c2pa-scanner 0.7.1__tar.gz

c2pa_scanner-0.7.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or Derivative
+          Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and do
+          not modify the License. You may add Your own attribution notices
+          within Derivative Works that You distribute, alongside or as an
+          addendum to the NOTICE text from the Work, provided that such
+          additional attribution notices cannot be construed as modifying
+          the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Michael Blaess
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

c2pa_scanner-0.7.1/PKG-INFO

@@ -0,0 +1,283 @@
+Metadata-Version: 2.4
+Name: c2pa-scanner
+Version: 0.7.1
+Summary: Detect C2PA provenance / AI-generated images in website sitemaps (EU AI Act Art. 50)
+Author: Michael Blaess
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/michaelblaess/c2pa-scanner
+Project-URL: Repository, https://github.com/michaelblaess/c2pa-scanner
+Project-URL: Issues, https://github.com/michaelblaess/c2pa-scanner/issues
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Internet :: WWW/HTTP :: Site Management
+Classifier: Topic :: Multimedia :: Graphics
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: c2pa-python>=0.36
+Requires-Dist: Pillow>=10.0
+Requires-Dist: cryptography>=42.0
+Requires-Dist: httpx>=0.25
+Requires-Dist: playwright>=1.40
+Requires-Dist: textual>=0.80
+Requires-Dist: rich>=13.0
+Requires-Dist: textual-image[textual]>=0.12.0
+Requires-Dist: textual-fspicker>=1.0
+Requires-Dist: textual-themes[textual]>=0.15.1
+Requires-Dist: textual-widgets>=0.32.1
+Requires-Dist: textual-slider>=0.2.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: mypy>=1.8; extra == "dev"
+Requires-Dist: ruff>=0.6; extra == "dev"
+Requires-Dist: poethepoet>=0.27; extra == "dev"
+Dynamic: license-file
+
+# c2pa-scanner
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/michaelblaess/c2pa-scanner/0f5bc531cf45dc972c60fc1313adf01a209f72a8/docs/flags/gb.svg" height="13" alt=""> <b>English</b> &middot;
+  <img src="https://raw.githubusercontent.com/michaelblaess/c2pa-scanner/0f5bc531cf45dc972c60fc1313adf01a209f72a8/docs/flags/de.svg" height="13" alt=""> <a href="https://github.com/michaelblaess/c2pa-scanner/blob/0f5bc531cf45dc972c60fc1313adf01a209f72a8/README.de.md">Deutsch</a>
+</p>
+
+---
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/michaelblaess/c2pa-scanner/0f5bc531cf45dc972c60fc1313adf01a209f72a8/docs/banner.jpg" alt="c2pa-scanner - images labeled as AI-generated, AI-edited or verified origin" width="100%">
+  <br>
+  <sub>This banner is AI-generated (Google Gemini) and carries its signed C2PA manifest -
+  c2pa-scanner classifies it as <b>AI-generated</b> (<code>trainedAlgorithmicMedia</code>).</sub>
+</p>
+
+Detects the **C2PA provenance manifest** in images and flags the ones that are
+**AI-generated** - so you can label them as required by the EU AI Act (Art. 50).
+
+It reads the `digitalSourceType` from a C2PA manifest (e.g. embedded automatically by Adobe /
+Firefly) and classifies each image: AI-generated, AI-edited, other provenance, or none.
+
+## What this tool is for - and what it is not
+
+> **This tool checks your own images and pages** for AI labeling under the EU AI Act and
+> makes them compliant - nothing more.
+>
+> It is **explicitly NOT** meant to scan third-party websites, collect violations and turn them
+> into cease-and-desist letters. If that is your plan, you are in the wrong place.
+>
+> For context: the C2PA scan is only an **indicator** - it only finds images that carry a
+> provenance manifest (e.g. Adobe / Firefly), never all AI images. It is not legal advice and not
+> proof of a violation. Use it fairly.
+>
+> **Legal basis:** EU AI Act (Regulation (EU) 2024/1689), in particular Article 50 (transparency
+> obligations), applicable from 2 August 2026.
+> Legal text (EUR-Lex): https://eur-lex.europa.eu/eli/reg/2024/1689/oj
+> Article 50 (readable): https://artificialintelligenceact.eu/article/50/
+
+## Load on the target system - please read this
+
+Crawling a sitemap means fetching **every page and every image** it lists. With browser
+rendering enabled, each page additionally goes through a real Chromium, which bypasses the
+server's caches. On a large site this quickly adds up to several hundred requests per minute and
+can noticeably degrade a production system - slower responses, in the worst case a server pushed
+to its memory limit.
