diff --git a/crawler/pyproject.toml b/crawler/pyproject.toml index 4dc623d..fe2ecf7 100644 --- a/crawler/pyproject.toml +++ b/crawler/pyproject.toml @@ -7,11 +7,13 @@ dependencies = [ "httpx>=0.28", "legacy-doc>=0.2.1", "lxml>=6.1.3", + "onnxruntime>=1.31.1", "openpyxl>=3.1.5", "playwright>=1.64.1", "pydantic>=2.14.1", "pypdf>=7.0.0", "python-docx>=1.2.0", + "rapidocr>=3.10.0", "xlrd>=2.0.2", ] @@ -21,6 +23,7 @@ crawler = "crawler.main:main" [dependency-groups] dev = [ "datamodel-code-generator>=0.86.0", + "pillow>=13.0.0", "pyright>=1.1.400", "pytest>=9.1", "ruff>=0.17", diff --git a/crawler/src/crawler/parse/files.py b/crawler/src/crawler/parse/files.py index c55f508..c7722ad 100644 --- a/crawler/src/crawler/parse/files.py +++ b/crawler/src/crawler/parse/files.py @@ -1,5 +1,5 @@ -"""The words in the files notices attach (design §5.1): PDF, Word and Excel, the old binary formats -too. Images wait for text recognition (#47); archives and other files have none to read.""" +"""The words in the files notices attach (design §5.1): images, PDF, Word and Excel, including +the old binary formats. Archives and other files have none to read.""" import io import unicodedata @@ -14,9 +14,20 @@ from legacy_doc import extract_text from pypdf import PdfReader +from crawler.parse.image import image_text + _PDF = b"%PDF" _ZIP = b"PK\x03\x04" _OLE = b"\xd0\xcf\x11\xe0\xa1\xb1\x1a\xe1" +_IMAGE_HEADERS = ( + b"\x89PNG\r\n\x1a\n", + b"\xff\xd8\xff", + b"GIF87a", + b"GIF89a", + b"BM", + b"II*\x00", + b"MM\x00*", +) # Old Word files keep their text in a stream of this name; old Excel files have none. _WORD = "WordDocument".encode("utf-16-le") # Some PDFs map common characters to the Kangxi radicals that look like them, ⽣ for 生. @@ -26,6 +37,8 @@ def file_text(data: bytes) -> str: """Raises ValueError when the file is broken.""" try: + if data.startswith(_IMAGE_HEADERS) or (data.startswith(b"RIFF") and data[8:12] == b"WEBP"): + return image_text(data) if data.startswith(_PDF): pages = PdfReader(io.BytesIO(data)).pages return "\n".join(page.extract_text() for page in pages).translate(_RADICALS) diff --git a/crawler/src/crawler/parse/files_test.py b/crawler/src/crawler/parse/files_test.py index c949177..67bfca2 100644 --- a/crawler/src/crawler/parse/files_test.py +++ b/crawler/src/crawler/parse/files_test.py @@ -1,13 +1,39 @@ import io import zipfile +from pathlib import Path import docx import openpyxl import pytest +from PIL import Image, ImageDraw, ImageFont from crawler.parse.files import file_text +def test_image_reads_generated_chinese_attachment() -> None: + image = Image.new("RGB", (1600, 500), "white") + draw = ImageDraw.Draw(image) + font = ImageFont.truetype(Path(__file__).with_name("fixtures") / "NotoSansSC-test.ttf", 64) + draw.text((60, 50), "夏令营报名时间", fill="black", font=font) + draw.text((60, 170), "7月6日10:00至8月10日17:00", fill="black", font=font) + draw.text((60, 290), "请填写申请表", fill="black", font=font) + buffer = io.BytesIO() + image.save(buffer, format="PNG") + + text = file_text(buffer.getvalue()) + + assert "夏令营报名时间" in text + assert "7月6日10:00至8月10日17:00" in text + assert "请填写申请表" in text + + +def test_blank_image_has_no_words_to_read() -> None: + buffer = io.BytesIO() + Image.new("RGB", (600, 300), "white").save(buffer, format="JPEG") + + assert file_text(buffer.getvalue()) == "" + + def test_word_keeps_paragraphs_and_tables_in_order_with_merged_cells_once() -> None: document = docx.Document() document.add_paragraph("报名截止6月30日。") @@ -80,9 +106,10 @@ def test_files_with_no_words_to_read_give_none() -> None: with zipfile.ZipFile(archive, "w") as files: files.writestr("说明.txt", "自编的说明") assert file_text(archive.getvalue()) == "" - assert file_text(b"\x89PNG\r\n\x1a\n") == "" def test_a_broken_file_is_an_error() -> None: with pytest.raises(ValueError, match="BadZipFile"): file_text(b"PK\x03\x04" + b"\x00" * 30) + with pytest.raises(ValueError, match="UnidentifiedImageError"): + file_text(b"\x89PNG\r\n\x1a\n") diff --git a/crawler/src/crawler/parse/fixtures/NotoSansSC-OFL.txt b/crawler/src/crawler/parse/fixtures/NotoSansSC-OFL.txt new file mode 100644 index 0000000..79a917b --- /dev/null +++ b/crawler/src/crawler/parse/fixtures/NotoSansSC-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2014-2021 Adobe (http://www.adobe.com/), with Reserved Font Name 'Source' + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://scripts.sil.org/OFL + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/crawler/src/crawler/parse/fixtures/NotoSansSC-test.ttf b/crawler/src/crawler/parse/fixtures/NotoSansSC-test.ttf new file mode 100644 index 0000000..33c68f4 Binary files /dev/null and b/crawler/src/crawler/parse/fixtures/NotoSansSC-test.ttf differ diff --git a/crawler/src/crawler/parse/image.py b/crawler/src/crawler/parse/image.py new file mode 100644 index 0000000..92a255c --- /dev/null +++ b/crawler/src/crawler/parse/image.py @@ -0,0 +1,43 @@ +"""Read text from image attachments.""" + +import logging +import resource +import threading +import time + +from rapidocr import RapidOCR +from rapidocr.utils.output import RapidOCROutput + +logger = logging.getLogger(__name__) +_lock = threading.Lock() +_engine: RapidOCR | None = None + + +def image_text(data: bytes) -> str: + """Return recognized lines in reading order, with one OCR call at a time.""" + global _engine + + with _lock: + start = time.monotonic() + if _engine is None: + _engine = RapidOCR( + params={ + # Find lines on a smaller copy, then crop the legible text from the original. + "Global.use_preprocess_img": False, + "Det.limit_type": "max", + "Det.limit_side_len": 2000, + # A batch is padded to its widest line; one line at a time keeps the peak low. + "Rec.rec_batch_num": 1, + } + ) + result = _engine(data) + if not isinstance(result, RapidOCROutput): + raise TypeError("OCR did not return recognized text") + logger.info( + "Image OCR completed", + extra={ + "elapsed": time.monotonic() - start, + "peak_rss_kib": resource.getrusage(resource.RUSAGE_SELF).ru_maxrss, + }, + ) + return "\n".join(result.txts or []) diff --git a/crawler/uv.lock b/crawler/uv.lock index 8476f81..232d7c2 100644 --- a/crawler/uv.lock +++ b/crawler/uv.lock @@ -87,6 +87,100 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/32/d1/a3652fe2c19134d0d15922177821d863cbd7e842d53a21bbe7e8e3a1b5ac/certifi-2026.10.23-py3-none-any.whl", hash = "sha256:e9b54de76e530bb6cf0ccd036787103acb58fd42ba930ea8bf948ddbaa2f61d1", size = 135082, upload-time = "2026-10-23T11:36:14.763Z" }, ] +[[package]] +name = "charset-normalizer" +version = "3.5.2" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/33/1c/f41d4e74c28ab327ff3acd36053f7ea506c55872d7a90b0fa71aa3ab0c89/charset_normalizer-3.5.2.tar.gz", hash = "sha256:39de2a259fc954455c57274dc94c79d5842774e1247a016aff30bc0efed0f4ef", size = 172659, upload-time = "2026-09-30T04:39:23.398Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/58/ca/7aa91362a2f77ac8e9e28a9b902a74f7d0e11a851ef0d27a74308da8cd90/charset_normalizer-3.5.2-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:1afb975bd5d68d5ce9f6b6d44fdf2f7e34b895a35e95708a7a91b20a3b51d187", size = 226010, upload-time = "2026-09-30T04:36:27.669Z" }, + { url = "https://files.pythonhosted.org/packages/a8/cf/ac8878d0322cf88a1aad4c7b147db32ca0bd806eb0060957b2e31486dbe6/charset_normalizer-3.5.2-cp314-cp314-android_24_x86_64.whl", hash = "sha256:bbbfc8e28816f19d7c0f1816664980c0a9875d01b27cdf8eedddb639d9e108ad", size = 239266, upload-time = "2026-09-30T04:36:29.434Z" }, + { url = "https://files.pythonhosted.org/packages/c9/6d/9a08d7e0b29b7208e2c6c01dc56c8e0520e7c7beadbbfb024b58fd69c8a5/charset_normalizer-3.5.2-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:7967d08cf06dee78443b874f98c98036f624f3a4e73e11f9f64f5be4d25393cf", size = 206783, upload-time = "2026-09-30T04:36:30.872Z" }, + { url = "https://files.pythonhosted.org/packages/82/44/b0aa350280e6ff5a5492d17cf10460dd39d5ee848f872f7ba2df10607f60/charset_normalizer-3.5.2-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:4c2b5031f63e331e3839b40aed2dd6f191e9c07edbde303e7876846ea1946995", size = 210449, upload-time = "2026-09-30T04:36:32.625Z" }, + { url = "https://files.pythonhosted.org/packages/7c/8a/40db9aa9f5907bb0e6f8b6d64064bf8852fb33d4b813ff9414911df7647c/charset_normalizer-3.5.2-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:fcff63213e8e6e47770541a4607175404f47cbb3ebea7b6058cc82d524a0e424", size = 367815, upload-time = "2026-09-30T04:36:34.197Z" }, + { url = "https://files.pythonhosted.org/packages/7f/72/9c5e7707b57c8ddfa9ddf7b0b1d009d7fbab9e9e887d5b721060f37e307d/charset_normalizer-3.5.2-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8d86d6fc60743dc916eb79e2eb1ec4818e21e427731543af40a3021851174a13", size = 247095, upload-time = "2026-09-30T04:36:35.803Z" }, + { url = "https://files.pythonhosted.org/packages/83/09/71e453691e927de4ddf792770cfaab3f49d494e222f66ea5e404bbd5e39c/charset_normalizer-3.5.2-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7a881931aa470808df94a8c380eed2bbbc76cd9dc622310f99665658c821eb6d", size = 233942, upload-time = "2026-09-30T04:36:37.407Z" }, + { url = "https://files.pythonhosted.org/packages/9f/86/85c84e4da8b27dd409577d9437926ff581c5f9d3c66038dc68c1a526de51/charset_normalizer-3.5.2-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8024d00c3faf3fc0c16e07a69f4405e8eac7cc0ab15f65fe6cf43827c4cf72b4", size = 273762, upload-time = "2026-09-30T04:36:38.904Z" }, + { url = "https://files.pythonhosted.org/packages/92/08/564955a4b5f2ccb410ab480bbe8c6a18063ff27f2d35458731c4a5335df9/charset_normalizer-3.5.2-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4d48f2d08b9de5864e2c8744d4461b862fb149a18274abc8b698c45975573438", size = 269514, upload-time = "2026-09-30T04:36:40.469Z" }, + { url = "https://files.pythonhosted.org/packages/18/24/bad3ac4271589df29cf5ce2f5ae490518a5739358052bd0d61209e6fea54/charset_normalizer-3.5.2-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:34276fd796040bf0993ab33a369aa572e6979c7aab225a88893667ad8eac8f7a", size = 255056, upload-time = "2026-09-30T04:36:42.02Z" }, + { url = "https://files.pythonhosted.org/packages/d6/3e/350d89ad49916b86554d6f5f2d03ec1152148f87e5ff735106c6a03b1a36/charset_normalizer-3.5.2-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0521c5665880b33d603717defa76c094048900010897909952397feb3039da56", size = 251311, upload-time = "2026-09-30T04:36:43.577Z" }, + { url = "https://files.pythonhosted.org/packages/56/5b/4970a2d154df502e133402906dd04e3ae7cada7b3011283c88d0479a2585/charset_normalizer-3.5.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:eff0ac9dbe711a4aee69bf04a83896aa9b85f19641264053a9f6d48573abb7dd", size = 250190, upload-time = "2026-09-30T04:36:45.185Z" }, + { url = "https://files.pythonhosted.org/packages/88/8c/f1a91bddc8fb47c2889e29ea7ea49a194eb0d9868675d786806519c00d76/charset_normalizer-3.5.2-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:1503bccbeb36d5527790c3930327704c39af22de3112f1b1666a9f3ce15ee204", size = 237098, upload-time = "2026-09-30T04:36:46.689Z" }, + { url = "https://files.pythonhosted.org/packages/24/0e/bb5dace3cc7e79068425386a6589c19b5a2ab5fefc2a46abea6919683332/charset_normalizer-3.5.2-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:52aa6992700996af31f375de0c6bacd402b0097fe40b53c426b9f51a90ebabc7", size = 274228, upload-time = "2026-09-30T04:36:48.31Z" }, + { url = "https://files.pythonhosted.org/packages/9d/79/b849ad523017ea9f5a45581bbebed91439e0cf42fd2860a6f64e358eb5a6/charset_normalizer-3.5.2-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:e09a3942ecbdee5cce73ea9d42da82b81b72ac1bf031ce069b93b5adf4eac8cd", size = 252401, upload-time = "2026-09-30T04:36:50.091Z" }, + { url = "https://files.pythonhosted.org/packages/89/8c/75469d690cf47200bce8f6cad7655724fc23148e147abfc5ce78b5f65863/charset_normalizer-3.5.2-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:c7c9ab723cde841fefb34efbad91e87f00a674b1fe1cd0784fde742bf2c154dc", size = 271846, upload-time = "2026-09-30T04:36:51.719Z" }, + { url = "https://files.pythonhosted.org/packages/26/cd/6d52d3c7437cdcf2e310ce9f28f282e733d4ef60ed19105d1819c356255f/charset_normalizer-3.5.