diff --git a/.gitignore b/.gitignore index 0deacf8..b846e4d 100644 --- a/.gitignore +++ b/.gitignore @@ -1,6 +1,7 @@ *.png *.jpg *.txt +visual_search.json !nouns.txt Todo.md data-dir/ diff --git a/README.md b/README.md index 7e49df7..d865ac4 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@ cd rewards-farmer You should also have an Ollama account created (for the LLM), the `ollama` tool installed, and you should have signed in to the Ollama CLI via the command line using `ollama signin`. This project will use a minimal amount of Ollama cloud usage using `gemma4:cloud`. If you wish to use a different model, please change the `model` parameter in the `get_ollama_response` function in `src/llm_utils.py`. -You must also provide an image for the script to upload to complete the visual search task. Currently, this image is named `visual_search.jpg` and is located in the root directory of the project. You may provide an image of your own, just ensure that the absolute path of the image is placed in the `VISUAL_SEARCH_IMAGE_PATH` constant at the top of `rewards_tasks.py`. +You must also provide an image for the script to upload to complete the visual search task. A helper script is included at `src/random_image_for_visual_search.py` that will download an image from Wikipedia named `visual_search.jpg` into the project root for you. You may also provide an image of your own, just ensure that the absolute path of the image is placed in the `VISUAL_SEARCH_IMAGE_PATH` constant at the top of `rewards_tasks.py`. Activate the virtual environment & install dependencies (you may have to use `python -m poetry` instead of `poetry`). You must have Python 3.12+ and Poetry installed. diff --git a/poetry.lock b/poetry.lock index e12f1a0..9125b87 100644 --- a/poetry.lock +++ b/poetry.lock @@ -169,6 +169,188 @@ files = [ [package.dependencies] pycparser = {version = "*", markers = "implementation_name != \"PyPy\""} +[[package]] +name = "charset-normalizer" +version = "3.5.1" +description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet." +optional = false +python-versions = ">=3.7" +groups = ["main"] +files = [ + {file = "charset_normalizer-3.5.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:d1ee1e296209fdce05b81b663250eefa02213a2da7b41bf26f7829b8ba3545aa"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e9fbdce1e47394b09bc9f26ab117dfc8d6491977a11d86f592bb42c779db2fda"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:00668ebb0609751758682eb0b5857e7c35b9f00e84dfdef062e103244ec94d45"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:ba2f37ee79e6338845261a3c5b1784e5d1acdff2c0785b284f1b633033d136ab"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:ce854f5f478050ade5a238731c4ca985a7d3b3cb53ff600a9b5c3b689b5f0a7a"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:96eefc178f8636b9c760c5829345307fd81cfae9ab1e80997dbddeb0f54ee9a3"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:366ec70f5547c640d3ce1985722490f23faf4eb5216a7eeba78277490e78dacb"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:950f23cb393f85543777b0433f082cddd25b51ab398eac7971146495679efe5f"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:c1dcc36dcb96abc02236e182d17e0f71430152a6c2c7447421da2d2dc144edea"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:07ffd07412fc5d5e84cd8952acf9ff7e4ed7a708e69d1bada19d8ba91711353f"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:f5542f9b941279d82d41eb0aa9f98eba36fe4df5c7086c651df7944935b37182"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:a545775cfe815855ea32d7c27731d79da358ef2055b4a25830231b1622dd18aa"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:494b70049a4d69aec6e8137c13af4cf8db8c9f9820a1392ac293b0dd2987a818"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-win32.whl", hash = "sha256:94fbf1c0c6cc0d3d5e50f9a9313a8cdca90dd696d34b381cd1704f8c9e939f20"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-win_amd64.whl", hash = "sha256:be47f99644b208bff7766314013f9acf57b056b04191d570d68ad14022cf5b1d"}, + {file = "charset_normalizer-3.5.1-cp310-cp310-win_arm64.whl", hash = "sha256:a6d095662e73e74f0a49988e0593373e243e3a52e27bfeea0a859e88acf4a0f5"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:eda059b6bc8bc0812d626fd91a7ce01bf583df0a61296eff390fd94141a34e30"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:aa2bb0b37202dca27175591f761108b5d34096ade1191ffe4808bdf6b1571488"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:0b2b1b3fa5670c127b246df1d0c059defd41f689a868a3b9d79df9b1cac42d22"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6e5e4d73d588ca5ed09df1b7dcd1b203d1df3c542e3f50d126c947d432b10731"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:b54e7e13267d49ffbfe68e25b3cbd774dab38fa37238f71265e91b36146eb21c"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c7b742bf31c88566b4bb6335a7f393bb322e580b6bb98df7bd0c25e6e3519ce8"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:6ba32c4d2abf1d2fe7cf27d280f4cca5664233b0f885549c7761719eb977f486"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:0722590aabf9dc6a6c0343d523c05458fa2b5047dbe6302fd526bb570600753f"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:aa1099b956fb795e686d073568f6dc002a0bb89765ea6d5b055dd7d9bf1b116c"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:bd6c173f04743d483881bffa1478d5a4624475b8cd1d2194956a75548e191c18"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:f298e218441525d3794428b4c8b8fb8662c6d3ea79925d4807ee6b9a96a3bca5"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:6e2912d4babbc65196ac13c2f53468dc57fb8b9c25ef913e8c59ddf7c6dc0e1b"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:3d27167433c0d5f18dc850f07d0b3816221984fecdc405d6c157a6f0b8f8e9e6"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-win32.whl", hash = "sha256:ac00177c4831ffa650f8609e4bdddd5fe09c03b1c0c47acece7e6ea20421598b"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-win_amd64.whl", hash = "sha256:f9b1e28d0e8dbfa858abdba91d6b547beaf2df1a59bec6da6faae7b96a4991a9"}, + {file = "charset_normalizer-3.5.1-cp311-cp311-win_arm64.whl", hash = "sha256:ae31a1a1db2ee6cc2942fccaf695c934bc7f3db9f2133a3fef1f367cf1a4ab10"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:5b6d1386bf0096d26d3a863dc0a487a5b4eb9aa93cf5ba69683d29dde6b9d60f"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4582c27e8c889d64811987b5967fbd3ae0c823fe1fd933b543d55ac20bb475fa"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:1d1c7a53a6c2103925cdd6d7229f8c567379f211c869793df679f2e9f738c369"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:e6621fb2a4988d6e53eedc455e5903e2679f3967b8acb3d639f1b63c14a2e893"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:7c0c10730342b0c9b35dd1d619beb8214e520bd96a1f870f452680b238aab3e0"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b9af956078716df40d985fb0dfeb2c2120c5ca92ba4ff4b388acfd01cdc14d08"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f9f8405c2c758532c74fed975dbee57be1f31a6e865c031870c79a6ed3212ada"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:96fef3e886d6a9874b14f27fc193fbdc69d5d8035783d86aa4e1cea594e695f9"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:5d8531a6569d025f68e2321e7638fb7978f23db58e5f69f56913837aae03816e"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:aae2ee51122d3ae968a3837d97dc24a0aeebb0dea23694422cd172bd30017cd6"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:7235dc28fc6dd9d832ac7c7bce95367dedb85929f17368a0c2bee1e080b9acbf"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:4abdc5f9ad448c1ecbfae2974b820535d6bc6e7eef63babbab3d81cf46968c71"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:ba501e667c17d8411f98e67a022d9604ef179aff0e459b7e292c796837c13573"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-win32.whl", hash = "sha256:cfa1c0cc3a8f9f53f1243a5a99ac36fd003880199383b37672e86ddda9cb07e2"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-win_amd64.whl", hash = "sha256:3617ac3cfd8b9888f145ad89dd6e692285834b0201c6074a5eeaad3fd4d668c2"}, + {file = "charset_normalizer-3.5.1-cp312-cp312-win_arm64.whl", hash = "sha256:88e85ab89cb822c1e635f51d6d32e488f94e002e70e2f492bdb8b945543f345a"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-android_24_arm64_v8a.whl", hash = "sha256:4f298bdadb8f0b9e5672877f647d1be9373ef5320c9e2f049795e26cad28b6a9"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-android_24_x86_64.whl", hash = "sha256:88ca277405c2d3b71c4e1c2ee0e7966e807bcba86a69d11e19ba199d18ae4491"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:9362dd90aa7dab48c0054a21187791ccf05473f7dba5d92b8033ae62164675e7"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:977cdbd483a9cff38179bea4fd754289a6f2195c7abd414aba85410b3e66cc5e"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:e90251c0c7bdd54a100a0dce3c07b7e637278c93af29dbf78ebb89a58c4bac7d"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:94d78ecec2605a8d0398b0f365d5f12a63248438516f5dac536a5eff7337df4a"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d59b75732e9b6f27388e10c14b0259cc5f2e48c78627d185e6a177b58ad3cffe"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:0d929fc574b4d6fd9e7c0f5c2ede8716a41911923aa7fa5fce38e0818aa4a1ac"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:394fea06235c8543390050ed5f529187074b029fb027213f6c46ac11ab5d950e"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:62b55f6722735a6c472f88361cde6640608773d9443cebdbb51abf436a1fcdd3"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:fa48b1b63d639f9483e0633e092f5851e2348c352f1f9bb6c8182f87884ef876"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:c71fb0d56c920c269cd3e2e3fe7c610e3f1fdb21a6ce60efa6430ff63676cea6"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:485a0d363cafefcd2538a73c7c838daa2035f09b2c9f9b5e3133f80c6aeb84c2"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:5c0ea61a470e070686aa30892fed79e297d2c8d0ab46b8bcdf027d38c51da591"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:90b7481fb62fbe172c558bc6fd1c4c98d82004a54a7551f20e11ac9bf0b8708c"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:35fe081843b35aad20ffeccec3eeffbe637b15d14f3fb22cc1b59cd8ec17e93c"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:fd0350afdc3aabd5576f60ea109228bd5538139713c7b094c5cd27c73a98bc6f"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-pyemscripten_2025_0_wasm32.whl", hash = "sha256:9d9a0dc7cbe9bec24c3f767c9122c41fe5a1bc43f47cd099d00d393e09769de4"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-win32.whl", hash = "sha256:d63600d620ad0064c3a748b950ac5ea38a80190e5498532efefa4b7b3f1da1f3"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-win_amd64.whl", hash = "sha256:aea996a6aba25260827c9ea511d1addfde2da9eb686ac961838509086188b7e6"}, + {file = "charset_normalizer-3.5.1-cp313-cp313-win_arm64.whl", hash = "sha256:fd0a274c0e5f9a21565cd9d3dd749b61f96b7aa1e20a93aa1ba4029518f2e5c0"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:774d157f112367ff4abd29019f38f023c24e00e56edc7829c20e358a5a913ad8"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-android_24_x86_64.whl", hash = "sha256:26422d45fd13551cf564c58932f7d72b4f58b93b0fcf18c35ba6be12b46bb102"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:09a7bba9f739468c8e78c36a75c33768e53cb1959fc638f510454c14683f00d5"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:4c9548dc78002099910abaebc0a72ac58b7d30931869e0351c09b507dff4ece3"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:c428c6c31eb5f4277d7f8eccaf767fbd548ddd5ce3c8b4f4cbbfab3d96b5904c"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2f06b7eae9dbe77fe1d644ca244dad508de8d302870a43f3c559b521270938a0"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:6b7430cf5728e68f6c462254009a6ef4086e1bea43cf2f57aa9c55fb4f50ff96"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:ab743e9bc90c1f73552ec33e10e3331315acd2c397b36065b591b0181de533cc"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:f6f7deae3feb4edfa2efaf7c574fe88cbf055038a6abdb40188e4fff66d5699f"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:15f024313246a4ed976c60f440bb8d257815513a681d212ff74fd46f7d715a90"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:823f82903d189af463d7df250ef1f7f696f3cee08cc8d91deb565e8d425f6506"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:01e93745f7f219b703b60ba7afead36cfc4242782be5af484673fc500df12da5"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:329fc3ccb63ad22d867d84c2adea759a64079a37ba4a343433b02c7a2816871e"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:bb57753e36e4855b8ca375069482250a6246372331a3e4f3407eaebb007443f5"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:fce8cbd4997efeb450bd298b54f755dcdff18d496f7a5ddbb4867c6d7c88fdc3"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:6c9cdde8becb25a7fde49924511aa2644d6f8081cc8df8e9452724303348d8e3"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:9ac4444d8d4fd4c4bd08bf451ed3167aa9e7ec6cdb41b648794f1d1103652e36"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-pyemscripten_2026_0_wasm32.whl", hash = "sha256:f03ac127268b43ef4fe9e6ab6794a6794b49485a0cc0c1db79876d2f33f75bc7"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-win32.whl", hash = "sha256:1f5883d77fd409a261abb5dc8ccbe335720d798b1de4abb3b1d47ccbbc76b53b"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-win_amd64.whl", hash = "sha256:c658c50ac0c98cd755a2dd50b7977d3bca7df401dcc47fbdfa87db53ef7d4e8b"}, + {file = "charset_normalizer-3.5.1-cp314-cp314-win_arm64.whl", hash = "sha256:4bea7f8ebe90bbd7f0e4a2de42ca6924ba23e3e76418c408ff82f1d46fabd687"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:fbc597639158fd7c14d55e808718848319540f51b0e6746e3eefa59723a4a348"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e71c909f353863b2b89c83de2ebed71ea6d0df8a6ef65a128193c5e650766bef"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7ac76cf9afd34929d76eb7fcb63be476a4853d8a96f0dcf2d0db68a0cbdf9885"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a3a370082ce34d0612f421e15fe011c53bb1feff21a26d06ad4fb244dab5a375"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:256dd4d85d9e4dc595e2bc983c980e73f62ddeb3165c58b4c3dfe78c5c8548c1"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:58d4aa13a59c969dbfdf9e6a9560e242cbfd9e8a8f50c2747714df1a423adf65"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0c6dfb5ca6723eeed15aa8e564a014d69fcb8812f94eef11fe3631e0508199f5"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:c010f5581d9c612804cc59fcf7b524b707fbcb72828551237ab545bb5c7034af"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:52ec005752a56ae79547a05c0139ca2501a0c866390b6115008456b9f0e7cde1"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:2bced4061f000f7187254a02ad3433ae17eaf991747ceea2f478422590a5bba9"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:9eea3ab2597a5e65fe65296e2d6a84570845a6b55532d90333d740d48bbc850a"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:496846868fea80e479324862fa877f02411f2fd0f83b79ccee2607aa68b2a032"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:85d5855daafc240cc045c026d7a15fd198a09b0fc8ff6f5ecbb5297b509cb11e"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-win32.whl", hash = "sha256:58d3e12c88e0950bca850ae1f7c256055c097639c2edb9eb123af9807d8b15e4"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-win_amd64.whl", hash = "sha256:acaf604462bf330b0d07e7a07c1d6e4adac79e5fb13e9c5140590542cafacc00"}, + {file = "charset_normalizer-3.5.1-cp314-cp314t-win_arm64.whl", hash = "sha256:fdb8a068947befafba9952162645dc2fecaeb400e64584829ed5e9b2fbe21a7f"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-macosx_10_15_universal2.whl", hash = "sha256:9085f87b0e38a2b92b8923059b4e8789fe40d9279712d15dcc670048d77079af"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2679de311c7946dde5d3b6f44941844133ff5c7cb86099c0061ab1e8901c20a8"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:baf3775a2635e5a11fbd5e4e64ee69c7e86875d224a5c72aca4c141064589a90"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8ac8c94b6539074e0f40899301273ac8402b9b3e01c7b7ba269ff30340aaaf20"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:8fe532b3c966d1fb794e0698e4589d0444017ae77fc0b31edea13c0e35bcc449"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5c84bec0ab5ae0c64bfe73a7d2adcb5ce73b467523fc27fd6a28ab2aa6cbe35a"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:854066be00447fa8de2ccbbe893e2ffc4b123ef16d897af794c1e18bd4a714b0"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-musllinux_1_2_aarch64.whl", hash = "sha256:21b82d8082f6f5e7f456ef0bd16323d08de1266efbfeb476e64b2a91d1471a4e"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-musllinux_1_2_armv7l.whl", hash = "sha256:838648accb3a7fd9803fd45c87bce8509648eb0c11bc34e216141300977244f2"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-musllinux_1_2_ppc64le.whl", hash = "sha256:195ce897c6153c0700078142cf8efe3e6454ca4cf4357499e4078dfd83396626"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-musllinux_1_2_riscv64.whl", hash = "sha256:978eab16f55b4ab2c2a745be9a0a840bf8f09a7f227d9c76eb30214d078865a5"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-musllinux_1_2_s390x.whl", hash = "sha256:cc0329df4caaceb950d2f580b5ac716a377f7059624a0bafaeaf8a218c6ed774"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-musllinux_1_2_x86_64.whl", hash = "sha256:687c9ca3035544b113bea2055e180af96fb63c0c476e22a9180f51925186e7b7"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-win32.whl", hash = "sha256:706bfd38730a5ac7a365793269a00f4e988178cec121391f4248d84ad8c972e9"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-win_amd64.whl", hash = "sha256:92caef967d287a407085d61176fce4012b1dd62daed4eb6d5ceb26d3d2538712"}, + {file = "charset_normalizer-3.5.1-cp315-cp315-win_arm64.whl", hash = "sha256:5fc45d653ea8c9a20479167e11d4a0f8cb2fa3470737ab6f9c827532313187b7"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-macosx_10_15_universal2.whl", hash = "sha256:59171c6e45bf07d0d5cab3b0bf81d945035530f6873398b3b531c31184d46663"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9dbdd9205662134957cf0c324f639bdc5031c0ca056e2369e238db75187c0f11"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:e4b018dc5a0eee4676e38fe84a47a427816c590b93b55d9025274ec4d6ffc2dc"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:ced3fdd71aaa83ce593746c2edb42b7a59cb4c19c8b5c407781c72e493aae55a"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:19a3dd5aa73cef1c99687c4fc57db016a9c17104ae1185da88ba566a5d3bebe4"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:cc5d36d96478aa9c60654bd932525bf32964c62a7281eafdf16d85003a8d6004"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:04368edf83514385ffc3e1cfd4546e595f4f1272dd23ba437a93a9cc3741d47b"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-musllinux_1_2_aarch64.whl", hash = "sha256:9b5db6052055d34d41230fb78d7c439c23dc536a9896f6cb039e8dd92cfc1263"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-musllinux_1_2_armv7l.whl", hash = "sha256:252d099029bcbea642f2a06c4ed5046bdf8b5a8150b64afa5e027e88b106e5ee"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-musllinux_1_2_ppc64le.whl", hash = "sha256:6199d5606e2bbf2b096cf64d03f8b6790c91081d5ac866b8e7bb6422738cc60c"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-musllinux_1_2_riscv64.whl", hash = "sha256:77efcff2b23071c349402ac1066667a3d011f62398d81408c9b88ad991747c9e"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-musllinux_1_2_s390x.whl", hash = "sha256:a5cbd90ecf0fc62e64726917ad083b73001f0563657a87ec3c0b504e277dc90d"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-musllinux_1_2_x86_64.whl", hash = "sha256:4d26f14f041e83dd8edfd61f4cd4fa7285d31798b5bf1f28e70c367ba6c41d61"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-win32.whl", hash = "sha256:ac13b004224fb341e1e25a1ed5e19d32f57cdb2a403e01f003b46f051a550f6f"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-win_amd64.whl", hash = "sha256:35aea775dc2bd5f54cd84a1cd2696cc3207c479cb9cf0bd346f0d343e4300ddb"}, + {file = "charset_normalizer-3.5.1-cp315-cp315t-win_arm64.whl", hash = "sha256:fb78f6e7fcd8ad785d28cd577168bc1aaee827b25bb8755638f694794ea98f0a"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:41876ee62a3dddf48ff1121ad8f0798032aa03f2fd35f21f34a4cab14f18d8d2"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:a6dac12ff6b846103483683f60c5f8fee205121adc58ffd87e90a90a3af69e99"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:cee5dd7c6fb5dd52a0fe2a740f9bc6e3593f5f8b1788bde49de02086f30182b2"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:343fb4f2821043bd87095f7b08a1a181febc8e36ac64212143bbfd0a0e1bc235"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:ae4a097991662cd4fff0ddc74e0fe7874f82e00042fa0ea00855645ed0c79598"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4b599739b93b2cbeded49645ae3c8d1405c29ddfbceac1545c87a3f9580a9e96"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:b39b69b347e5e47a3b5b8cfc005c68c1ba347474e3960236c4944a8ecd174962"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:a2028475ba855475b8b4d3cfeb4994269c967aea8b9892dfba907f4263a863a3"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:36047af20e17097c3bb9476c2b7655f2f7aa51322c0ba58c07695bedf755a950"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-musllinux_1_2_ppc64le.whl", hash = "sha256:4c4fb141a727957c93edfe5c32a26ceb6b5f6461d67146e2d39f51e16170bea8"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-musllinux_1_2_riscv64.whl", hash = "sha256:2f293479cce755c75f1697e87c409b7ae4c555c7dfecb6e988ad13abba943031"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-musllinux_1_2_s390x.whl", hash = "sha256:3588e376b3ea2eea84976f67273d679f229e24c66dce7b82ae45aef04ff6e072"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:e199fb99720074809a7720f1c0b4d919eea8b87e88713e0f8f602f7bef543d9d"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-win32.whl", hash = "sha256:dd732602a7009217f658d5863d12d79d373a4de0eebc111094bcdd3bb8e0a6cc"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-win_amd64.whl", hash = "sha256:70055ff39b97c99e7ae40ea3e393fb62aa2e44dbd9b29f8d14f42fb0025c3959"}, + {file = "charset_normalizer-3.5.1-cp37-abi3-win_arm64.whl", hash = "sha256:87e4f41d375c0b9be2fb5251aee4b8a689169e134535aed81bf085c3b647451e"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:85de3134b5379856e323ba37c19c9256d39425f7b76a63af52b09fb4664c2e8f"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3e5e1224c0a6a90e05843e07adfec669edebec17801c67072f51e59561d63c0b"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:5e2d0e146dcb57034f8b97dc58d2d512cb90aba253960ce449f695fec6a82c6f"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:e06efa066f7dbadbc84ebc126a97c452a6451dfcf589d89d788484949e1cf795"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:994e883d17c559cdfd38c84003c8b27d25424a1077272a17e7cd27bfe0bf57b2"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:789b8982559ae28dad2356519f841655756cdcd96616410590ae0b17454ee64f"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:a951ad59cad9145664a730d3036b40b844e74d2d3683da40111463cd3a83845d"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:55261ac0d2941c42f196dd576f543d87a8ee03cd6f5e30dfb4d807b2e3b9121a"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-musllinux_1_2_armv7l.whl", hash = "sha256:5ca0555312ae2fe82715cada7fac375530c2f3349e1eaa1bcb33d0283ac79a18"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:2e9cf9253119d8e5d111f05d71626786fd3d6193817316eab1ca088cdb8593cf"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-musllinux_1_2_riscv64.whl", hash = "sha256:433c5a81eade63b47e522303bad236f59dba55ea6951746f5558355eeed8c75d"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:13e3afe97712e8887cd516e960c63f0b93122971e5b5e4b2622fe7701771e838"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:eb12fb2ba69ffa05f8695f61c69e591dc4b4a12ac3757ac8af8adb259bf56d17"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-win32.whl", hash = "sha256:56490c595a28b1bb27dfc583e816152a9767721ef58b2c03b13f954d2f707420"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-win_amd64.whl", hash = "sha256:012a22b88a77ca2e59b98ac5889b0deb604147666032f45e6d6e217634d2550d"}, + {file = "charset_normalizer-3.5.1-cp39-cp39-win_arm64.whl", hash = "sha256:29880d17a8eb0b5cfdfd8944b468322928059aa35f1f5fa8ff22b149ec0b42f8"}, + {file = "charset_normalizer-3.5.1-py3-none-any.whl", hash = "sha256:6df0ec430f9a831772c23ca5a224cba36517a58a84bb32c32bb59a9fa67c47f6"}, + {file = "charset_normalizer-3.5.1.tar.gz", hash = "sha256:6117b84ea48435e5356dc737f5121485c30920ba43375fa7b434fd753df0eac3"}, +] + [[package]] name = "contourpy" version = "1.3.3" @@ -4869,6 +5051,28 @@ files = [ [package.dependencies] six = ">=1.5" +[[package]] +name = "requests" +version = "2.34.2" +description = "Python HTTP for Humans." +optional = false +python-versions = ">=3.10" +groups = ["main"] +files = [ + {file = "requests-2.34.2-py3-none-any.whl", hash = "sha256:2a0d60c172f83ac6ab31e4554906c0f3b3588d37b5cb939b1c061f4907e278e0"}, + {file = "requests-2.34.2.tar.gz", hash = "sha256:f288924cae4e29463698d6d60bc6a4da69c89185ad1e0bcc4104f584e960b9ed"}, +] + +[package.dependencies] +certifi = ">=2023.5.7" +charset_normalizer = ">=2,<4" +idna = ">=2.5,<4" +urllib3 = ">=1.26,<3" + +[package.extras] +socks = ["PySocks (>=1.5.6,!=1.5.7)"] +use-chardet-on-py3 = ["chardet (>=3.0.2,<8)"] + [[package]] name = "selenium" version = "4.46.0" @@ -5045,4 +5249,4 @@ h11 = ">=0.16.0,<1" [metadata] lock-version = "2.1" python-versions = ">=3.12" -content-hash = "fd4eaf67a2a0849a8ce66dfd1ac2be20276da3d8a1454ef9d991214912a51d61" +content-hash = "6f6874b55cb994ba31fcb815e7f2680cd49498becf9823594dc08ab3c6bbbcbf" diff --git a/pyproject.toml b/pyproject.toml index 43211af..c49ef36 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -13,7 +13,9 @@ dependencies = [ "pygetwindow (>=0.0.9,<0.0.10)", "keyboard (>=0.13.5,<0.14.0)", "pygame-ce (>=2.5.8,<3.0.0)", - "ollama (>=0.6.2,<0.7.0)" + "ollama (>=0.6.2,<0.7.0)", + "requests>=2.32.0", + "pillow>=11.0.0" ] diff --git a/src/random_image_for_visual_search.py b/src/random_image_for_visual_search.py new file mode 100644 index 0000000..0cf22d2 --- /dev/null +++ b/src/random_image_for_visual_search.py @@ -0,0 +1,512 @@ +import io +import json +import time +from pathlib import Path +from urllib.parse import urlsplit, urlunsplit + +import requests +from PIL import Image + + +# ============================================================ +# CONFIG +# ============================================================ + +API_URL = "https://commons.wikimedia.org/w/api.php" + +OUTPUT_FILE = Path("visual_search.jpg") +METADATA_FILE = Path("visual_search.json") + +MAX_ATTEMPTS = 10 + +# Loose filtering +MIN_WIDTH = 300 +MIN_HEIGHT = 300 + +# Maximum original file size we'll