"""Even with a profile root, a name that does not exist is an error
|
|
95
|
+
(never a silent anonymous fallback)."""
|
|
96
|
+
|
|
97
|
+
async def run():
|
|
98
|
+
env = {**os.environ, "WEBGET_PROFILE_DIR": str(tmp_path / "profiles")}
|
|
99
|
+
params = StdioServerParameters(command=sys.executable, args=[str(MCP)], env=env)
|
|
100
|
+
async with stdio_client(params) as (read, write), ClientSession(read, write) as session:
|
|
101
|
+
await session.initialize()
|
|
102
|
+
res = await session.call_tool(
|
|
103
|
+
"fetch", {"url": "https://example.com", "profile": "ghost", "no_cache": True}
|
|
104
|
+
)
|
|
105
|
+
return res
|
|
106
|
+
|
|
107
|
+
res = asyncio.run(asyncio.wait_for(run(), timeout=60))
|
|
108
|
+
assert not res.isError
|
|
109
|
+
assert "profile 'ghost' not found" in res.content[0].text
|
|
110
|
+
|
|
111
|
+
|
|
112
|
+
if __name__ == "__main__":
|
|
113
|
+
import pytest
|
|
114
|
+
|
|
115
|
+
sys.exit(pytest.main([__file__, "-v"]))
|