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:ddc7dacc8ece3a182e7f15cb862d1fd616b46d076cb1ae9dd232b2c38b655874", size = 258151, upload-time = "2026-09-30T04:36:53.234Z" }, + { url = "https://files.pythonhosted.org/packages/f7/4c/070b38bdb5f49a70199fce923ec0726a49536a63ab262abbfcaaf351110b/charset_normalizer-3.5.2-cp314-cp314-pyemscripten_2026_0_wasm32.whl", hash = "sha256:ee43c17b173d46a3212baa6ead3ae258eeabdae48c263a01ccf0218c366dd655", size = 143570, upload-time = "2026-09-30T04:36:54.816Z" }, + { url = "https://files.pythonhosted.org/packages/81/84/9ebfc8ed6c8c4fcd8e726ff6bf220cc8deb3966e31dce9be8dd8aa017e64/charset_normalizer-3.5.2-cp314-cp314-win32.whl", hash = "sha256:4f87960d57feabfb618e4e0af6e7371645fa26a277860739d6e5d6e0012c92f0", size = 186412, upload-time = "2026-09-30T04:36:56.643Z" }, + { url = "https://files.pythonhosted.org/packages/d1/78/5ed86f743d4bc350db307e7636419a0a5ee1d91806d30c7f667bd5c80dae/charset_normalizer-3.5.2-cp314-cp314-win_amd64.whl", hash = "sha256:e4e81e09c1578b8df602e3db08b0b3ea0a6947ad612f52bf8dc5ea8d47691f0c", size = 210965, upload-time = "2026-09-30T04:36:58.205Z" }, + { url = "https://files.pythonhosted.org/packages/53/94/a3a7698e9b1a395e1eb99ccd9a324be9347973bff4e72db2a06496d7cd27/charset_normalizer-3.5.2-cp314-cp314-win_arm64.whl", hash = "sha256:80d02b6f04e92601a081dd97b23d3128033098bff5d35d392ddcc0476ea11253", size = 200406, upload-time = "2026-09-30T04:36:59.764Z" }, + { url = "https://files.pythonhosted.org/packages/c1/48/c5dd00d5ef7791f02666de250a5bb6071e29b7e133cf4b835800b6d3bc27/charset_normalizer-3.5.2-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:dca9ab98072a5a54ebacebdc45f53e645336b320c667410b061be1ca588ae709", size = 396871, upload-time = "2026-09-30T04:37:01.543Z" }, + { url = "https://files.pythonhosted.org/packages/12/c8/8379554b42e8368161d898476686947a0fdbd3e8865170d7909dcabfdee8/charset_normalizer-3.5.2-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f0aa869112ef88429ae17820d99c3dd9504c9e9c671d3c246f3d7442cb051084", size = 249711, upload-time = "2026-09-30T04:37:03.111Z" }, + { url = "https://files.pythonhosted.org/packages/4a/eb/2ddb1035d17320caa9f41682935123a9a250277b261c3efc86b2d2a21343/charset_normalizer-3.5.2-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:c0afc6800ba57ccc350374c5bd6150419915d95ce93cdbab2d783d75eaf30ecb", size = 231146, upload-time = "2026-09-30T04:37:04.721Z" }, + { url = "https://files.pythonhosted.org/packages/4a/24/2ecb4bde104322cd7859d6594fcfa74649f8d90b3221c9feecbef149875b/charset_normalizer-3.5.2-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:7dcd882da75ef9adf94903b1e3b9419e8aa8fb4c7396822b834b9ef7fb96954f", size = 271552, upload-time = "2026-09-30T04:37:06.295Z" }, + { url = "https://files.pythonhosted.org/packages/3f/98/9d5f6ebc3aee9fef5d30b4aff11fb2ab7a1222b4064f8ef2c7c87cde217a/charset_normalizer-3.5.2-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2e06a3a98f916dd41d27f3105e02e7a40181c98c94b9158733d03a6f80506c09", size = 269810, upload-time = "2026-09-30T04:37:07.905Z" }, + { url = "https://files.pythonhosted.org/packages/09/e1/a3b06a10461b1b7628853c934c644e03bc28e42767116afb52f19a56519b/charset_normalizer-3.5.2-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6bd128f206a7752ae1f2ab6c61bf8a24ba28913a10df8b14c2637b973ff97a80", size = 259845, upload-time = "2026-09-30T04:37:09.554Z" }, + { url = "https://files.pythonhosted.org/packages/fd/d3/6f561f74a296cf27d61775a1dc665ad13f3bff6a798810ca05907f37a7c4/charset_normalizer-3.5.2-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c8f3d67aeaf55f017982b73683f0e7342ba2f6635a78f69ce89ebb26aa411e5c", size = 252825, upload-time = "2026-09-30T04:37:11.274Z" }, + { url = "https://files.pythonhosted.org/packages/26/9f/69e13ca3b18f43e0eafcd34c04a45b732ae22a43b54a5fc9e119103356eb/charset_normalizer-3.5.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:fe9753dfee015c570d73df76f899f18444d41388bffcde097deba51c4fadbb9f", size = 252659, upload-time = "2026-09-30T04:37:12.941Z" }, + { url = "https://files.pythonhosted.org/packages/73/a9/ace29806a0dae18939919c76ba526472d83214afa101105fabff2cf30625/charset_normalizer-3.5.2-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:92888bb3187c5ba50500b00b3b310c9f2c651709d28036077680cb5255450a03", size = 238819, upload-time = "2026-09-30T04:37:14.659Z" }, + { url = "https://files.pythonhosted.org/packages/f8/c1/6116d52a2e3311ec80f21f5fb5e17b27405f10b9608af8f6e69516841a1b/charset_normalizer-3.5.2-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:d008d90a7f2471519aef0c90dfbe73b3e6e4d5e66ac48e19154c17e89e98b604", size = 272973, upload-time = "2026-09-30T04:37:16.346Z" }, + { url = "https://files.pythonhosted.org/packages/19/aa/9955c7e93bba10a9c7e8f7a5031b7ced66f3a1883a55c00712b8d5850ff3/charset_normalizer-3.5.2-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:31f3930700408d211f13378ccbe1c40845d8da54bd0681fac3a9b5aae81c7aa8", size = 253692, upload-time = "2026-09-30T04:37:18.212Z" }, + { url = "https://files.pythonhosted.org/packages/bb/33/2a6ae7fdc1b10cb581cef91addd8cdfc5f40d50abb5702309369d5834579/charset_normalizer-3.5.2-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:2a925889534b3748302dae5dead07cc13480de1dac3aea80a941b729b471ef93", size = 268757, upload-time = "2026-09-30T04:37:19.877Z" }, + { url = "https://files.pythonhosted.org/packages/a2/22/80992720a0282cd39bba1db35868e6b9c22f41281160143a836544bc1d8a/charset_normalizer-3.5.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:f5ec61164adcec446f8969a3358ec3f9b26bbda3b9213e5586d219afa8df2915", size = 262220, upload-time = "2026-09-30T04:37:21.583Z" }, + { url = "https://files.pythonhosted.org/packages/92/9f/181fd07e1bffea1d95cd80c84ac537354f50699c22cfc4d3c02b6fc16208/charset_normalizer-3.5.2-cp314-cp314t-win32.whl", hash = "sha256:598a11a2c7ebaa5334bf698bf29568c9c390abac6a154d8170fedecd1cea38c5", size = 197797, upload-time = "2026-09-30T04:37:23.235Z" }, + { url = "https://files.pythonhosted.org/packages/49/1c/25d8415ec1c4f2f41f1680435e4c87cfb378ff2f677d950946f2a45d0632/charset_normalizer-3.5.2-cp314-cp314t-win_amd64.whl", hash = "sha256:7fdde2c9fd9e3eca40631e024664cf2584272cc8f96308cbe5fdfc930f51d8bc", size = 222765, upload-time = "2026-09-30T04:37:24.891Z" }, + { url = "https://files.pythonhosted.org/packages/3e/b4/46b48f013dadfc0d0d33b375438e31bdf5a989dc68389c6bf627054d4df9/charset_normalizer-3.5.2-cp314-cp314t-win_arm64.whl", hash = "sha256:d1befeed746d247c81127bb14de9dc3d30edb6e5976d34f83f86ed262b1d9105", size = 210985, upload-time = "2026-09-30T04:37:26.634Z" }, + { url = "https://files.pythonhosted.org/packages/ca/e9/34e597dee616d0b8ee4b34d29399e85c2204ade174157a48505d42baa4ff/charset_normalizer-3.5.2-cp315-cp315-macosx_10_15_universal2.whl", hash = "sha256:87475fabc8d9996fd9c27debb395e642e8c838d78a00b6e932227a0e06b81e26", size = 367676, upload-time = "2026-09-30T04:37:28.329Z" }, + { url = "https://files.pythonhosted.org/packages/60/9f/a5d1c91c0263745e2cd344c5a4415d787c575501ab1d449f1148ac6b495d/charset_normalizer-3.5.2-cp315-cp315-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9409a8bf35cf78353942504b24a57de3d75b708997a1e4bd8db71ac8633ce364", size = 248414, upload-time = "2026-09-30T04:37:30.167Z" }, + { url = "https://files.pythonhosted.org/packages/26/79/e697f77464748a3ee3cf490c83d592459400d4898380d66c38366b03080c/charset_normalizer-3.5.2-cp315-cp315-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:498dc3188ca05a68231ac3fdbfc7f57eb67e1343c30e0fea17f8218c1599b253", size = 244775, upload-time = "2026-09-30T04:37:31.964Z" }, + { url = "https://files.pythonhosted.org/packages/ca/87/3d42a42e18ea066e2513936fd678a00696e77878b5ae04528976abdbcb83/charset_normalizer-3.5.2-cp315-cp315-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:e242bb1c5e76e97dfa9e7f209a71e93a01d7f19ffdd5cfbb2e2d55b4f08f8ab0", size = 273877, upload-time = "2026-09-30T04:37:33.661Z" }, + { url = "https://files.pythonhosted.org/packages/c3/76/8a28136f3938ba9836f84280ce0c4d61ed1cf15a036b2034900c62634162/charset_normalizer-3.5.2-cp315-cp315-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:def79fa35ef0cef8d2accec024f4fdc7ead3012ff02f5215c783f39f03ef8cfc", size = 269455, upload-time = "2026-09-30T04:37:35.573Z" }, + { url = "https://files.pythonhosted.org/packages/a0/a1/4fbf5d0f0f1b2a080474c1cf9a2f12c4c6531bb0e8ba591055e846d2b4e9/charset_normalizer-3.5.2-cp315-cp315-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3df041de8887954562c9b261cba85ca0e9ded74048daf125f45edcfaa4832229", size = 257336, upload-time = "2026-09-30T04:37:37.397Z" }, + { url = "https://files.pythonhosted.org/packages/ba/a2/8b50aa320adb880ad579518e6f718f24944804b42a88b83d267d5d444125/charset_normalizer-3.5.2-cp315-cp315-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:04851f73ae72b8413dddadb16a49dfee95263553741fd42d546f7d66907e6be5", size = 257584, upload-time = "2026-09-30T04:37:39.522Z" }, + { url = "https://files.pythonhosted.org/packages/a5/57/50e3fed84e175f40349bd0da7a4fce94c87f0378f52d74f511d89e0bdc20/charset_normalizer-3.5.2-cp315-cp315-musllinux_1_2_aarch64.whl", hash = "sha256:183b88127acdb4fabe59d951ab424faf1af7b63cdbb5f776186c1ea2ffcaed98", size = 251854, upload-time = "2026-09-30T04:37:41.23Z" }, + { url = "https://files.pythonhosted.org/packages/d6/54/f7fbb3493c9f49091213b9c2d6dd65800696f1ce1a3f196a4205f50417b1/charset_normalizer-3.5.2-cp315-cp315-musllinux_1_2_armv7l.whl", hash = "sha256:16fa0eccf81304b79c5cd87f9271c3b85dd9dd99245e4422ae9c0dd45e0f99d3", size = 248767, upload-time = "2026-09-30T04:37:42.883Z" }, + { url = "https://files.pythonhosted.org/packages/d9/37/b3a6385acc5a1e45b39ae9c90bfb9cf838a09b9dd37ef2740ab4c6b4a2eb/charset_normalizer-3.5.2-cp315-cp315-musllinux_1_2_ppc64le.whl", hash = "sha256:7441d755b7ab94f8d4eb3e43ec05482d760842fd263d003a99102d742cd835e2", size = 274479, upload-time = "2026-09-30T04:37:44.658Z" }, + { url = "https://files.pythonhosted.org/packages/89/44/809913e2cfd279e635a9294fdbbfb1b1dc62a8189d473d561f649fce98d8/charset_normalizer-3.5.2-cp315-cp315-musllinux_1_2_riscv64.whl", hash = "sha256:ca403d7e4798f525fdfc78e258820419cbbd0f0ecbab9de7840e3c017cf6b8cf", size = 258310, upload-time = "2026-09-30T04:37:46.529Z" }, + { url = "https://files.pythonhosted.org/packages/af/a2/f28400ab13359d91bd39179df8e149376b9bf36588e739a3a4f9de2b84b2/charset_normalizer-3.5.2-cp315-cp315-musllinux_1_2_s390x.whl", hash = "sha256:df29a0a7107f7011e77f4eebdddec4c7331e24d787a0b21a46d63bdf7445da95", size = 271100, upload-time = "2026-09-30T04:37:48.399Z" }, + { url = "https://files.pythonhosted.org/packages/e9/89/9bab37955edf0adb3b66f8a3a6617d9f2f487e0d56f295a6a286cb640aa6/charset_normalizer-3.5.2-cp315-cp315-musllinux_1_2_x86_64.whl", hash = "sha256:f3c96f633825733f735c5a9cf21d21a257d8e1edf0b1cee0a064b9c424ca0f7d", size = 259936, upload-time = "2026-09-30T04:37:50.023Z" }, + { url = "https://files.pythonhosted.org/packages/23/b5/4459e08d45a679f903d50fea08bc52cfa728cca4d7bd02c757b5e5abda2e/charset_normalizer-3.5.2-cp315-cp315-win32.whl", hash = "sha256:281cb91036248400f4cc957495cccd44c275c2e0c5854f7e45ac5cf7dc193847", size = 186301, upload-time = "2026-09-30T04:37:51.722Z" }, + { url = "https://files.pythonhosted.org/packages/98/e8/55d5fd3935b4bce6da4fe0df61898e8c82653e317e677bd58aceb9c60f13/charset_normalizer-3.5.2-cp315-cp315-win_amd64.whl", hash = "sha256:89b53f3cda69831909888e0494f4fa0bcd3537e3e138dabeb620bd6ad946bae8", size = 210858, upload-time = "2026-09-30T04:37:53.427Z" }, + { url = "https://files.pythonhosted.org/packages/a9/5b/974423c2fd8e524c7a7f64318c1e02240ef954912fa2b4d70344107b9c68/charset_normalizer-3.5.2-cp315-cp315-win_arm64.whl", hash = "sha256:6be488a102b8cf28d0391d8c4ba7748938ae28b78ad901f8585520fca33ead1a", size = 200309, upload-time = "2026-09-30T04:37:55.015Z" }, + { url = "https://files.pythonhosted.org/packages/ee/f9/00ee0195db1013d8f7c416fd770fbeb560bb46eb2e36b054d05cb56f6cfa/charset_normalizer-3.5.2-cp315-cp315t-macosx_10_15_universal2.whl", hash = "sha256:915563965d418f986e7e145accc592eae9e1a1be3566ff98a05d7a9ec42a76e1", size = 395343, upload-time = "2026-09-30T04:37:56.743Z" }, + { url = "https://files.pythonhosted.org/packages/04/3a/c00b50e94c964cf934c7899cd47c97952fc11dad71cc5884b3c61795b09b/charset_normalizer-3.5.2-cp315-cp315t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:65cd72beeeca9d3aaea1201e5923859f308f952f9c71de93f06063c79f0f7a3b", size = 250114, upload-time = "2026-09-30T04:37:58.607Z" }, + { url = "https://files.pythonhosted.org/packages/50/27/d102dc880bbcffd0479ab64dfc1fb96777a854355a55e2bda72a71efadcb/charset_normalizer-3.5.2-cp315-cp315t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:b7fd005a73d9e657273b7a10dc71a9e03c8fb9ee6999798d6918ce095b81ac7f", size = 239997, upload-time = "2026-09-30T04:38:00.511Z" }, + { url = "https://files.pythonhosted.org/packages/a5/4a/bf7ef45794dd293fab5f98a9309817977fbb845b9998f171b8cc5d8437a3/charset_normalizer-3.5.2-cp315-cp315t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:e54da4baf05720032d527874d40b65fa4d7e5c6c6a43d0c3adbeffcaf275a2b3", size = 272313, upload-time = "2026-09-30T04:38:02.509Z" }, + { url = "https://files.pythonhosted.org/packages/e8/ee/008a2837737991474c5754bb3191010007663860979701990982a502cbaf/charset_normalizer-3.5.2-cp315-cp315t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:124fbf1a8ff966d87ae05bb8bd45a71f966055ed8bba320d0c7cf450bc5f4d0e", size = 269986, upload-time = "2026-09-30T04:38:04.435Z" }, + { url = "https://files.pythonhosted.org/packages/93/ad/bd74a283940dc910c5b14f8e4f80a248082bc9c0fcbe1f54530cb6d9cc5e/charset_normalizer-3.5.2-cp315-cp315t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:28b4f0d66fb834ff90f28209ac7bce77868c45d8c93e26f906709d9b7c2e1af9", size = 260202, upload-time = "2026-09-30T04:38:06.549Z" }, + { url = "https://files.pythonhosted.org/packages/8a/7b/ed341c66f69f688723501fac752be3d63c7159ca0d0d4174fc611e5710bb/charset_normalizer-3.5.2-cp315-cp315t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:58ca3755ee7ff7f59b57789ec9833c9de9ea275405cdd240eda1f193112e398a", size = 259083, upload-time = "2026-09-30T04:38:08.311Z" }, + { url = "https://files.pythonhosted.org/packages/cc/9d/e41588b777965e5031a43128a1e96173ebb35ac75fc53ec3b517e7c21cd4/charset_normalizer-3.5.2-cp315-cp315t-musllinux_1_2_aarch64.whl", hash = "sha256:443eae2bf318abeaf6f15d785138f71fd6de770e99a92158b8b814265e079115", size = 253081, upload-time = "2026-09-30T04:38:10.402Z" }, + { url = "https://files.pythonhosted.org/packages/81/35/b761eb6d8c1eb218b9b42b9b4d5ac902afdc399fb6dac6f9a9aac7bda589/charset_normalizer-3.5.2-cp315-cp315t-musllinux_1_2_armv7l.whl", hash = "sha256:58f361dcbab699cf8f42db3f47c8e7fd1036f138c23a5d08de9fde5f425a730c", size = 248712, upload-time = "2026-09-30T04:38:12.317Z" }, + { url = "https://files.pythonhosted.org/packages/4d/2c/147169a041b747759f37405c0a97157e8e92de967968373101ff14915cba/charset_normalizer-3.5.2-cp315-cp315t-musllinux_1_2_ppc64le.whl", hash = "sha256:1b4cbc7c3491ccb4aa17fcd8165649d01cf39f76de1696da8631b5f71b85401d", size = 274176, upload-time = "2026-09-30T04:38:14.138Z" }, + { url = "https://files.pythonhosted.org/packages/f0/2d/0ff8db0d373ba8538db686db11cd7e8912031490b9e4f383b41912e8d594/charset_normalizer-3.5.2-cp315-cp315t-musllinux_1_2_riscv64.whl", hash = "sha256:ba0b1d2620edf869789c3879223f52bf2afc5d31b3cb47cc57b3a12c05e2aa9d", size = 259413, upload-time = "2026-09-30T04:38:15.841Z" }, + { url = "https://files.pythonhosted.org/packages/8a/8e/b4a085fb47c9d3a7e43576a4784fdd8fe23f907514a972de8086edaf7a48/charset_normalizer-3.5.2-cp315-cp315t-musllinux_1_2_s390x.whl", hash = "sha256:5e2b6b57e9733d39f0c9fd3185efa6b8e29652c4cd8fe94180272cf6ed9a78c4", size = 269434, upload-time = "2026-09-30T04:38:17.626Z" }, + { url = "https://files.pythonhosted.org/packages/83/1c/d8d8d7322a7c3eecdf3237a4a419cf41d2eaad8e006ce7dfdd9d4c8fa2eb/charset_normalizer-3.5.2-cp315-cp315t-musllinux_1_2_x86_64.whl", hash = "sha256:51cf45226a9b588d0d2b4880c62d686934b63ab0bd79ca23ab0e9762eb27441b", size = 262716, upload-time = "2026-09-30T04:38:19.214Z" }, + { url = "https://files.pythonhosted.org/packages/a0/16/0e4c6ba9b44e97a2da150e52d331e8f9c968b21b358fbffa6c856cebcd89/charset_normalizer-3.5.2-cp315-cp315t-win32.whl", hash = "sha256:5fb29fb8cd1a46c27a1bf9613ad5ec2599310d46b4025d9556404a6b6a292800", size = 197159, upload-time = "2026-09-30T04:38:21.037Z" }, + { url = "https://files.pythonhosted.org/packages/be/33/e90bc2b1374f7f36ef106f56620de5a783907e19ca857efe2277e31cac3e/charset_normalizer-3.5.2-cp315-cp315t-win_amd64.whl", hash = "sha256:a192e2c40070d92c3ccf777e3a5c4ff515573cd2bb7ed0c537fdadbbec5bbf21", size = 221322, upload-time = "2026-09-30T04:38:22.886Z" }, + { url = "https://files.pythonhosted.org/packages/66/89/dfa6dcb08c200b7830ab56439e8c1890f2971d51aafbb3937894a2e7fcfc/charset_normalizer-3.5.2-cp315-cp315t-win_arm64.whl", hash = "sha256:749e97e1b32313717a565abbe321bc2190bc8b35f1a67e4cdbc7c56c8d8ffe58", size = 209192, upload-time = "2026-09-30T04:38:24.648Z" }, + { url = "https://files.pythonhosted.org/packages/8c/ab/176fbfd5b64939c55d652366aa5b9ef1d767af207a3aa6ebeb0d226c484d/charset_normalizer-3.5.2-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:4275811936e2f06feff5e598fb42a1b7ae852da8e39605211892b56b81a34efd", size = 331815, upload-time = "2026-09-30T04:38:26.216Z" }, + { url = "https://files.pythonhosted.org/packages/7e/84/371eac6b30bdbcbf2d632a1a01809103459216fcaae61b8b8d922c1bfb8a/charset_normalizer-3.5.2-cp37-abi3-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:1c50fe28bbc2ced33386f298650d91218076c05420e6cbd790b913adc41659e7", size = 253276, upload-time = "2026-09-30T04:38:28.032Z" }, + { url = "https://files.pythonhosted.org/packages/43/6f/c4fbae58febff71709c51bc7e18fdfa55341dc382704740f9f0cbf03817b/charset_normalizer-3.5.2-cp37-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d19fbd981a488e22cd04883659ca6b08f50b5974f9fd7c95655ef6a043e5893f", size = 241239, upload-time = "2026-09-30T04:38:29.732Z" }, + { url = "https://files.pythonhosted.org/packages/61/71/458c3f42164a07d0c5210798e9e704b39e540a6793b05aba67f3a35243a9/charset_normalizer-3.5.2-cp37-abi3-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:0fed1d06615f022ee3b13caf5e8b180cfea32bb2c5aded8a9d44277afc040f93", size = 231121, upload-time = "2026-09-30T04:38:31.462Z" }, + { url = "https://files.pythonhosted.org/packages/09/54/ab9e89367076f6331bb6c65c4bf14a5361fa5191cb6561bf534f18504e1b/charset_normalizer-3.5.2-cp37-abi3-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:838dcc90063569a0448120554591a1d6c4a4ffe11babf048908793154ab86ade", size = 260350, upload-time = "2026-09-30T04:38:33.239Z" }, + { url = "https://files.pythonhosted.org/packages/7c/c1/061431ecc688d9d76602502cb57cc01e691e682c18f1beb45f9673b5bbd2/charset_normalizer-3.5.2-cp37-abi3-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2ce45c6627b22c47e390bc91a41c3d13032192e699fa0bea96e9671b373d69b0", size = 255430, upload-time = "2026-09-30T04:38:34.865Z" }, + { url = "https://files.pythonhosted.org/packages/8d/1f/20c8949f0676f7ab811abdeb7f4d7f1cbc6e61ff20bef08b44edeb092bc8/charset_normalizer-3.5.2-cp37-abi3-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0774bf9bf620249fee3e0b8b9fd3065de213be30f3aa94ce2494b3b638949e26", size = 250612, upload-time = "2026-09-30T04:38:36.649Z" }, + { url = "https://files.pythonhosted.org/packages/2b/9e/46f2fa4c431fc98c4ae76a8cb5bdca54e0341e3cfc3fcfd8e82740250818/charset_normalizer-3.5.2-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:1db38f4c5496827c1a501846d64d14c3b80c7e6714e406cd7dc36a9899fa1011", size = 242083, upload-time = "2026-09-30T04:38:38.26Z" }, + { url = "https://files.pythonhosted.org/packages/bd/39/559be29a0c0f086e0bba6922babd38916cc5e0b58ced4de13ee01ea05508/charset_normalizer-3.5.2-cp37-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:304d8e4d493af723536393eee0c689eb7813f4a474c8b479dee63f1fdd98f621", size = 232738, upload-time = "2026-09-30T04:38:39.81Z" }, + { url = "https://files.pythonhosted.org/packages/ff/6c/387b0e4f756a282831c1d9fc6aeb6c51ca4507ca202767c8de15ce9b12e2/charset_normalizer-3.5.2-cp37-abi3-musllinux_1_2_ppc64le.whl", hash = "sha256:9b7f416ff0978e2f2249330527f0ad6fa02f4932e6199692d3b52da2048c19e4", size = 260703, upload-time = "2026-09-30T04:38:41.346Z" }, + { url = "https://files.pythonhosted.org/packages/96/92/1fdf015f09ef449f50d3ac4b67c90887c9c318b727daa95cc4f866e6521d/charset_normalizer-3.5.2-cp37-abi3-musllinux_1_2_riscv64.whl", hash = "sha256:01077390b03f7988f11d700a2194e69b119741a86b1a638b1db88891e3eced8e", size = 247622, upload-time = "2026-09-30T04:38:42.937Z" }, + { url = "https://files.pythonhosted.org/packages/dc/3c/8e7b8a5671ad5d433669fb2a76f1a0164df2d9b1718b0206bc2a16d840cc/charset_normalizer-3.5.2-cp37-abi3-musllinux_1_2_s390x.whl", hash = "sha256:7e841fb9010836c992c9f12fcbd43a831de93a5f726fc1ccd8ca1d0268c5014c", size = 257500, upload-time = "2026-09-30T04:38:44.604Z" }, + { url = "https://files.pythonhosted.org/packages/b4/f0/45b579df5cabc1d5d53ea1cc35e8437d3ca768c0acccc7041517cb6fbb32/charset_normalizer-3.5.2-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:9cae88599c7219005d879f98e5ed53341e9a122af585e1091200358a3003d2a0", size = 255100, upload-time = "2026-09-30T04:38:46.289Z" }, + { url = "https://files.pythonhosted.org/packages/31/68/fdec18a343f5fb3f310588dd478b09ac4799e0b187dbade3a8cd776f03ef/charset_normalizer-3.5.2-cp37-abi3-win32.whl", hash = "sha256:01b0c0d2262a9e28e8484a278c7e1b5d650e3ac8cf2683d2967e25899f208bdf", size = 174499, upload-time = "2026-09-30T04:38:47.999Z" }, + { url = "https://files.pythonhosted.org/packages/9d/8a/b618149cc5207943a0242068d7a27897f56a62947b5a039085f2a22029f8/charset_normalizer-3.5.2-cp37-abi3-win_amd64.whl", hash = "sha256:9f56f72050826f63dcee7a7f55b0a77168cb3bfc553fd405e7f8f9ece75a4036", size = 200092, upload-time = "2026-09-30T04:38:49.707Z" }, + { url = "https://files.pythonhosted.org/packages/03/cf/4c66866fa9e2b1c78e3c911516d1de497a677b7ac60f1eceda74ce777ca3/charset_normalizer-3.5.2-cp37-abi3-win_arm64.whl", hash = "sha256:40ab6bffa02ae10a0581e6c198be7d2d8ca5c2a0c64e4ed3465d766df457573e", size = 294363, upload-time = "2026-09-30T04:38:51.312Z" }, + { url = "https://files.pythonhosted.org/packages/fc/ad/d07d7862a62ffa6d79d68074d14823243dd235a77c45262acbf6adeb28bf/charset_normalizer-3.5.2-py3-none-any.whl", hash = "sha256:b6b751274acb69d77b3323d6b7dbaa3c7fdfc1eb829b7eb61d262f32e1af9685", size = 68872, upload-time = "2026-09-30T04:39:21.828Z" }, +] + [[package]] name = "click" version = "8.5.0" @@ -105,6 +199,18 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" }, ] +[[package]] +name = "colorlog" +version = "6.12.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "colorama", marker = "sys_platform == 'win32'" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/8c/55/ba79756cb90c8d69d599d57785398ac87bba7b19c80e87f4e8a562197c93/colorlog-6.12.0.tar.gz", hash = "sha256:2a7924c1dadf18b22a0eb8b06d1c7b01d5341707ec1641eb6fcc4fde0c3e8e5f", size = 18151, upload-time = "2026-07-23T13:40:40.71Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/d4/19/0b6647bf5e331521e55d2b63bfbdc210bd9cd605189273f03614a05f702d/colorlog-6.12.0-py3-none-any.whl", hash = "sha256:30d392604e9110045a2c2aeefc27d7a017abbab63f3a8aee594eac0801df784e", size = 12239, upload-time = "2026-07-23T13:40:39.562Z" }, +] + [[package]] name = "crawler" version = "0.1.0" @@ -113,17 +219,20 @@ dependencies = [ { name = "httpx" }, { name = "legacy-doc" }, { name = "lxml" }, + { name = "onnxruntime" }, { name = "openpyxl" }, { name = "playwright" }, { name = "pydantic" }, { name = "pypdf" }, { name = "python-docx" }, + { name = "rapidocr" }, { name = "xlrd" }, ] [package.dev-dependencies] dev = [ { name = "datamodel-code-generator" }, + { name = "pillow" }, { name = "pyright" }, { name = "pytest" }, { name = "ruff" }, @@ -137,17 +246,20 @@ requires-dist = [ { name = "httpx", specifier = ">=0.28" }, { name = "legacy-doc", specifier = ">=0.2.1" }, { name = "lxml", specifier = ">=6.1.3" }, + { name = "onnxruntime", specifier = ">=1.31.1" }, { name = "openpyxl", specifier = ">=3.1.5" }, { name = "playwright", specifier = ">=1.64.1" }, { name = "pydantic", specifier = ">=2.14.1" }, { name = "pypdf", specifier = ">=7.0.0" }, { name = "python-docx", specifier = ">=1.2.0" }, + { name = "rapidocr", specifier = ">=3.10.0" }, { name = "xlrd", specifier = ">=2.0.2" }, ] [package.metadata.requires-dev] dev = [ { name = "datamodel-code-generator", specifier = ">=0.86.0" }, + { name = "pillow", specifier = ">=13.0.0" }, { name = "pyright", specifier = ">=1.1.400" }, { name = "pytest", specifier = ">=9.1" }, { name = "ruff", specifier = ">=0.17" }, @@ -194,6 +306,14 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/c1/8b/5fe2cc11fee489817272089c4203e679c63b570a5aaeb18d852ae3cbba6a/et_xmlfile-2.0.0-py3-none-any.whl", hash = "sha256:7a91720bc756843502c3b7504c77b8fe44217c85c537d85037f0f536151b2caa", size = 18059, upload-time = "2024-10-25T17:25:39.051Z" }, ] +[[package]] +name = "flatbuffers" +version = "25.12.19" +source = { registry = "https://pypi.org/simple" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/e8/2d/d2a548598be01649e2d46231d151a6c56d10b964d94043a335ae56ea2d92/flatbuffers-25.12.19-py2.py3-none-any.whl", hash = "sha256:7634f50c427838bb021c2d66a3d1168e9d199b0607e6329399f04846d42e20b4", size = 26661, upload-time = "2025-12-19T23:16:13.622Z" }, +] + [[package]] name = "genson" version = "1.4.0" @@ -540,6 +660,108 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/54/c8/12811c9b48fde162bb72b6f2e78fada9a247a09d7bb5be2050a5d099c77b/nodeenv-1.11.0-py2.py3-none-any.whl", hash = "sha256:edaa16e6c14d7cf395d75d4bbd5a26390f4dc06501a33b4e76282b02cc688a25", size = 34277, upload-time = "2026-09-26T11:29:19.933Z" }, ] +[[package]] +name = "numpy" +version = "2.5.4" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/95/b0/c7453d0b6e2073c3264468b106ee1563750cecc910965e67357e3698c83e/numpy-2.5.4.tar.gz", hash = "sha256:9a94cf751c9ad8ebaa835bcd3d40dacf8534ad086b88c38029b65123c7999d2a", size = 20866315, upload-time = "2026-10-10T20:05:31.422Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/99/ba/005cb5edd580d2f84d7ca3206b92dc17d4388e56e6f87ffe8f2762f83139/numpy-2.5.4-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:c668b2f0d651605b58892644b0e302c7157f7159544227758c896982ef384b18", size = 17005499, upload-time = "2026-10-10T20:03:37.961Z" }, + { url = "https://files.pythonhosted.org/packages/f3/49/fee7587c33ee35f7977f9051d7f2023d4e7246d62710c80f20c2361ea232/numpy-2.5.4-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:ffa6ce09a1c6a08e9667dd9c97aa0b14184e8d18f2a14b78b2a2328c9147f076", size = 12019666, upload-time = "2026-10-10T20:03:40.606Z" }, + { url = "https://files.pythonhosted.org/packages/d5/b2/c6ce165acffceb15a82c07b9cc77d391f86b3f379ba62911908ae5d34b91/numpy-2.5.4-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:956555e0603a4d38019ae6925711cb9dc43195c076a928accf7ea5d50bddfe53", size = 5455617, upload-time = "2026-10-10T20:03:43.138Z" }, + { url = "https://files.pythonhosted.org/packages/77/7f/dd85ce260a669a89be06842cf355d7353a33e6cfbc590fb8ebb947d88dc9/numpy-2.5.4-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:2c2c4afffdeb7920e445028dd71eb932cac3e704792e964bc2a232426d4f1255", size = 6791932, upload-time = "2026-10-10T20:03:44.874Z" }, + { url = "https://files.pythonhosted.org/packages/63/d6/34b0a2b0741386a63025a65a2c09caaaaaad6d0ca95b66cd65c30dd7fcb5/numpy-2.5.4-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4054173604cd8658796053f1f3bc0befb68ec1c0762c57fdad61e199256a8617", size = 15710899, upload-time = "2026-10-10T20:03:46.839Z" }, + { url = "https://files.pythonhosted.org/packages/16/d5/928078d2b28f26829b138b4a6c3980045022fb409f570657a224ae60ef4e/numpy-2.5.4-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d549420b8858885cea8838a727842249218b9c1da24dd517e25c9c7a948310a3", size = 16721710, upload-time = "2026-10-10T20:03:49.489Z" }, + { url = "https://files.pythonhosted.org/packages/f9/cf/673fd1b8f4cd78eb6320e87ec4c90ac19c095644259e3749853a405c70f4/numpy-2.5.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:823874a507a84af050493b622affde94b6f7c3a0dc22cb2801381bc03b871c00", size = 17066182, upload-time = "2026-10-10T20:03:52.25Z" }, + { url = "https://files.pythonhosted.org/packages/f3/92/a77b5061b1b3e2643928c37976d79ee173e1b171ed158b7a3c61056b41bc/numpy-2.5.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:4e263278bfb5ee6409db8aedbc4cc32973b1b82bc1e8d3c668551d04d83a7e37", size = 18480315, upload-time = "2026-10-10T20:03:55.39Z" }, + { url = "https://files.pythonhosted.org/packages/bb/1d/1486ef3d3fb2279fd93c4c43c1bbbf1ca389a19816696684409f71babaab/numpy-2.5.4-cp314-cp314-win32.whl", hash = "sha256:cfd73180400042a7c532d30c5e287bdd03c59ff9ee1b4c0316af0539e29dfe23", size = 6185739, upload-time = "2026-10-10T20:03:58.186Z" }, + { url = "https://files.pythonhosted.org/packages/52/9a/e1e512ebc948d5b9dd33b08736760f0ebbed2848fd4eda1f553088a6dcee/numpy-2.5.4-cp314-cp314-win_amd64.whl", hash = "sha256:2ca144f15135b6212a5c47b1e2aeca6e412f102f95a2d5d88d8aec77eb255de3", size = 12703552, upload-time = "2026-10-10T20:04:00.28Z" }, + { url = "https://files.pythonhosted.org/packages/2c/05/de709a982d7bbcd688a3fad71f002e9ff80c2db39e03ee726609b610f1d1/numpy-2.5.4-cp314-cp314-win_arm64.whl", hash = "sha256:468397ba3c64427474706e5c9123fe266395496714dc684294eac75cd4930d1e", size = 10803901, upload-time = "2026-10-10T20:04:02.659Z" }, + { url = "https://files.pythonhosted.org/packages/13/34/083570ada3bb2a30fbe5d77c8c6fef9141144a15d33e6f793a67e9749ab8/numpy-2.5.4-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:1ef3aa6d7e29bb13677323114280b05acc57607fa2300e66432d665d5418a162", size = 12138695, upload-time = "2026-10-10T20:04:05.012Z" }, + { url = "https://files.pythonhosted.org/packages/94/06/1f9c24db48eef0c2d1207e3b11fffb0478e39dfd8c1e1be7476936885eed/numpy-2.5.4-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:98b053943e5a0474ec0da309d2cb9d3f18ea57f8a2067c2ab7b5f763d1068380", size = 5574615, upload-time = "2026-10-10T20:04:07.316Z" }, + { url = "https://files.pythonhosted.org/packages/da/0f/593fba2e1560e949123bc7d2fc48b5893d56e58cd4bd5a273d2fbf60b220/numpy-2.5.4-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:b64a85f40e154983960a4167d4c1d57a50c7f109b3d3264a3a984154e90a8454", size = 6889383, upload-time = "2026-10-10T20:04:09.918Z" }, + { url = "https://files.pythonhosted.org/packages/eb/9f/b799dfdce4e05e80ed4bc815c71ff343a11533b2c0ffc221cae8538cda63/numpy-2.5.4-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a813ed7719bf45463c51779e6a98d0385fe905e48447526938a4b8337333d551", size = 15753763, upload-time = "2026-10-10T20:04:12.278Z" }, + { url = "https://files.pythonhosted.org/packages/34/88/16c5f12f86f5ad2817c4d103205131fc6c8acb3d1878af05a1a4f23ec859/numpy-2.5.4-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c9b80cdf5cedba0e90d93fa5f9a333c4d65bd545cd669b71bb97ce2b703c9d73", size = 16757212, upload-time = "2026-10-10T20:04:14.799Z" }, + { url = "https://files.pythonhosted.org/packages/ff/4f/a1fe40e18a898e6a5089f4f0d891f0a493eb0574d5b34458f0fbe5aa3e5c/numpy-2.5.4-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:2199ed071f460487c8db2c0e5c0b564494190edb4772fe80f9aad88b2604def5", size = 17116471, upload-time = "2026-10-10T20:04:17.58Z" }, + { url = "https://files.pythonhosted.org/packages/aa/46/e923a11c78e65c1722e7aaad817c06bd591324174b9d28ce5d31eee4d432/numpy-2.5.4-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:64f9c9878c1938476365e11ccfb6b770f3b9e5f045ccddc514235041e6959365", size = 18524063, upload-time = "2026-10-10T20:04:20.365Z" }, + { url = "https://files.pythonhosted.org/packages/5a/fa/84ab064514440c1f64a1b21088f2c82756defdd05e07c75ab233899565b2/numpy-2.5.4-cp314-cp314t-win32.whl", hash = "sha256:64d1c8ac28a4077cf987e0a71a7a0ef7e2df70722f07f0baa42dbb7eb6938647", size = 6340926, upload-time = "2026-10-10T20:04:22.865Z" }, + { url = "https://files.pythonhosted.org/packages/7e/7e/6cd886876f435b10685db9b9f7eeb70356f99e052116f4e5f11c5792c714/numpy-2.5.4-cp314-cp314t-win_amd64.whl", hash = "sha256:067374eb538c34c745436365cf7b0112595c1d326f21ce4ff340f61230239fbb", size = 12901584, upload-time = "2026-10-10T20:04:24.99Z" }, + { url = "https://files.pythonhosted.org/packages/38/1b/3c1684f6a06f7307f2335fca6e486cb162847fb97e91d65f8eb5cabad213/numpy-2.5.4-cp314-cp314t-win_arm64.whl", hash = "sha256:e94aef2c639da4a960ad0db8e06471208d8589974953d78b61d345b4eb99e394", size = 10891152, upload-time = "2026-10-10T20:04:27.52Z" }, + { url = "https://files.pythonhosted.org/packages/08/f4/3224deff3af2bef6bc0b175369698d8cb348f3d91d9bb0286cd5c9eae9e0/numpy-2.5.4-cp315-cp315-macosx_10_15_x86_64.whl", hash = "sha256:8dddfbee2e68d26d0d7d7d9cb247b1fd4409241cce32d815a11d97ec2cfde179", size = 17003231, upload-time = "2026-10-10T20:04:30.021Z" }, + { url = "https://files.pythonhosted.org/packages/be/75/fee0b8c6d94b44b2fdfae74f6a4ad5a138739589a8aebaec28ce4e713ed5/numpy-2.5.4-cp315-cp315-macosx_11_0_arm64.whl", hash = "sha256:81e3420b27048b65eb14c3acf0c174a8cb0e023277716110347d2dcb26026dad", size = 12018300, upload-time = "2026-10-10T20:04:32.519Z" }, + { url = "https://files.pythonhosted.org/packages/47/c0/d0b335a499a04b65f532c3f034346ef390f81299060f928492dabc1e0272/numpy-2.5.4-cp315-cp315-macosx_14_0_arm64.whl", hash = "sha256:0b4724a19de67bea8cfc4970798efa78bcbbe2ac2613cfac16721a42d44de2a5", size = 5454250, upload-time = "2026-10-10T20:04:34.943Z" }, + { url = "https://files.pythonhosted.org/packages/5a/0e/461b3783c03d668052e6a21b01b673db6ffcb7831fd32d9aa5368c1cd426/numpy-2.5.4-cp315-cp315-macosx_14_0_x86_64.whl", hash = "sha256:2132418bf8dd124a427ca9e6a1daf9ee1a87185344c95119ceae868b99466da1", size = 6789644, upload-time = "2026-10-10T20:04:37.258Z" }, + { url = "https://files.pythonhosted.org/packages/b3/02/5dad269b02166965a7b4ca14adaddd75dbee0de42435bfecf561b84ba5a6/numpy-2.5.4-cp315-cp315-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:325518d4245b9e331387702aa58c2ce1dc4cdcbb41dfb4ccd5dcbc7e08db1266", size = 15704353, upload-time = "2026-10-10T20:04:39.616Z" }, + { url = "https://files.pythonhosted.org/packages/93/3a/01360c8036822ed9f7aa32189a77d1476567ec1e8e1383522389e4faac45/numpy-2.5.4-cp315-cp315-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:56733449d2544178beaa4545cee357370440cf056c197f9c7bfb19dbfdd0e86d", size = 16718648, upload-time = "2026-10-10T20:04:42.383Z" }, + { url = "https://files.pythonhosted.org/packages/7d/5c/b863a2c093c4d6f21a597fcaf24ead0835c09ab16a8312d5a5a8868af683/numpy-2.5.4-cp315-cp315-musllinux_1_2_aarch64.whl", hash = "sha256:5ec3753760c1a6d8bb91200666e545c3a9728e6269dfb5d6ce02340996698aa3", size = 17059053, upload-time = "2026-10-10T20:04:44.976Z" }, + { url = "https://files.pythonhosted.org/packages/0a/60/ced4f57f9a1258a0af74f17cb0b0c2700b5c67cd6678823c803b263e4df3/numpy-2.5.4-cp315-cp315-musllinux_1_2_x86_64.whl", hash = "sha256:b1185012870173de7ae33d370bd45b1cf5baee747ea4b97036b65f4e93016877", size = 18477406, upload-time = "2026-10-10T20:04:47.863Z" }, + { url = "https://files.pythonhosted.org/packages/f9/bd/0ef22dafaafcc7d4bb3ca26b8d2afbd55dedad8eaba99a8c864e1997456f/numpy-2.5.4-cp315-cp315-win32.whl", hash = "sha256:298eca75243f2cbbfdb460560b9fb2a1792a33cf2ab4286efd43d92e8d3df508", size = 6185133, upload-time = "2026-10-10T20:04:50.467Z" }, + { url = "https://files.pythonhosted.org/packages/50/bc/d2651b155ecc608a77e6f4d15495c11f14f19bb98f8bf0c5b0d38f86dda1/numpy-2.5.4-cp315-cp315-win_amd64.whl", hash = "sha256:332f3378fe077dd850e677ec01bdcc4f22368fb5d50ef10b2c79230b1bf5a592", size = 12703085, upload-time = "2026-10-10T20:04:52.63Z" }, + { url = "https://files.pythonhosted.org/packages/dc/d2/45e404f8abb26fb9eda12b94012936873e827b1be76f2ee7890be128312e/numpy-2.5.4-cp315-cp315-win_arm64.whl", hash = "sha256:d4cccbbc78717966f764cd3af4fb70276fa01fc7a2688af11c78901fa5c04f05", size = 10801451, upload-time = "2026-10-10T20:04:55.677Z" }, + { url = "https://files.pythonhosted.org/packages/c6/c3/2ae14e09cfdb67dc187a342e15308a21c15bf4d2071f8079e6aee5fe56dc/numpy-2.5.4-cp315-cp315t-macosx_10_15_x86_64.whl", hash = "sha256:950ea81d57ef070665581b6e1b5f6a029306423cd1739c5b95fe78aa30db6b9d", size = 17097121, upload-time = "2026-10-10T20:04:58.403Z" }, + { url = "https://files.pythonhosted.org/packages/f5/cf/305ae624ef8a039414317224abe9ec9c2fe7ea3c2e1cf204d43ff6b2ffb9/numpy-2.5.4-cp315-cp315t-macosx_11_0_arm64.whl", hash = "sha256:c05ede731b03fb1b7591faca9389ade3267d2bddf1ad8882bb3f2cc5e101694f", size = 12135439, upload-time = "2026-10-10T20:05:01.65Z" }, + { url = "https://files.pythonhosted.org/packages/a9/a8/f75c63813aef95827bb2c0d13b12803016853056e8792c280058cdbfe783/numpy-2.5.4-cp315-cp315t-macosx_14_0_arm64.whl", hash = "sha256:5fbf7141bbfd63aea22f435c9062a032b9ea0082fe9845dad7f021d3f1234e71", size = 5571451, upload-time = "2026-10-10T20:05:04.135Z" }, + { url = "https://files.pythonhosted.org/packages/6f/0f/f17763f983868b5c49b4101ebd7e00760bd1769478a6bb6a8de6e085bbac/numpy-2.5.4-cp315-cp315t-macosx_14_0_x86_64.whl", hash = "sha256:3573cd22564692a5b899ec344e5d5b9cc4576f2985b96f22af3564ed54f2710f", size = 6883356, upload-time = "2026-10-10T20:05:06.249Z" }, + { url = "https://files.pythonhosted.org/packages/67/a7/8af04c5a79e047996cfa38854dcfbececdd0343a7c933a46fdd03ef6f5da/numpy-2.5.4-cp315-cp315t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6c109eac9cd439193678f69d70733c1108487546ca8eafc107b510ae10c1aecd", size = 15750991, upload-time = "2026-10-10T20:05:08.376Z" }, + { url = "https://files.pythonhosted.org/packages/57/7a/648254290d0c504faa8f2d07aa206660c728802c781a6f3fc68ab7cb5d71/numpy-2.5.4-cp315-cp315t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:80d6ef6e8620eb2c2b4c4caad50b5935d6db3cde2d51581b55dcc79e14016d1d", size = 16757675, upload-time = "2026-10-10T20:05:11.393Z" }, + { url = "https://files.pythonhosted.org/packages/b8/fe/4a8c3cdb0c70400cfe4c5bec42d3099a5673802a95064614b33e07b82aa1/numpy-2.5.4-cp315-cp315t-musllinux_1_2_aarch64.whl", hash = "sha256:77045a4b175bbf5316ec08003880804336c78f92281a1b72222b274ea85ec5ac", size = 17113846, upload-time = "2026-10-10T20:05:14.49Z" }, + { url = "https://files.pythonhosted.org/packages/1b/7e/619692bb67778702c0e9eb2d468568a7573f4e269386ea61aed01ee4e557/numpy-2.5.4-cp315-cp315t-musllinux_1_2_x86_64.whl", hash = "sha256:0f02a46e49cfb6c73bdb7aea1c0d3461dbae9aba613542b65f657cd3d17b9fab", size = 18522915, upload-time = "2026-10-10T20:05:17.33Z" }, + { url = "https://files.pythonhosted.org/packages/b7/b5/4da41c328788f575838f97a098fe8ca691ebc6f6fd73ad4a262ee40b184d/numpy-2.5.4-cp315-cp315t-win32.whl", hash = "sha256:ad62a416ddcf863bf44bba76fbf6b53366ab0692e294f51cae4b5fbe0d246788", size = 6335804, upload-time = "2026-10-10T20:05:19.921Z" }, + { url = "https://files.pythonhosted.org/packages/98/94/6482ddfa3d312490cb9358f375bf2ad56427dbea8769187158e94d653753/numpy-2.5.4-cp315-cp315t-win_amd64.whl", hash = "sha256:38f47be9f74ab870d2633b5456ae519c43758a8d1fd05342f0ce4ecc034396ee", size = 12890095, upload-time = "2026-10-10T20:05:21.875Z" }, + { url = "https://files.pythonhosted.org/packages/48/7f/c2d1b436b6e7cfebac140c2579a298344b85f2991a2ce5c3615cefb29400/numpy-2.5.4-cp315-cp315t-win_arm64.whl", hash = "sha256:7a14a461d9340f1b46b8648578aed9cdb8b3b018a8fac6c1dde2c9192a01a87f", size = 10883718, upload-time = "2026-10-10T20:05:28.547Z" }, +] + +[[package]] +name = "omegaconf" +version = "2.4.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "pyyaml" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/cc/10/1cabf3188a4d9684a06568c7fd76f9536eede625733c8399cf1f5337b83e/omegaconf-2.4.0.tar.gz", hash = "sha256:7e219a70bea371da250285b9c01c7db027bc421722799c2cc4ff14bc4a2a753b", size = 3544508, upload-time = "2026-10-09T12:44:02.326Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/4f/bd/0d9f8247b0819385213d09564eda5c52d3673313c2414d51f72883ec24cd/omegaconf-2.4.0-py3-none-any.whl", hash = "sha256:f141a664c777582405e3cc6e0545ecc79429e79f844995b1a6e71c35946a025c", size = 254152, upload-time = "2026-10-09T12:43:59.764Z" }, +] + +[[package]] +name = "onnxruntime" +version = "1.31.1" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "flatbuffers" }, + { name = "numpy" }, + { name = "packaging" }, + { name = "protobuf" }, +] +wheels = [ + { url = "https://files.pythonhosted.org/packages/d7/55/b511099a435972b86b5d04ef374cdca8de920311cc979180029b80145bf5/onnxruntime-1.31.1-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:8536ac43682caa7492c46d6cfd4c3c8db288dcf0619508431a22170b670ee1d0", size = 20883427, upload-time = "2026-10-26T19:26:54.067Z" }, + { url = "https://files.pythonhosted.org/packages/06/ef/98f0060d6cf58f9f663268fef65fe729120b8fbe26ef35eaa2c8d9030d33/onnxruntime-1.31.1-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:c878686b75cade1ed59131aa018ab004b1e64368b0d54041912450b9642cf04f", size = 21421619, upload-time = "2026-10-26T19:26:57.332Z" }, + { url = "https://files.pythonhosted.org/packages/aa/74/a891a659ccc427469de0d7bdbd5ff770a35f73084ee590ce02456cf61f7f/onnxruntime-1.31.1-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:c20d7f15d84427db070b163f78c2c7146cc93edd6113fa7327671259a24184fe", size = 23762999, upload-time = "2026-10-26T19:27:00.865Z" }, + { url = "https://files.pythonhosted.org/packages/e5/e9/9112e9322aef42bff80e805915b61cdcbb82577589bdd42dedf73a5ff9b6/onnxruntime-1.31.1-cp314-cp314-win_amd64.whl", hash = "sha256:0a3998e18cb667ef54287556bd62291a788ed235723dd90c83b2294b24e71d81", size = 15268752, upload-time = "2026-10-26T19:27:03.629Z" }, + { url = "https://files.pythonhosted.org/packages/ed/ee/b69384d9b94c6bf3beb030bcba25dc573e490d3136117be0f78d79078d35/onnxruntime-1.31.1-cp314-cp314-win_arm64.whl", hash = "sha256:fc01b4e7c0a81778fb741bcf5c16b7871d196275f6240720a8b8bfd9f0c0af14", size = 15153930, upload-time = "2026-10-26T19:27:06.159Z" }, + { url = "https://files.pythonhosted.org/packages/2b/5b/beeb6acb5a9e17311b4ebc36fe91ac4893200ddb290257fb072509a7c26b/onnxruntime-1.31.1-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:564d7b83fb3e94fb3d18629c6b339e9bce10966dd29a8442c433175aac3d60fd", size = 21432341, upload-time = "2026-10-26T19:27:09.131Z" }, + { url = "https://files.pythonhosted.org/packages/c6/3d/a5b15c4ab9d67a384da5a2c10fb569e643076c28179fe1a265af7d8f1b87/onnxruntime-1.31.1-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:4d5f5fcc01f0c334d282a8991eab44e7752ad01c47b336d848ba43eb38084958", size = 23772582, upload-time = "2026-10-26T19:27:12.025Z" }, +] + +[[package]] +name = "opencv-python-headless" +version = "5.0.0.93" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "numpy" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/1d/99/76b7c80252aa83c1af16393454aafd125a0287101afe8deb0a6821af0e30/opencv_python_headless-5.0.0.93.tar.gz", hash = "sha256:b82f9831daab90b725c7c1ee1b36cb5732c367096ac76d119e64e14eb70d5f3c", size = 81817738, upload-time = "2026-07-02T07:01:06.039Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/53/7c/8c8097891c509d98cd128493835c95631c80be6a8f37ed9d25716c2e16f1/opencv_python_headless-5.0.0.93-cp37-abi3-macosx_13_0_arm64.whl", hash = "sha256:030ca5e0837a2963ab36ef896baa9767eb8d2b83353fb28af5a521e40dd8756f", size = 48322581, upload-time = "2026-07-02T05:50:34.207Z" }, + { url = "https://files.pythonhosted.org/packages/90/8c/eab2ad388c3cbab2a350c10c2ef19ce6bd099240afc31789032c996bab52/opencv_python_headless-5.0.0.93-cp37-abi3-macosx_14_0_x86_64.whl", hash = "sha256:1e55af3abfb462eeeabe5c775f12bdb36216d8a93a3583d69e6bd6e1d6ba7d00", size = 34782894, upload-time = "2026-07-02T05:51:39.856Z" }, + { url = "https://files.pythonhosted.org/packages/ec/78/afca939f40ffe2b2380bfa86f812b2f7d4acc5a27b27dc41b49cad7ce7b4/opencv_python_headless-5.0.0.93-cp37-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:10818d91510e05c04568ae12b5cd120779c70c01bf897b001a6221fe430df80f", size = 36521085, upload-time = "2026-07-02T06:55:24.429Z" }, + { url = "https://files.pythonhosted.org/packages/2b/97/8170e9819764c47e436c130d3ff6cfb73b58f923eae9d3a03d8982b04aec/opencv_python_headless-5.0.0.93-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:09a872a157c1376ab922a69bbf22f9a95bcc7b658a9d8b436a60212b02b2eeb4", size = 56563598, upload-time = "2026-07-02T06:55:47.355Z" }, + { url = "https://files.pythonhosted.org/packages/3a/98/1a28a7101e31801042b3098871a74b76c61581d328ef40774ff4edb53a56/opencv_python_headless-5.0.0.93-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:840bd717c21e5c11cadadc022a823315ea417f961213d06b4df010e019eb16f4", size = 39648433, upload-time = "2026-07-02T06:56:04.255Z" }, + { url = "https://files.pythonhosted.org/packages/9b/21/f6ef335f6e65724aa78b8d792b48d40a48c381715f1e62f5a5049e09d07e/opencv_python_headless-5.0.0.93-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:ed709fdf9aa0bd1f2ed8549e71d19449b03a675bb581eb292285f6861953be37", size = 61204038, upload-time = "2026-07-02T06:56:41.823Z" }, + { url = "https://files.pythonhosted.org/packages/d0/8f/b8756467ea991449a293797f6b3fa80fcfdd29598a0a60d1cd5715b96e61/opencv_python_headless-5.0.0.93-cp37-abi3-win32.whl", hash = "sha256:c6bcd96b185975ea240d22cfdb15a1f6d080cc95264cfbe2621f21bb144d89b9", size = 35411237, upload-time = "2026-07-02T05:50:12.901Z" }, + { url = "https://files.pythonhosted.org/packages/b8/88/763b967f7efd7226b82c9fae16d560cba049b1f0c036647e65c610fd636e/opencv_python_headless-5.0.0.93-cp37-abi3-win_amd64.whl", hash = "sha256:829717b6a95554f273e49e357cee3b3a2a26b6f4842fbc1bed2b45bdd8f87e0e", size = 43825962, upload-time = "2026-07-02T05:50:09.627Z" }, +] + [[package]] name = "openpyxl" version = "3.1.5" @@ -570,6 +792,56 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/f1/d9/7fb5aa316bc299258e68c73ba3bddbc499654a07f151cba08f6153988714/pathspec-1.1.1-py3-none-any.whl", hash = "sha256:a00ce642f577bf7f473932318056212bc4f8bfdf53128c78bbd5af0b9b20b189", size = 57328, upload-time = "2026-04-27T01:46:07.06Z" }, ] +[[package]] +name = "pillow" +version = "13.0.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/ce/a4/9cc30690a394a8305e8be4c9036aa16d0dfddadd09079860b582f562496d/pillow-13.0.0.tar.gz", hash = "sha256:cdcd1ba258178f7356d74170c9a81ba4eab6a5d55748bc402a5a2a6fe6be3510", size = 47058631, upload-time = "2026-10-16T22:18:09.718Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/8e/45/fbad9c7f5e2f1745c373a434d46072bc84eddfefaa28b852425ac957fda6/pillow-13.0.0-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:44629d4498c9cb6b2051806155f22141df0d8a929c56134b166655232dfb2f8c", size = 4190721, upload-time = "2026-10-16T22:16:27.524Z" }, + { url = "https://files.pythonhosted.org/packages/a2/bf/2074902a259a90692c5dbf132885d21671644cbbd3f690047516243a55db/pillow-13.0.0-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:bf97ba1b5542050e9b0c74e632323b6d8136cc99d64e193abebee22fe6013c76", size = 4290236, upload-time = "2026-10-16T22:16:29.562Z" }, + { url = "https://files.pythonhosted.org/packages/ff/a5/3d1bb93b8ea38d15d21356c1b8e9f50971ac592aaa248f7fb71739094c0e/pillow-13.0.0-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:aa694c49787040943570d61c9b8fc01271bd2a2cfdd55f0d896f8aecdce1a981", size = 3723093, upload-time = "2026-10-16T22:16:31.249Z" }, + { url = "https://files.pythonhosted.org/packages/84/a1/be060135d85187b25fa8b2573786c0e45c62ae27527fff5257675eb97f4a/pillow-13.0.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:49c12af515073e9bf511e4ef736743bf70d531a643668722279314b937742ba4", size = 5572253, upload-time = "2026-10-16T22:16:33.103Z" }, + { url = "https://files.pythonhosted.org/packages/b5/f4/0bf6f1ac9ba7ee2ffe9914aeb410a1035a0c1a3c42f122388d7fc950bc4b/pillow-13.0.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:d9b0a2bee3f3e03e9f29057aedb807dbf1e1d96ee1b9d0f422d9db6c8583271d", size = 4852269, upload-time = "2026-10-16T22:16:35.102Z" }, + { url = "https://files.pythonhosted.org/packages/83/16/b603274617b3e6728da3a0133d4fba1ea8d7fbe0c4ea5fef9cbffa398b8b/pillow-13.0.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5933fcea5a5ba64c686f55c886a115cbfd92f2900460784a1e79909fdbafd7b6", size = 6516058, upload-time = "2026-10-16T22:16:37.228Z" }, + { url = "https://files.pythonhosted.org/packages/1d/f2/1371707ce438ba9a43f9d24089828494ec6f9396e28cd7903aa704dd6306/pillow-13.0.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e91c2b1cbeae768c98752e67e717e283d68dae45717b41f2d91eaee648e37b7d", size = 7142574, upload-time = "2026-10-16T22:16:39.172Z" }, + { url = "https://files.pythonhosted.org/packages/b9/a9/62cf68587f910bc87c5951bcb6e9430c7643a65076adf5f18b4bf350e2bd/pillow-13.0.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:7f6299e494e46253d40c34653cac369412f44ca53b5f85d848d3f95b1ed0546c", size = 6614295, upload-time = "2026-10-16T22:16:41.117Z" }, + { url = "https://files.pythonhosted.org/packages/6c/c9/9e9b48178649730299be0bafbf5f810a5b6977538f5a92d47e4ba5f5d608/pillow-13.0.