accept +MAX_FILE_SIZE = 20 * 1024 * 1024 # 20 MB + +# Wikimedia will generate a thumbnail around this width +THUMBNAIL_WIDTH = 1280 + +# Normal delay between failed attempts +REQUEST_DELAY = 3 + +# Maximum rate-limit wait +MAX_BACKOFF = 300 + + +# ============================================================ +# HTTP SESSION +# ============================================================ + +session = requests.Session() + +session.headers.update({ + "User-Agent": ( + "RandomVisualSearchImage/1.1 " + "(contact: 12345rfdz@gmail.com)" + ) +}) + + +# ============================================================ +# URL HELPERS +# ============================================================ + +def clean_url(url): + """Remove query parameters from Wikimedia URLs.""" + + parts = urlsplit(url) + + return urlunsplit(( + parts.scheme, + parts.netloc, + parts.path, + "", + "", + )) + + +# ============================================================ +# RATE LIMIT HANDLING +# ============================================================ + +def wait_after_429(response, attempt): + """Wait according to Wikimedia's Retry-After header.""" + + retry_after = response.headers.get("Retry-After") + + if retry_after: + try: + wait_time = int(retry_after) + except ValueError: + wait_time = min( + 2 ** attempt, + MAX_BACKOFF, + ) + else: + wait_time = min( + 2 ** attempt, + MAX_BACKOFF, + ) + + wait_time = max(5, wait_time) + + print( + f"Rate limited. Waiting " + f"{wait_time} seconds..." + ) + + time.sleep(wait_time) + + +# ============================================================ +# DOWNLOAD +# ============================================================ + +def download_image(url): + """Download image bytes from Wikimedia.""" + + url = clean_url(url) + + try: + response = session.get( + url, + timeout=30, + allow_redirects=True, + ) + + except requests.RequestException as e: + print(f"Download failed: {e}") + return None + + if response.status_code == 429: + wait_after_429(response, 1) + return None + + if response.status_code == 403: + print("Wikimedia returned 403 Forbidden.") + return None + + try: + response.raise_for_status() + except requests.RequestException as e: + print(f"HTTP error: {e}") + return None + + content_type = response.headers.get( + "Content-Type", + "", + ).lower() + + if not content_type.startswith("image/"): + print( + f"Not an image: {content_type}" + ) + return None + + if not response.content: + print("Downloaded image is empty.") + return None + + return response.content + + +# ============================================================ +# JPEG CONVERSION +# ============================================================ + +def convert_to_jpeg(image_data): + """Convert downloaded image bytes to JPEG.""" + + try: + with Image.open( + io.BytesIO(image_data) + ) as image: + + # JPEG does not support alpha (transparency). + # If the image has transparency (RGBA or LA), paste it over a white background. + if image.mode in ("RGBA", "LA") or (image.mode == "P" and "transparency" in image.info): + background = Image.new("RGB", image.size, (255, 255, 255)) + if image.mode == "P": + image = image.convert("RGBA") + background.paste(image, mask=image.split()[-1]) + jpeg_image = background + else: + jpeg_image = image.convert("RGB") + + output = io.BytesIO() + + jpeg_image.save( + output, + format="JPEG", + quality=90, + optimize=True, + ) + + return output.getvalue() + + except Exception as e: + print( + f"JPEG conversion failed: {e}" + ) + return None + + +# ============================================================ +# RANDOM IMAGE +# ============================================================ + +def get_random_image(): + + for attempt in range( + 1, + MAX_ATTEMPTS + 1, + ): + + if attempt > 1: + time.sleep(REQUEST_DELAY) + + print( + f"\nAttempt " + f"{attempt}/{MAX_ATTEMPTS}" + ) + + # ---------------------------------------------------- + # RANDOM FILE + # ---------------------------------------------------- + + params = { + "action": "query", + "format": "json", + + "generator": "random", + "grnnamespace": 6, + "grnlimit": 1, + + "prop": "imageinfo", + + "iiprop": ( + "url|size|mime|dimensions" + ), + + "iiurlwidth": THUMBNAIL_WIDTH, + } + + try: + response = session.get( + API_URL, + params=params, + timeout=20, + ) + + except requests.RequestException as e: + print(f"API request failed: {e}") + continue + + # ---------------------------------------------------- + # API RATE