+
+The scanner is therefore **rate-limited out of the box**: 60 requests per minute, counting
+pages, renderings and images together. Change it under *Settings -> Scan*, or on the command
+line:
+
+```bash
+c2pa-scanner scan https://www.example.com/sitemap.xml --rate-limit 20   # gentler
+c2pa-scanner scan https://www.example.com/sitemap.xml --rate-limit 0    # no limit - be careful
+```
+
+Two things worth knowing:
+
+- **"Parallel requests" is not a rate limit.** It caps how many requests run at the same time,
+  not how many go out per minute. Only the rate limit does that.
+- **With rendering, the limit throttles page requests only.** Whatever the browser pulls in
+  afterwards - scripts, fonts, images - is not counted, so the real load is higher than the
+  configured number.
+
+`robots.txt` is honoured by default for the pages listed in the sitemap; blocked pages are
+skipped and reported in the log. Images are not checked against it, because they often live on a
+separate CDN domain with its own rules. You can turn this off in the settings for systems of
+your own - for instance a staging site that blocks everything by default.
+
+## Use at your own risk
+
+This program retrieves web pages automatically and thereby places load on the target systems.
+Depending on its settings, that load can exceed the load of an ordinary visitor many times over
+and can impair the availability of the target system.
+
+By using it, you declare that:
+
+1. You will use this program only against systems for which you hold explicit authorisation from
+   their operator.
+2. You bear sole responsibility for its use, for the settings you choose and for all
+   consequences arising from them.
+3. Before running it against a production system, you will verify that the configured limits are
+   appropriate for that system.
+
+The software is provided free of charge and without warranty of any kind ("as is"), as set out in
+section 7 of the Apache License 2.0. The liability of the author (Michael Blaess) for damages
+arising from its use is excluded to the extent permitted by applicable law. Liability for intent
+and gross negligence, for injury to life, body or health, and under mandatory product liability
+law remains unaffected.
+
+On first start the program asks you to confirm this notice. On the command line, confirm it once
+with `--accept-disclaimer`.
+
+## Usage
+
+```bash
+# Launch the graphical TUI (default when no command is given)
+c2pa-scanner
+c2pa-scanner tui https://www.example.com/sitemap.xml
+
+# Crawl a sitemap and check every image for C2PA / AI provenance (a bare domain
+# works too - the sitemap is then discovered automatically). The first run needs
+# --accept-disclaimer once; the rate limit defaults to 60 requests per minute.
+c2pa-scanner scan https://www.example.com/sitemap.xml --accept-disclaimer
+c2pa-scanner scan ./sitemap.xml
+
+# Render each page in Chromium as well (finds JS / shadow-DOM images, much heavier)
+c2pa-scanner scan https://www.example.com/sitemap.xml --render --rate-limit 20
+
+# Leave cookie banners in place instead of accepting them (only affects --render)
+c2pa-scanner scan https://www.example.com/sitemap.xml --render --no-consent
+
+# Create a signed C2PA test image (positive test fixture)
+c2pa-scanner make-testimage ./test-ai.jpg
+c2pa-scanner make-testimage ./test-edited.jpg --edited
+```
+
+## How it works
+
+Detection is layered and deliberately tuned for few false positives:
+
+- **C2PA manifest** (primary signal): the official `c2pa` library reads the signed manifest; the
+  `digitalSourceType` assertion decides the verdict (`trainedAlgorithmicMedia` = AI-generated,
+  `compositeWithTrainedAlgorithmicMedia` = AI-edited).
+- **XMP/EXIF `digitalSourceType`** (secondary signal): the same IPTC marker is also read from XMP when
+  there is no valid C2PA - this catches images that lost their signature on resize but kept the XMP.
+- **Generating tool** (fallback): if there is no `digitalSourceType` at all, the `Software` /
+  `CreatorTool` tag is matched against a curated list of unambiguous generative-AI tools (Midjourney,
+  DALL-E, Stable Diffusion, Adobe Firefly, ...). Ambiguous editors like Photoshop or GIMP are
+  deliberately NOT on the list, to avoid false positives.
+- **Page crawl:** all pages from a sitemap are fetched and image URLs are extracted via regex over the
+  raw HTML - this also finds images in web-component attributes / shadow DOM, not just classic
+  `<img src>`. If no direct sitemap URL is given, it is discovered automatically (robots.txt, then
+  common paths). For a more complete sitemap than the official one, use the companion tool
+  [Sitemap-Tracker](https://github.com/michaelblaess/sitemap-tracker) and load its XML output as a
+  local file.
+- **Browser rendering** (optional, off by default): when enabled, each page is additionally rendered in
+  a headless Chromium (Playwright), adding images that only appear in the (shadow) DOM after JavaScript
+  runs - as a union with the regex extraction.
+- **Cookie consent** (on by default): a banner is confirmed automatically once it has loaded
+  (Usercentrics, OneTrust, Cookiebot; otherwise by clicking the accept button inside the banner). This
+  matters because many sites only release their images after consent - and because the banner otherwise
+  covers the page preview. The consent manager is loaded by a script and is not there yet when the page
+  fires its load event, so the tool waits for it instead of guessing once. Switch it off under
+  *Settings -> Scan*, or on the command line with `--no-consent`.