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:f9bd7d260d986f3553518c5d723544346fa48031f8aef3265d786aeb59845bc0", size = 7224841, upload-time = "2026-10-16T22:16:43.118Z" }, + { url = "https://files.pythonhosted.org/packages/8f/48/c44e91384b1b6c072a714a63d00608acc16a6a968735e478e4be4384e5ac/pillow-13.0.0-cp314-cp314-win32.whl", hash = "sha256:2e31c4e68cffd7b1f116127626813b82fcba19edf6b940a7b0c266d6484d0055", size = 6508694, upload-time = "2026-10-16T22:16:45.883Z" }, + { url = "https://files.pythonhosted.org/packages/50/e2/7ad17747517e4c813dca78257d6bb593466f8231baf1384bc98d92745edb/pillow-13.0.0-cp314-cp314-win_amd64.whl", hash = "sha256:f7cbb7a64e7ec664775195e4f81923bc8a93d9451b963f844e59118f63147a7a", size = 7281830, upload-time = "2026-10-16T22:16:47.725Z" }, + { url = "https://files.pythonhosted.org/packages/41/9f/e5b51f2ce8ef4563215334035403ce61a244f93a2e65c24a940131618f87/pillow-13.0.0-cp314-cp314-win_arm64.whl", hash = "sha256:a6aaa7871aebca081eb5c45f83e845bbd9712ae99fa9286dbfdcee835e63f4b4", size = 2695468, upload-time = "2026-10-16T22:16:49.515Z" }, + { url = "https://files.pythonhosted.org/packages/97/73/a53502f731f6c84805a4ce87a8881e86d07a65aee64728b900d112dc703e/pillow-13.0.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:7b999816b5850a35ada08443e6e03945f1f6488144a83afe2d37b240a552aafa", size = 5578196, upload-time = "2026-10-16T22:16:51.291Z" }, + { url = "https://files.pythonhosted.org/packages/21/50/7e949959a56b5559c78ef172b70fc6025706acb289f3f648a15329e4fa6f/pillow-13.0.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:67871a13cf47275201553b536c025da777f997fa562a19eb798af4ad4b97c18f", size = 4857276, upload-time = "2026-10-16T22:16:53.399Z" }, + { url = "https://files.pythonhosted.org/packages/c9/52/43ded0ac08e77e39d17bd6d894162572201b5e8fdc4a022b14c55a1960a4/pillow-13.0.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e8ca8f69b7c77fa96dad99f8638c1fc4f1c0bed4acaa1baf7a3c31bdb80a0ab1", size = 6607008, upload-time = "2026-10-16T22:16:55.525Z" }, + { url = "https://files.pythonhosted.org/packages/0d/2e/4a57ed216d5bf877387cba4d44c02aa87abe51ad2e06404aa6b597c4da39/pillow-13.0.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6bce6a29c3898191f4c9998e4d4e8f69790caeabde46e54da4bc235ce5bde683", size = 7224281, upload-time = "2026-10-16T22:16:57.738Z" }, + { url = "https://files.pythonhosted.org/packages/5c/3d/2929b248e135752d63aaeabf53f6de797e905b7b6263f9c1e2adade20aba/pillow-13.0.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:816752a5ef76a80484c8c441c85593b7ea9304f6231fc5776ad1fbff7e773058", size = 6695600, upload-time = "2026-10-16T22:16:59.842Z" }, + { url = "https://files.pythonhosted.org/packages/bc/33/fb0da992cf084ed1ee6ee05e96b6191e35c351eb707ca2df874feb24ce47/pillow-13.0.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:5bdb38ba220b61b4ec31dd1046dea6b016d3c6850a23f43ed8b58332b2fc668e", size = 7300589, upload-time = "2026-10-16T22:17:01.686Z" }, + { url = "https://files.pythonhosted.org/packages/bb/af/c30dd9ef6a3dce84ecb1b2393cac629047a32e66279056c6cb46c3ffd65c/pillow-13.0.0-cp314-cp314t-win32.whl", hash = "sha256:06903aac074d00c988e77a1fc435286dc498506d4ca8d6f69df9babddf4ecc15", size = 6517204, upload-time = "2026-10-16T22:17:03.722Z" }, + { url = "https://files.pythonhosted.org/packages/85/d5/ef3a8ae7609c8ab26570abf18194882534b480d245a9148b895a2262c004/pillow-13.0.0-cp314-cp314t-win_amd64.whl", hash = "sha256:9a635068d9793c7f0d929f39f18b58f1bd86c236e8e7b64167b86af9232ebca0", size = 7286695, upload-time = "2026-10-16T22:17:05.543Z" }, + { url = "https://files.pythonhosted.org/packages/84/3c/0861db0c69a03689ebe3e7599d35668a414deb5aaafd8255215e4e62e3d3/pillow-13.0.0-cp314-cp314t-win_arm64.whl", hash = "sha256:0d1a9cf7bc6917538b20f8d06b9ab2147e542f68849e96fc58eb66bdf6acc692", size = 2698098, upload-time = "2026-10-16T22:17:07.674Z" }, + { url = "https://files.pythonhosted.org/packages/6e/eb/e86a41962a3a31ad495a3d6a912d9002b01bba4a6fa71c28703abdca7f69/pillow-13.0.0-cp315-cp315-ios_13_0_arm64_iphoneos.whl", hash = "sha256:7d5e097eabd5d4915c27ac9f6e9325bb1e01a7c94d7348b5c4451d3fc30e8521", size = 4191213, upload-time = "2026-10-16T22:17:09.449Z" }, + { url = "https://files.pythonhosted.org/packages/dd/04/7e7445e706afec84ef06dc25b2c77f9cecff242c23730c62928ad1089d4a/pillow-13.0.0-cp315-cp315-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:51ebb529fc5e8abdd55302f6c3f8943037348ec2384329a3e55677f69ae2fdfc", size = 4290650, upload-time = "2026-10-16T22:17:11.196Z" }, + { url = "https://files.pythonhosted.org/packages/46/85/d534089068ac40c0f61f650389a296c812eab745a8a733f81feec39ae955/pillow-13.0.0-cp315-cp315-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:c87a04e7f152ee4db5dbe15f0bfa3fe628a1aeedbe66b81c43b87f52c813f9ac", size = 3723078, upload-time = "2026-10-16T22:17:12.772Z" }, + { url = "https://files.pythonhosted.org/packages/ce/2b/00b5c3b401df538b5dbe311d3899730fae5ba1e21cb8b80a128887ac6747/pillow-13.0.0-cp315-cp315-macosx_10_15_x86_64.whl", hash = "sha256:20722cd5375533ad754053363a80b8fb30c79d37930a6f7228030e237ce3bd5d", size = 5572292, upload-time = "2026-10-16T22:17:14.539Z" }, + { url = "https://files.pythonhosted.org/packages/72/f5/a6b0610f946e9b54ae888ba7ad29d6e2f8d9b11f69e212d70416b7186c09/pillow-13.0.0-cp315-cp315-macosx_11_0_arm64.whl", hash = "sha256:04a63720f79e22fd54d897c233a68314c50ca0603360f54ce2bd5db8f0f43782", size = 4852222, upload-time = "2026-10-16T22:17:16.521Z" }, + { url = "https://files.pythonhosted.org/packages/1e/d0/c0ff25bb0427ec70f32aac995453321fc3c4494a46c7292ff02d9d260b04/pillow-13.0.0-cp315-cp315-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4f8db54177035a2b5f717f94475b74907e12a96dc74f6d487f3966b0a4694071", size = 6527349, upload-time = "2026-10-16T22:17:18.534Z" }, + { url = "https://files.pythonhosted.org/packages/85/11/e46fa0bcc0fc117f1eacc206b3d51f04d583fab328b4b740672d0438d83f/pillow-13.0.0-cp315-cp315-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8f36aa77f74b14a2103622b196402c71330e4e7cf4122ee45c854e9a01e0eecf", size = 7152873, upload-time = "2026-10-16T22:17:20.415Z" }, + { url = "https://files.pythonhosted.org/packages/7c/53/2bdeca705f3a58679fa9201233193c86a30238340ca29b3a152c3fcc719b/pillow-13.0.0-cp315-cp315-musllinux_1_2_aarch64.whl", hash = "sha256:149a1c323ba366f90b48e6f1a6db6582eb50512df374588de56fc909abc0f0f3", size = 6626871, upload-time = "2026-10-16T22:17:22.361Z" }, + { url = "https://files.pythonhosted.org/packages/14/de/3829030f209722ade3753bb456b805a0e7f885cf885b483407365c82e9ca/pillow-13.0.0-cp315-cp315-musllinux_1_2_x86_64.whl", hash = "sha256:e892354a424b1e82a78ba16785822bdd40de06f19446a3d4a28047df1a4f8932", size = 7236439, upload-time = "2026-10-16T22:17:24.352Z" }, + { url = "https://files.pythonhosted.org/packages/44/b1/67fc37388382bc036a74f04da5bb6fcbf90ec3ac1f45893e06176c373fd3/pillow-13.0.0-cp315-cp315-win32.whl", hash = "sha256:8e459b613cf31f8980f584387b4fe47bf08e076e288d61aa8eba1f7fd4ddbb81", size = 6508688, upload-time = "2026-10-16T22:17:26.314Z" }, + { url = "https://files.pythonhosted.org/packages/44/05/fdb6a79aee10861165526b41b7b440e36ee1ff58613b2fbefe3acbf06d4f/pillow-13.0.0-cp315-cp315-win_amd64.whl", hash = "sha256:d4737f50d23ddd11d6685faacbb9252887dde0bc7997127757247983d74399d6", size = 7281107, upload-time = "2026-10-16T22:17:28.198Z" }, + { url = "https://files.pythonhosted.org/packages/e6/9c/6c6f7dc2a566467baf121394e83de25ac287cffe34cc030726beb4be0224/pillow-13.0.0-cp315-cp315-win_arm64.whl", hash = "sha256:2310e2adfc13c6d457d7d0f2ffdd5c56a74a317650cf765887df8d515a647ac0", size = 2695513, upload-time = "2026-10-16T22:17:30.013Z" }, + { url = "https://files.pythonhosted.org/packages/23/16/e9120defdb8bff693b582d035312acc6f530cdc2bc5238a87f410efccd82/pillow-13.0.0-cp315-cp315t-macosx_10_15_x86_64.whl", hash = "sha256:21c32061a5512dc13f87cc7303e120e4d77c2f70df89a35af0e3ce246e5ac57f", size = 5578129, upload-time = "2026-10-16T22:17:31.642Z" }, + { url = "https://files.pythonhosted.org/packages/47/22/76faf2bb2448f48a84cf894c1e2bb1090d7d2b1aa521ece131cb2f05d631/pillow-13.0.0-cp315-cp315t-macosx_11_0_arm64.whl", hash = "sha256:1c774b9c0ba0d0b356f71530677b39028878a2cae5a93e0a13779cfd17120f88", size = 4857428, upload-time = "2026-10-16T22:17:33.43Z" }, + { url = "https://files.pythonhosted.org/packages/b3/64/0861ea4e03c50b14af9ed9dd8b9f388ab42f445c623a9fcbab19aef7aa55/pillow-13.0.0-cp315-cp315t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:20822140c9a2ba9c5e42df342b0a892ab2e102fc0e3db967a133bb9ce3f898bb", size = 6612582, upload-time = "2026-10-16T22:17:35.415Z" }, + { url = "https://files.pythonhosted.org/packages/5c/20/cd1e9b3f60a9f3d5ebe46da36955c26004092a501f7f2c42f9fcc26611bc/pillow-13.0.0-cp315-cp315t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ffea6b2986a797c84b6d1d27d4f43e0b83c73fc16281a930891cd237cf0d08fe", size = 7230176, upload-time = "2026-10-16T22:17:37.362Z" }, + { url = "https://files.pythonhosted.org/packages/b6/ef/ffb0a2fc85690714fb7ac662956949645d57f15bf4426f520da361e7b6e3/pillow-13.0.0-cp315-cp315t-musllinux_1_2_aarch64.whl", hash = "sha256:05cd2cd39055d0b9650060e4513ef4a9a0aea870083950bd046a0d6490f93a22", size = 6703640, upload-time = "2026-10-16T22:17:39.313Z" }, + { url = "https://files.pythonhosted.org/packages/e0/c2/6402ee3ccb3363aeed8fdb3f9fe56703ac5377a539f0b81b53999d7e121f/pillow-13.0.0-cp315-cp315t-musllinux_1_2_x86_64.whl", hash = "sha256:c6fd031333dedcad7ce3e03d244093f43504f209e86925ebdb2b868fa4037630", size = 7309231, upload-time = "2026-10-16T22:17:41.021Z" }, + { url = "https://files.pythonhosted.org/packages/fc/96/d6b82e8b8c06ad143b66b12e0b31051e4bf489b4fabca1f390a14fe1ebde/pillow-13.0.0-cp315-cp315t-win32.whl", hash = "sha256:c50c80e3591e5cf9a8dfa6007d4f10732f02e32263850999286e56ccd650cfb2", size = 6517200, upload-time = "2026-10-16T22:17:42.886Z" }, + { url = "https://files.pythonhosted.org/packages/60/d4/0062e6005e9b270b165015aafd343364ac378ec5a685431ea42baad33357/pillow-13.0.0-cp315-cp315t-win_amd64.whl", hash = "sha256:adb3c2124c68e480f4632d06cb7caa3b48a51678475f483b4edb1c6dee29ea43", size = 7287488, upload-time = "2026-10-16T22:17:45.56Z" }, + { url = "https://files.pythonhosted.org/packages/e4/81/b8eb349746be7bce47dd95337c6634e84910af91b59aaa9159c034c614fa/pillow-13.0.0-cp315-cp315t-win_arm64.whl", hash = "sha256:4a25756244bdcce3b50580baadf320fa48297f0eeb8e114ba64139a40d4d0fc8", size = 2698073, upload-time = "2026-10-16T22:17:47.556Z" }, +] + [[package]] name = "platformdirs" version = "4.13.5" @@ -607,6 +879,39 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/40/9e/2b38731e0fc536806f16490e1a12d7f0dc2a1235aa8cc07bcc75416a7daa/pluggy-1.7.0-py3-none-any.whl", hash = "sha256:7dd7b0d8832ba3cb632c306926ded123429211b83641b35dc5c41ad2d34f9bec", size = 27082, upload-time = "2026-10-15T09:50:56.808Z" }, ] +[[package]] +name = "protobuf" +version = "7.36.2" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/d9/89/5b8517baa72f84a67b8a307ba953c91057af618bf40bf676f3c03551f8f0/protobuf-7.36.2.tar.gz", hash = "sha256:497d0463ff3316681da6c0b9e8d06cb465d61abce00b613ab42226175644d1bb", size = 512737, upload-time = "2026-09-17T20:07:59.326Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/32/72/98342feb672507c8f3a69e34b4fa8961f608edba5c1a48a6f47156d92cb5/protobuf-7.36.2-cp310-abi3-macosx_10_9_universal2.whl", hash = "sha256:cbc70b17ee27e28894c7fee8bb04be1abead49e936bc70eb60052531eee2079e", size = 456039, upload-time = "2026-09-17T20:07:51.542Z" }, + { url = "https://files.pythonhosted.org/packages/b6/ea/91fdf7c2b8bbd49cde056f00a9df6773532987e1c00fe2830b895af95c7e/protobuf-7.36.2-cp310-abi3-manylinux2014_aarch64.whl", hash = "sha256:e11e1f0180583a2af89db6a2ecd9e8dc40aa6d2988ca175bfd0e6d12ea72d74e", size = 344219, upload-time = "2026-09-17T20:07:52.914Z" }, + { url = "https://files.pythonhosted.org/packages/17/ab/5fd5f8ece73fad885c5a09aa849b32d70472f954ba3a92d3bb5974ea953b/protobuf-7.36.2-cp310-abi3-manylinux2014_s390x.whl", hash = "sha256:f4fee11ec330d238b34a05c9b675f693c20415d1c5bd7d5320cc2f8a798eb9cf", size = 357223, upload-time = "2026-09-17T20:07:53.985Z" }, + { url = "https://files.pythonhosted.org/packages/db/f3/3996583dd2906297a637af12114deddf7658af6e683fedb83be061983fb5/protobuf-7.36.2-cp310-abi3-manylinux2014_x86_64.whl", hash = "sha256:89f23aa53c24553a2416fd4fd1ec06f74fa42b14b546d8883128813f775bbfd2", size = 343223, upload-time = "2026-09-17T20:07:54.931Z" }, + { url = "https://files.pythonhosted.org/packages/fc/1b/dcc64f358fcb51811b58ae40b3d28f820725f116d86487cc20bd4b130701/protobuf-7.36.2-cp310-abi3-win32.whl", hash = "sha256:912c1221170e16c08d1f086762f563dd61ff83c18b5fa6652952dfaded66f728", size = 442998, upload-time = "2026-09-17T20:07:55.826Z" }, + { url = "https://files.pythonhosted.org/packages/8a/55/b77bda4e5e5f5971fb51b07663694690e9afdb9402136c16a522bd621cad/protobuf-7.36.2-cp310-abi3-win_amd64.whl", hash = "sha256:a300819d441e078a5608c0d3c709796bb548136058fda017ae51d425b44fd353", size = 456514, upload-time = "2026-09-17T20:07:57.188Z" }, + { url = "https://files.pythonhosted.org/packages/e4/04/d52c7016b04b6c5108f26691f9d33ec82a9b65d041f1a9c771137693d618/protobuf-7.36.2-py3-none-any.whl", hash = "sha256:bdb3a345d48db958e6ce1f18e508beb0cc981d64f24088427549c866cd039f1e", size = 179806, upload-time = "2026-09-17T20:07:58.211Z" }, +] + +[[package]] +name = "pyclipper" +version = "1.4.