LIMIT + # ---------------------------------------------------- + + if response.status_code == 429: + wait_after_429( + response, + attempt, + ) + continue + + try: + response.raise_for_status() + data = response.json() + + except ( + requests.RequestException, + ValueError, + ) as e: + print(f"API error: {e}") + continue + + # ---------------------------------------------------- + # GET PAGE + # ---------------------------------------------------- + + pages = ( + data + .get("query", {}) + .get("pages", {}) + ) + + if not pages: + print("No page returned.") + continue + + page = next( + iter(pages.values()) + ) + + title = page.get( + "title", + "Unknown", + ) + + imageinfo = page.get( + "imageinfo" + ) + + if not imageinfo: + print( + "No image information." + ) + continue + + info = imageinfo[0] + + mime = info.get( + "mime", + "", + ) + + width = info.get( + "width", + 0, + ) + + height = info.get( + "height", + 0, + ) + + size = info.get( + "size", + 0, + ) + + thumbnail_url = info.get( + "thumburl" + ) + + original_url = info.get( + "url" + ) + + # ---------------------------------------------------- + # FILTER + # ---------------------------------------------------- + + if mime not in { + "image/jpeg", + "image/png", + "image/webp", + }: + print( + f"Skipping unsupported type: " + f"{mime}" + ) + continue + + if width < MIN_WIDTH or height < MIN_HEIGHT: + print( + f"Skipping small image: " + f"{width}x{height}" + ) + continue + + if size > MAX_FILE_SIZE: + print( + f"Skipping large image: " + f"{size / 1024 / 1024:.1f} MB" + ) + continue + + if not thumbnail_url: + print("No thumbnail URL.") + continue + + # ---------------------------------------------------- + # FOUND + # ---------------------------------------------------- + + print(f"Found: {title}") + print( + f"Size: {width}x{height}" + ) + + # ---------------------------------------------------- + # DOWNLOAD THUMBNAIL + # ---------------------------------------------------- + + image_data = download_image( + thumbnail_url + ) + + # ---------------------------------------------------- + # FALLBACK TO ORIGINAL + # ---------------------------------------------------- + + if image_data is None and original_url: + print( + "Trying original..." + ) + + image_data = download_image( + original_url + ) + + if image_data is None: + print( + "Couldn't download image." + ) + continue + + # ---------------------------------------------------- + # CONVERT TO JPEG + # ---------------------------------------------------- + + print("Converting to JPEG...") + + jpeg_data = convert_to_jpeg( + image_data + ) + + if jpeg_data is None: + continue + + # ---------------------------------------------------- + # SAVE JPEG + # ---------------------------------------------------- + + try: + OUTPUT_FILE.write_bytes( + jpeg_data + ) + + except OSError as e: + print( + f"Couldn't save image: {e}" + ) + continue + + # ---------------------------------------------------- + # SAVE METADATA + # ---------------------------------------------------- + + metadata = { + "title": title, + "source": "Wikimedia Commons", + "output_format": "JPEG", + + "width": width, + "height": height, + + "original_mime": mime, + + "original_size": size, + + "jpeg_size": len( + jpeg_data + ), + + "original_url": ( + clean_url(original_url) + if original_url + else None + ), + + "thumbnail_url": ( + clean_url(thumbnail_url) + if thumbnail_url + else None + ), + } + + try: + METADATA_FILE.write_text( + json.dumps( + metadata, + indent=4, + ensure_ascii=False, + ), + encoding="utf-8", + ) + + except OSError as e: + print( + f"Warning: couldn't save " + f"metadata: {e}" + ) + + # ---------------------------------------------------- + # DONE + # ---------------------------------------------------- + + print() + print("=" * 50) + print("SUCCESS") + print("=" * 50) + print( + f"Image: " + f"{OUTPUT_FILE.absolute()}" + ) + print( + f"Size: " + f"{len(jpeg_data) / 1024:.1f} KB" + ) + print( + f"Source: {title}" + ) + + return metadata + + raise RuntimeError( + "Unable to obtain a suitable " + "Wikimedia image." + ) + + +# ============================================================ +# MAIN +# ============================================================ + +if __name__ == "__main__": + get_random_image() \ No newline at end of file diff --git a/visual_search.jpg b/visual_search.jpg new file mode 100644 index 0000000..158d82b Binary files /dev/null and b/visual_search.jpg differ