+
+**Limits:** images with no provenance signal at all (no C2PA, no XMP/EXIF) cannot be flagged as AI.
+Metadata can be stripped - screenshots, re-saving, and many platforms remove it on upload. A hit is a
+solid indication **for** AI; its absence is **not** proof against it. Any resize/crop breaks the C2PA
+signature, so scan the original master where possible.
+
+### In the TUI
+
+- **Live image preview** next to the result list, with a clickable link to the source page and a dialog
+  for the raw C2PA manifest.
+- **Page preview** (optional): below the image, a screenshot of the rendered source page scrolled to the
+  image - so you can check without leaving the tool whether an AI label is shown on/near the image. A
+  cookie banner is dismissed beforehand (see above).
+- **Cancel a scan** with `x`: the key only appears in the footer while a run is in progress. The
+  cancellation is cooperative - requests already under way finish, no new ones start, and the images
+  found so far stay in the table. Before, only `q` was left, and that discarded the partial result.
+- **Filter & sorting**, an "AI images only" toggle, **export** via right-click (JSON, JIRA table, plain
+  text) and **test-image signing** as a positive fixture. The JIRA table comes in two formats
+  (Settings -> Export): **Markdown** for Jira Cloud (converts to a real table when pasted into a
+  comment) and **Wiki Markup** for older Jira Server/Data Center instances.
+
+- **Two languages**: the interface is available in English and German. On first start the language
+  follows your system environment - German only for a demonstrably German-speaking environment,
+  everything else (including any error while reading it) falls back to English. You can switch at
+  any time under *Settings -> Language*; the setting takes effect after a restart.
+
+### Other detection methods - and why they are (not yet) implemented
+
+For completeness, the alternatives that exist but are deliberately NOT built in:
+
+- **Invisible watermarks** (Google SynthID, Meta, Amazon Titan): robust against edits, but each scheme
+  needs its vendor's own detector - there is no open, universal reader. SynthID can only be checked via
+  Google's own portal, not as a library. **Reason: not integrable.**
+- **ML classifiers** ("is this AI?", e.g. Hive, Sensity, Illuminarty): unreliable across generators and
+  after compression/resize (high false-positive AND false-negative rates), age quickly, adversarially
+  fragile. **Reason: not defensible for a labeling decision** - it would undermine the solid verdict; at
+  most conceivable as a separately flagged "uncertain hint" that does not drive the result.
+- **Forensics/statistics** (frequency spectrum, noise residuals, diffusion fingerprints): research-grade,
+  no turnkey tool, same reliability caveats as ML classifiers. **Reason: effort vs. value does not add
+  up.**
+- **Fingerprint/hash matching** against a registry of known AI images: only works if the image is
+  registered there - not a general solution. **Reason: coverage too low.**
+
+The guiding principle: prefer a few solid signals (provenance) over many uncertain ones - fitting the
+purpose of supporting compliant AI labeling under EU AI Act Art. 50.
+
+## When something goes wrong
+
+### It will not start on an Intel Mac
+
+`zsh: bad CPU type in executable` means the architecture does not match: the
+release binaries are built for Apple Silicon (arm64) only. Rosetta cannot fix
+this - it translates x86 to arm, not the other way round, and a software update
+does not help either.
+
+Run it from source instead - that route works on both architectures, because
+[uv](https://docs.astral.sh/uv/) fetches the Python matching your processor:
+
+```bash
+git clone https://github.com/michaelblaess/c2pa-scanner.git
+cd c2pa-scanner
+./bootstrap.sh    # once
+./run.sh          # every time
+```
+
+### Crash reports
+
+If the program crashes, the report is written to disk instead of only to the
+terminal - two files next to the settings, both linked from the storage tab in
+the settings once they exist:
+
+| File | What for |
+| --- | --- |
+| `last-crash.txt` | Python errors including the traceback. Written **before** the error dialog runs - if that dialog dies during its own re-layout, the report would otherwise be lost. |
+| `fault.log` | Everything below that: native access violations, stack overflow, fatal interpreter errors. Such crashes bypass Python's error handling entirely. |
+
+Both files are **appended to**, not replaced - a second crash does not hide the
+first one.
+
+`fault.log` also gets a start and an end line per run, which makes the file
+readable at a glance:
+
+| What the file contains | What it means |
+| --- | --- |
+| start, traceback, end | Python error, the program saw it |
+| start, end | exited cleanly |
+| start, then nothing | process was killed - **not** a Python error |
+
+A killed process and a crash look identical in the terminal. Only the missing
+end line tells them apart.
+
+On Windows, prefer starting the program via `run.ps1`: the script restores the
+terminal even when the program crashes hard and can no longer do so itself.
+Otherwise mouse tracking stays on and every mouse move spills control
+characters into your prompt.
+
+## License
+
+Apache-2.0.