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/f6/21/3c06205bb407e1f79b73b7b4dfb3950bd9537c4f625a68ab5cc41177f5bc/pyclipper-1.4.0.tar.gz", hash = "sha256:9882bd889f27da78add4dd6f881d25697efc740bf840274e749988d25496c8e1", size = 54489, upload-time = "2025-12-01T13:15:35.015Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/1a/20/04d58c70f3ccd404f179f8dd81d16722a05a3bf1ab61445ee64e8218c1f8/pyclipper-1.4.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:7c87480fc91a5af4c1ba310bdb7de2f089a3eeef5fe351a3cedc37da1fcced1c", size = 265167, upload-time = "2025-12-01T13:15:20.844Z" }, + { url = "https://files.pythonhosted.org/packages/bd/2e/a570c1abe69b7260ca0caab4236ce6ea3661193ebf8d1bd7f78ccce537a5/pyclipper-1.4.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:81d8bb2d1fb9d66dc7ea4373b176bb4b02443a7e328b3b603a73faec088b952e", size = 139966, upload-time = "2025-12-01T13:15:22.036Z" }, + { url = "https://files.pythonhosted.org/packages/e8/3b/e0859e54adabdde8a24a29d3f525ebb31c71ddf2e8d93edce83a3c212ffc/pyclipper-1.4.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:773c0e06b683214dcfc6711be230c83b03cddebe8a57eae053d4603dd63582f9", size = 968216, upload-time = "2025-12-01T13:15:23.18Z" }, + { url = "https://files.pythonhosted.org/packages/f6/6b/e3c4febf0a35ae643ee579b09988dd931602b5bf311020535fd9e5b7e715/pyclipper-1.4.0-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9bc45f2463d997848450dbed91c950ca37c6cf27f84a49a5cad4affc0b469e39", size = 954198, upload-time = "2025-12-01T13:15:24.522Z" }, + { url = "https://files.pythonhosted.org/packages/fc/74/728efcee02e12acb486ce9d56fa037120c9bf5b77c54bbdbaa441c14a9d9/pyclipper-1.4.0-cp314-cp314-win32.whl", hash = "sha256:0b8c2105b3b3c44dbe1a266f64309407fe30bf372cf39a94dc8aaa97df00da5b", size = 96951, upload-time = "2025-12-01T13:15:25.79Z" }, + { url = "https://files.pythonhosted.org/packages/e3/d7/7f4354e69f10a917e5c7d5d72a499ef2e10945312f5e72c414a0a08d2ae4/pyclipper-1.4.0-cp314-cp314-win_amd64.whl", hash = "sha256:6c317e182590c88ec0194149995e3d71a979cfef3b246383f4e035f9d4a11826", size = 106782, upload-time = "2025-12-01T13:15:26.945Z" }, + { url = "https://files.pythonhosted.org/packages/63/60/fc32c7a3d7f61a970511ec2857ecd09693d8ac80d560ee7b8e67a6d268c9/pyclipper-1.4.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:f160a2c6ba036f7eaf09f1f10f4fbfa734234af9112fb5187877efed78df9303", size = 269880, upload-time = "2025-12-01T13:15:28.117Z" }, + { url = "https://files.pythonhosted.org/packages/49/df/c4a72d3f62f0ba03ec440c4fff56cd2d674a4334d23c5064cbf41c9583f6/pyclipper-1.4.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:a9f11ad133257c52c40d50de7a0ca3370a0cdd8e3d11eec0604ad3c34ba549e9", size = 141706, upload-time = "2025-12-01T13:15:30.134Z" }, + { url = "https://files.pythonhosted.org/packages/c5/0b/cf55df03e2175e1e2da9db585241401e0bc98f76bee3791bed39d0313449/pyclipper-1.4.0-cp314-cp314t-win32.whl", hash = "sha256:bbc827b77442c99deaeee26e0e7f172355ddb097a5e126aea206d447d3b26286", size = 105308, upload-time = "2025-12-01T13:15:31.225Z" }, + { url = "https://files.pythonhosted.org/packages/8f/dc/53df8b6931d47080b4fe4ee8450d42e660ee1c5c1556c7ab73359182b769/pyclipper-1.4.0-cp314-cp314t-win_amd64.whl", hash = "sha256:29dae3e0296dff8502eeb7639fcfee794b0eec8590ba3563aee28db269da6b04", size = 117608, upload-time = "2025-12-01T13:15:32.69Z" }, +] + [[package]] name = "pydantic" version = "2.14.1" @@ -811,6 +1116,42 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/f1/12/de94a39c2ef588c7e6455cfbe7343d3b2dc9d6b6b2f40c4c6565744c873d/pyyaml-6.0.3-cp314-cp314t-win_arm64.whl", hash = "sha256:ebc55a14a21cb14062aa4162f906cd962b28e2e9ea38f9b4391244cd8de4ae0b", size = 149341, upload-time = "2025-09-25T21:32:56.828Z" }, ] +[[package]] +name = "rapidocr" +version = "3.10.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "colorlog" }, + { name = "numpy" }, + { name = "omegaconf" }, + { name = "opencv-python-headless" }, + { name = "pillow" }, + { name = "pyclipper" }, + { name = "pyyaml" }, + { name = "requests" }, + { name = "shapely" }, + { name = "six" }, + { name = "tqdm" }, +] +wheels = [ + { url = "https://files.pythonhosted.org/packages/59/07/203065283bba0c5e9c10af3602dc25ab3e59ee54dc2d1d22c8faeabf5ed8/rapidocr-3.10.0-py3-none-any.whl", hash = "sha256:2fc34e26cd0f48514804a94f8832283039c7334076bff60768b1fed9ad068050", size = 27288134, upload-time = "2026-10-08T15:07:45.98Z" }, +] + +[[package]] +name = "requests" +version = "2.34.2" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "certifi" }, + { name = "charset-normalizer" }, + { name = "idna" }, + { name = "urllib3" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/ac/c3/e2a2b89f2d3e2179abd6d00ebd70bff6273f37fb3e0cc209f48b39d00cbf/requests-2.34.2.tar.gz", hash = "sha256:f288924cae4e29463698d6d60bc6a4da69c89185ad1e0bcc4104f584e960b9ed", size = 142856, upload-time = "2026-05-14T19:25:27.735Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/a0/f4/c67b0b3f1b9245e8d266f0f112c500d50e5b4e83cb6f3b71b6528104182a/requests-2.34.2-py3-none-any.whl", hash = "sha256:2a0d60c172f83ac6ab31e4554906c0f3b3588d37b5cb939b1c061f4907e278e0", size = 73075, upload-time = "2026-05-14T19:25:26.443Z" }, +] + [[package]] name = "ruff" version = "0.17.2" @@ -836,6 +1177,62 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/81/60/a3604c79cb02777b6cb84da894104021986f06c4bc41375102cc95049a32/ruff-0.17.2-py3-none-win_arm64.whl", hash = "sha256:195ad918027f817c119310ca89a42d347887dfc28934aaa869325e9c5dc9d962", size = 9827036, upload-time = "2026-10-22T18:37:58.031Z" }, ] +[[package]] +name = "shapely" +version = "2.2.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "numpy" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/f3/ab/924b6e202f796d270a3041a230151f7908db5ea48c74effe6f8023e9bd05/shapely-2.2.0.tar.gz", hash = "sha256:e8865e553d874a1ec4a032057ea81fca9def37b188cd8fb550af3b3480b3f88c", size = 380326, upload-time = "2026-10-07T09:18:01.001Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/eb/a9/83531b7a5349568c507c5701179b1727e21f238af318ac55ba8d0800e764/shapely-2.2.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:000c0ce2a3ba49427e6288b7add9de5d8525d4e65d6ebc8840103040d4d57b86", size = 1785489, upload-time = "2026-10-07T09:16:48.795Z" }, + { url = "https://files.pythonhosted.org/packages/a2/c8/e8117528eb96feafcd5fced50a939ecfdc6242b3782959d202755536bb9e/shapely-2.2.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:0a63e6b68ec785ef3aae3935c4aa9fb8edccced94e23c79d5d85276442c60859", size = 1585345, upload-time = "2026-10-07T09:16:50.527Z" }, + { url = "https://files.pythonhosted.org/packages/53/66/289a7055e3a383680771ba59764712db822fa406bbf52971a76e51d160d6/shapely-2.2.0-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:770d4db5cf0bfeed931a1c4aaf4f4eadad0f43f5fc72c27c88fe1f07904ae767", size = 2177801, upload-time = "2026-10-07T09:16:52.393Z" }, + { url = "https://files.pythonhosted.org/packages/d2/54/8f3d60050a703dcab48f7991ec4fb111772731d20ce6a1bf649465033476/shapely-2.2.0-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:74f4313af38d6e49ea83532d6cedfb4fe5e6c5485d7c40202bd61b19d6ff09bf", size = 2299593, upload-time = "2026-10-07T09:16:54.462Z" }, + { url = "https://files.pythonhosted.org/packages/cf/ec/3389afd3919494f479347a83db7b5672c3c73a339173426a902d9d295152/shapely-2.2.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:9ee11aeba1759d15a525ded58e17916d3edfa60d52110fd8df6a7609a871f066", size = 3246048, upload-time = "2026-10-07T09:16:56.477Z" }, + { url = "https://files.pythonhosted.org/packages/6f/b5/d0d4e3eaf232425a11be7af1a24aaf9c6792bc7a17dd17d722e42892f91a/shapely-2.2.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:24b175c570efc91d1180ac6cd527dc80e863bb7de37f8b2771703d822c65e023", size = 3389241, upload-time = "2026-10-07T09:16:59.055Z" }, + { url = "https://files.pythonhosted.org/packages/3a/3d/b9626c58982a3cf4278ad978644c7a315968c7e03cd7a8a6aaadde911074/shapely-2.2.0-cp314-cp314-win32.whl", hash = "sha256:4e5830637c080bdc646c5982ad6f7cc296b93038879649f7a6acd8e0f1c4db04", size = 1658287, upload-time = "2026-10-07T09:17:00.857Z" }, + { url = "https://files.pythonhosted.org/packages/0a/c1/b3acc1c764dff7e47485dd47fc7ff5fdc230257f02006fec049bf2b9449c/shapely-2.2.0-cp314-cp314-win_amd64.whl", hash = "sha256:48dd1d961391f314ab7fa8812c86ca2a727bee2bdca1478730eacaea007da18e", size = 1843568, upload-time = "2026-10-07T09:17:02.662Z" }, + { url = "https://files.pythonhosted.org/packages/53/12/3b4977cec6bbaee5d4538d8fbd8ffc75bf764fe3519aafb09d5eefb41daa/shapely-2.2.0-cp314-cp314-win_arm64.whl", hash = "sha256:c4127c064bc71f8b7f9b3f341d6627ed39977fd0b61a17c68d09179f5e0089ae", size = 1936825, upload-time = "2026-10-07T09:17:04.886Z" }, + { url = "https://files.pythonhosted.org/packages/cb/0c/8a8f59e344dc3b53c77d99e35e3eb81b8c46cceeb3ffcd44b41ed8d17d7e/shapely-2.2.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:c2915ae1b858e73d5832be7fb5e89497cc5140fa505da40a45223029dc6deace", size = 1793948, upload-time = "2026-10-07T09:17:07.07Z" }, + { url = "https://files.pythonhosted.org/packages/af/1e/76728b192507909866d7eaa398c9a558d326ca9a7dd14bc929362cce99c9/shapely-2.2.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:74028f468e05e461b30a479b08c1fb5094fa45062abeeec8e7905a6711761436", size = 1596025, upload-time = "2026-10-07T09:17:09.141Z" }, + { url = "https://files.pythonhosted.org/packages/11/be/e4b4219ab6414fe17f60d064693f31d5acd25bd8c98def75c4c2a1108b18/shapely-2.2.0-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6ec5178a39803fa8626322f69d298037f182461dd28e3ae96c2c7a4309a6bf30", size = 2177914, upload-time = "2026-10-07T09:17:11.011Z" }, + { url = "https://files.pythonhosted.org/packages/f4/36/c007a564ddfeda1aff3c79435d4beb2c0baf41b37d1ec212269ef62f8da8/shapely-2.2.0-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:593e51cd04fe1122f1ab3fae87b306c36b2be0184a5e0d9c26849c55ff4580dc", size = 2297494, upload-time = "2026-10-07T09:17:13.089Z" }, + { url = "https://files.pythonhosted.org/packages/cf/74/dd289ba822b8c50a2b47dc70f87a6f4933a6402f5fe4cc5cb999fdf1ea4a/shapely-2.2.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:3575a323b7665d7a2e391b16a626caa6b6f6348f399183aca3fc656febd7cf04", size = 3245678, upload-time = "2026-10-07T09:17:15.165Z" }, + { url = "https://files.pythonhosted.org/packages/04/d8/bd58de9c4f325369bbc7edc4f7cce1a56cfab61e2b1c534176ea58d89db4/shapely-2.2.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:776cc8571d53e42be8fa6d42ad52a599b8e2186dd0c752922831508099af71e2", size = 3387773, upload-time = "2026-10-07T09:17:17.685Z" }, + { url = "https://files.pythonhosted.org/packages/69/4a/6d6e41cab51bb8aa1256ddc28d94d74d016683312e6e0e874afc8b874f3b/shapely-2.2.0-cp314-cp314t-win32.whl", hash = "sha256:f8cd733a66a2a10f461a70dde9fad7b2b62c6a48c7a66cea57ee6f1cd9f2bd2f", size = 1676626, upload-time = "2026-10-07T09:17:19.523Z" }, + { url = "https://files.pythonhosted.org/packages/22/06/6ab21f86fc08aa95b6eb3dc8f8d64701359ce89aae471c15b896e5be5afe/shapely-2.2.0-cp314-cp314t-win_amd64.whl", hash = "sha256:7f68c1fbacab81c0c066d1c3051eeb0f680b7a7a2c511e741f77741640187896", size = 1868388, upload-time = "2026-10-07T09:17:21.376Z" }, + { url = "https://files.pythonhosted.org/packages/07/85/5c0452ee08cfd72b8945ac26fbd5ae559a7af7184aa989a0d83f68f07cf9/shapely-2.2.0-cp314-cp314t-win_arm64.whl", hash = "sha256:9147ebc3b116a0511dca043937f85caf1a41690815643d5b89c8bc472f51c850", size = 1946897, upload-time = "2026-10-07T09:17:23.413Z" }, + { url = "https://files.pythonhosted.org/packages/1d/d0/c994c26df87119e530b715f7109960036242861dba37db17a1b9f44b6e56/shapely-2.2.0-cp315-cp315-macosx_10_15_x86_64.whl", hash = "sha256:715561ceda03b09ca1c6baf9922179392d8c2bc53a1b877965225f0dfb487a58", size = 1785017, upload-time = "2026-10-07T09:17:25.31Z" }, + { url = "https://files.pythonhosted.org/packages/0b/60/2a8975ee00697cb33b17e140def38f2600323760e52eaa6423183a522f06/shapely-2.2.0-cp315-cp315-macosx_11_0_arm64.whl", hash = "sha256:556f20346a7d96fefbb71b74640d84ca14041703d60f0d2ff47b29d9b3e0093d", size = 1585001, upload-time = "2026-10-07T09:17:27.622Z" }, + { url = "https://files.pythonhosted.org/packages/26/07/45cd192ede49dd821c804fd53177ba5fa2739867ceeb542cfeb259ca4314/shapely-2.2.0-cp315-cp315-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ff9e87b534edf35af65758fafb31ad3b797354cba9323899e263f450c69a2ff2", size = 2177659, upload-time = "2026-10-07T09:17:29.501Z" }, + { url = "https://files.pythonhosted.org/packages/f1/7f/55a7f6ae91c10aa58005e985d01756048b6e4ff82e731ea39003e1eeda3e/shapely-2.2.0-cp315-cp315-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fdb599ec540cea5b635ac47bf24fca4cdfd1c39730ffc0b6cf0d2666b0dd9a33", size = 2299128, upload-time = "2026-10-07T09:17:31.352Z" }, + { url = "https://files.pythonhosted.org/packages/58/2f/49eb352f7c0c0c6ec17bc0bee33f9f449d397f8bfc9c2694c384e752f25e/shapely-2.2.0-cp315-cp315-musllinux_1_2_aarch64.whl", hash = "sha256:b8cb04906b74db26f848f76744fa995cd6abeae9145d27cc405277de1f949660", size = 3245354, upload-time = "2026-10-07T09:17:33.291Z" }, + { url = "https://files.pythonhosted.org/packages/1a/c6/3f4f736d615013b2c117cec4d716e775659b2452bb039643c0411d131750/shapely-2.2.0-cp315-cp315-musllinux_1_2_x86_64.whl", hash = "sha256:d9b11d712ac72f1d869f2b6964dea5bd9f20b89901adcd796d6712496144ab22", size = 3388587, upload-time = "2026-10-07T09:17:35.261Z" }, + { url = "https://files.pythonhosted.org/packages/27/ea/cb26677d3e34e1663a00a1395fc17c4a2acb5fef638297f94d5cdb9a63f0/shapely-2.2.0-cp315-cp315-win32.whl", hash = "sha256:1af6935acde1db0b6a1bcbea30cbad5ae900723dfd398367ae1488470dc53667", size = 1658324, upload-time = "2026-10-07T09:17:37.362Z" }, + { url = "https://files.pythonhosted.org/packages/14/7d/351c43d812b94197fe279dc3e0defc6886e4be5a144fc191b8635b0fd839/shapely-2.2.0-cp315-cp315-win_amd64.whl", hash = "sha256:96e5101ad2d73df869255bae4c55537f372d32066e2328c376e09841f0f66800", size = 1843506, upload-time = "2026-10-07T09:17:39.336Z" }, + { url = "https://files.pythonhosted.org/packages/82/de/9b62659a23fe8b9d590cf8e4698051d8eab5c5cdddfd86c531019e9d0d2d/shapely-2.2.0-cp315-cp315-win_arm64.whl", hash = "sha256:446b2d5a323bddd1c2a27f41325fdb3a3e8e33c1f8f0f840bdb63e8c1515b29e", size = 1936521, upload-time = "2026-10-07T09:17:41.121Z" }, + { url = "https://files.pythonhosted.org/packages/91/c9/5e16b2ac8853ec587406496a85cbeb1f3465b53c5e8bf0f222b4a39a44a1/shapely-2.2.0-cp315-cp315t-macosx_10_15_x86_64.whl", hash = "sha256:c88b21a0e9599ebb741e08f71a95c8f07a434af909efb088828a9874d234d06d", size = 1792605, upload-time = "2026-10-07T09:17:43.211Z" }, + { url = "https://files.pythonhosted.org/packages/19/87/ebaf70f25565ed82d75ab84b1d0eb3a8b803302020c16bb98234f67c0477/shapely-2.2.0-cp315-cp315t-macosx_11_0_arm64.whl", hash = "sha256:cbe184e1946cfe115a9dfeadd2effd88ab4a237ab1a4335d106defa80fbc2d82", size = 1594776, upload-time = "2026-10-07T09:17:44.972Z" }, + { url = "https://files.pythonhosted.org/packages/e6/a1/e6210ff8aa7d065c2a94d2a3486342675bcb3f4d740ec686a414ace0c3b9/shapely-2.2.0-cp315-cp315t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8bc985ad731da2f2cedde9c3cfb3c3d946fe6fc63d2ca557673dc33dd1e389b9", size = 2175890, upload-time = "2026-10-07T09:17:46.92Z" }, + { url = "https://files.pythonhosted.org/packages/96/19/4df2a474cdc24beb06ef557d433dbe936fa274600d4846ea19877ae47094/shapely-2.2.0-cp315-cp315t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c3caa4c6308e7eaf18f4661134a1575eb290a56df78d0ae1b02f919a4cc7bd9d", size = 2296432, upload-time = "2026-10-07T09:17:48.895Z" }, + { url = "https://files.pythonhosted.org/packages/c5/29/2b38bbe8b9b2dba0838b7718819e8751490e3d946cff232049d0e707f98e/shapely-2.2.0-cp315-cp315t-musllinux_1_2_aarch64.whl", hash = "sha256:2fd87e55d7a7d310553b527378545cdc6ef8702473ed9294926b892c3cfb2ba0", size = 3243397, upload-time = "2026-10-07T09:17:50.885Z" }, + { url = "https://files.pythonhosted.org/packages/e8/1c/5430d8d6559c944ac673984f25989121abfd2bac4254ec3fff1d7673b7bc/shapely-2.2.0-cp315-cp315t-musllinux_1_2_x86_64.whl", hash = "sha256:7416db8ff3a1003687d4118e741343b3cf9ac2a4a925a59d44d98a865ac4e9e7", size = 3386299, upload-time = "2026-10-07T09:17:52.969Z" }, + { url = "https://files.pythonhosted.org/packages/5b/00/feaeb392e96063717387ec09e6c8e38b29fe4088ddfe976470255c69792e/shapely-2.2.0-cp315-cp315t-win32.whl", hash = "sha256:778421a19085bef1fb38bc0699db1ee9b08fdd0e30a8768788d601a4371f2de0", size = 1675823, upload-time = "2026-10-07T09:17:55.022Z" }, + { url = "https://files.pythonhosted.org/packages/0e/30/0b77618f33fecbc2209c767cecca58bbf83947fc0018571542bf2b859865/shapely-2.2.0-cp315-cp315t-win_amd64.whl", hash = "sha256:287ec7602f7a114b862ae0123880e57160cebe059843a4c7028aaee9e74287f6", size = 1866197, upload-time = "2026-10-07T09:17:56.991Z" }, + { url = "https://files.pythonhosted.org/packages/06/2b/9837e94408335520f778b09067fced0a5d4b2feffa5ebf7119412eb18b00/shapely-2.2.0-cp315-cp315t-win_arm64.whl", hash = "sha256:e414c78bc81aadd76a429111a350f4ef3d05fc13019805617b524951258468e5", size = 1945749, upload-time = "2026-10-07T09:17:59.116Z" }, +] + +[[package]] +name = "six" +version = "1.17.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/94/e7/b2c673351809dca68a0e064b6af791aa332cf192da575fd474ed7d6f16a2/six-1.17.0.tar.gz", hash = "sha256:ff70335d468e7eb6ec65b95b99d3a2836546063f63acc5171de367e834932a81", size = 34031, upload-time = "2024-12-04T17:35:28.174Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274", size = 11050, upload-time = "2024-12-04T17:35:26.475Z" }, +] + [[package]] name = "soupsieve" version = "4.0.1" @@ -845,6 +1242,18 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/2c/5c/4f68370847b561a389dd9a2d7eb3d19fd8cbb8acbae543a0c6b8d0d9700b/soupsieve-4.0.1-py3-none-any.whl", hash = "sha256:2e68cf7dd5a0f29d81f9d485275ccf294e6475f615e211895d91cb81f8614f04", size = 50688, upload-time = "2026-11-04T16:36:26.158Z" }, ] +[[package]] +name = "tqdm" +version = "4.70.1" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "colorama", marker = "sys_platform == 'win32'" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/0d/ea/b2a5bd54b28a324dae8211928b2d730b6547500342c7e6c6dea08bd0a485/tqdm-4.70.1.tar.gz", hash = "sha256:cefd0eca11b2a37a3aee776544d4f4ae913f02688135b5556b8788dfa474afc4", size = 171846, upload-time = "2026-09-11T07:25:16.601Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/a7/03/921a3d3c75785aca9ebfbfcabfbc3a1be12e2ab5265deb026d55a5a3f83e/tqdm-4.70.1-py3-none-any.whl", hash = "sha256:c293e525e6fef9c20e8728fd4612df02a0aa31bb5fe91ecd93e123b1b7bffa73", size = 80199, upload-time = "2026-09-11T07:25:14.599Z" }, +] + [[package]] name = "typeguard" version = "4.6.0" @@ -932,6 +1341,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/67/81/4add07e5172b7ac40d8ed5ff580409a7801a4fe26d529bdd915401dabfbe/typing_inspection-0.4.4-py3-none-any.whl", hash = "sha256:65b8397ba37ccbce054456aaccddfc91e6e3083c92824df348d96ca832f3f147", size = 14750, upload-time = "2026-08-12T12:37:24.648Z" }, ] +[[package]] +name = "urllib3" +version = "2.8.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/e3/05/b17359e1cefb4f909b5e40b1b90a496d987258916dbbf88e842c729f510e/urllib3-2.8.0.tar.gz", hash = "sha256:63bf2ead4c879426ebf22ef2a781eeb4aa3b4ae798a0435506f8687fd5bb9b63", size = 458972, upload-time = "2026-09-15T19:29:36.253Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/92/9d/c4e665119135114480843e7ab388fa94d8480650450e6f8e26b70d323a4c/urllib3-2.8.0-py3-none-any.whl", hash = "sha256:0cf3cae568d36aa9576b28dfb35f11328f1cb974ca7647d9475ebb86c75ac6e3", size = 135717, upload-time = "2026-09-15T19:29:34.577Z" }, +] + [[package]] name = "xlrd" version = "2.0.2" diff --git a/docs/design.md b/docs/design.md index 6c2318c..a8ce068 100644 --- a/docs/design.md +++ b/docs/design.md @@ -81,7 +81,7 @@ | 数据库 | 服务器上 1Panel 的 PostgreSQL 18 | 和鼠洞共用实例，不加新服务 | | 抓取节点 | Python 3.14，uv 管依赖；Ruff 做 lint 和格式化，Pyright 的严格模式做类型检查，pytest 做测试 | 浏览器抓取、正文提取、PDF 和 Office 解析、中文的文字识别，Python 的库最全，代价是多一套工具链。3.15 刚发布，文字识别要用的 onnxruntime 还没有它的安装包。Pyright 和 VS Code 的 Pylance 是同一个引擎，编辑器里看到的错误和 CI 一致 | | 抓取 | httpx（异步）请求网页，Playwright 驱动浏览器（Chromium 的无头精简版），lxml 按 CSS 或 XPath 取出列表 | 各自领域的主流库 | -| 正文、附件和文字识别 | 正文按建站系统的模板用 lxml 取；pypdf 读 PDF，python-docx 读 `.docx`，legacy-doc 读老的 `.doc`，openpyxl 读 `.xlsx`，xlrd 读 `.xls`；文字识别候选 RapidOCR | 都关在 `parse` 模块里，换了不影响别处。正文和附件用真实的通知和附件比较后定，结果见第 5.2 节；文字识别在[文字识别](https://github.com/mousebaoyan/mouseclock/issues/47)的任务里定。不用 AGPL 许可的 PyMuPDF | +| 正文、附件和文字识别 | 正文按建站系统的模板用 lxml 取；pypdf 读 PDF，python-docx 读 `.docx`，legacy-doc 读老的 `.doc`，openpyxl 读 `.xlsx`，xlrd 读 `.xls`；图片的文字识别用 RapidOCR（PP-OCRv6 small，设置见第 5.2 节） | 都关在 `parse` 模块里，换了不影响别处。正文和附件用真实的通知和附件比较后定，结果见第 5.2 节；扫描的 PDF 用哪个库渲染成图片，在[文字识别](https://github.com/mousebaoyan/mouseclock/issues/47)的任务里定。不用 AGPL 许可的 PyMuPDF | | 接口的类型 | 网站用 Zod 写接口的定义，生成 OpenAPI 文档；抓取节点从这份文档生成 Pydantic 模型 | 两边语言不同，接口的类型也只有一个来源。抓取节点用 Pydantic 校验网站的返回和模型的输出 | | 判别接口和 LLM | System One 的 SemIf；DeepSeek 官方接口的 V4.1 Flash（`deepseek-flash`），按编号抽取 | 判别见第 8.1 节，抽取比较见第 8.5 节 | @@ -117,9 +117,21 @@ CPU 不是问题，要省的是带宽，做法见第 14 节。 | Excel | openpyxl 读 `.xlsx`，xlrd 读 `.xls`，样本里各 1 个都没问题 | | 下载 | 7 次拿到的不是文件，是博达的「请输入验证码下载附件」页面（北科计通、厦大、电子科大信通、国科大杭州等）；先打开通知页、带着来源页下载也一样，是网站的设置。按第 7.2 节不破解：附件照样列出，文字留空，不存文件 | -**文字识别**：RapidOCR（PP-OCRv6）识别一张 20 行的中文页面约 1 秒，进程峰值约 690MB；抓取节点只有 4 核，会慢几倍。 +**文字识别**：从 `data/sources.csv` 的 9 个来源各取一张通知图片（截图、海报、长图、密集的日程表），加一份渲染成图片的 4 页 PDF，在限成 4 核、3600 MiB、断网的 Linux 容器里用 RapidOCR 3.10.0 依次识别。只看日期、时刻、网址和邮箱：同一行里和原文一字不差才算对，一张里错一项就不算全对；有这些信息的共 12 张（页）。 -抓取节点同时开 2 个浏览器页面、一次识别一张图，峰值约 1.4GB，3.6GB 内存够用（第 16 节）。 +| PP-OCRv6 | 设置 | 关键信息全对 | 13 张（页）总耗时 | 峰值内存 | 模型文件 | +| --- | --- | ---: | ---: | ---: | ---: | +| tiny | 整图缩到 2000 | 2/12 | 85.19 秒 | 784.1 MiB | 6.58 MiB | +| small | 整图缩到 2000 | 4/12 | 289.04 秒 | 1151.2 MiB | 30.28 MiB | +| medium | 整图缩到 2000 | 4/12 | 842.72 秒 | 2077.9 MiB | 132.88 MiB | +| tiny | 整图缩到 4000 | 3/12 | 137.21 秒 | 1694.2 MiB | 6.58 MiB | +| small | 整图缩到 4000 | 5/12 | 354.25 秒 | 2058.8 MiB | 30.28 MiB | +| medium | 整图缩到 4000 | 7/12 | 1112.38 秒 | 3305.9 MiB | 132.88 MiB | +| small | 缩到 2000 找行，从原图切行，每批 1 行 | 7/12 | 240.87 秒 | 726.0 MiB | 30.28 MiB | + +选 small，在缩到 2000 的图上找行、从原图上切行识别，一次认一行：默认把整张图缩到 2000 再识别，长截图的字太小；把整张图放到 4000 仍少两张全对，检测还要多占 1GB 以上；medium 在三档整图方案里最准，但单独识别就占 3.3GB，给浏览器留不出余量。把 `text_score` 从默认的 0.5 降到 0.3 没找回关键信息，反而多出两行乱码，因此保留 0.5。三档都会漏掉整行的网址、拆开表格里的日程，图片里认出的关键信息不能当作可靠的原文，相关字段交给人审核，不根据上下文猜。 + +抓取节点同时开 2 个浏览器页面（约 450 MiB）、一次识别一张图（峰值 726 MiB），合计约 1.2 GiB，3.6GB 内存够用（第 16 节）。 ## 6. 账号与权限 @@ -591,7 +603,7 @@ L3 以上可以不提申请，直接修改，同样要写理由、附依据。 | 部分 | 放在哪 | 说明 | | --- | --- | --- | | 网站 | 香港的服务器，和鼠洞同一台 | 容器部署，前面是 1Panel 的 OpenResty；数据库用服务器上 1Panel 的 PostgreSQL | -| 抓取节点 | 上海的机器：4 核、3.6GB 内存 | 容器部署；浏览器抓取同时最多开 2 个页面，文字识别一次只做一张，内存峰值约 1.4GB（第 5.2 节） | +| 抓取节点 | 上海的机器：4 核、3.6GB 内存 | 容器部署；浏览器抓取同时最多开 2 个页面（约 450 MiB），文字识别一次只做一张（峰值 726 MiB），合计约 1.2 GiB，3.6GB 内存够用（第 5.2 节） | - 抓取节点每分钟向网站领一次活：到期要抓的来源和管理员要试抓的来源。抓取节点停了，网站照常能用，只是没有新数据；抓取看板会显示抓取节点多久没来领活。 - 为什么分开：实测 11 所学校和研究所的官网和研招网，香港和上海都能访问（浙大要用 HTTP），但从上海访问快 2–4 倍；浏览器抓取和附件解析吃 CPU 和内存，放在上海也不占网站服务器的资源。判别和抽取都调用外部接口，抓取节点不跑模型。 @@ -628,7 +640,7 @@ L3 以上可以不提申请，直接修改，同样要写理由、附依据。 | 事项 | 现状 | | --- | --- | | 名称 | 「鼠钟」暂定，帖子里在征名 | -| 文字识别用的库 | 用真实的图片和扫描件比较后定（第 5.1 节） | +| 扫描的 PDF 用哪个库渲染成图片 | 在文字识别任务里比较后定（第 5.1 节） | | 域名 | 待定，用 `mousebaoyan.cn` 的子域名 | | 群汇总由哪个插件发 | 扩展鼠洞的 bot 插件，还是新写一个 | | 第一批来源 | 先收对四非友好的学校，名单在帖子里征集 |