herocode/herolib_python
12
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

...

Browse Source
This commit is contained in:
despiegk 2025-08-08 09:38:37 +02:00
parent 824c71ef98
commit 749c89aefc
4 changed files with 216 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
env.sh
View File

@ -25,6 +25,8 @@ else
echo "✅ Virtual environment already exists"
fi
export PATH="$SCRIPT_DIR/.venv/bin:$PATH"
# Activate virtual environment
echo "🔄 Activating virtual environment..."
source .venv/bin/activate

86
examples/scrapper/yew_docs.sh Executable file
View File

@ -0,0 +1,86 @@
#!/bin/bash
set -ex
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
cd "$SCRIPT_DIR"
source ../../env.sh
cd "$SCRIPT_DIR"
# 1. Install dependencies
uv pip install --upgrade scrapy markdownify
#!/bin/bash
set -e
# Ensure clean environment
rm -rf yew_docs output
# 1. Install required packages
uv pip install --upgrade scrapy markdownify
# 2. Create Scrapy project
scrapy startproject yew_docs
cd yew_docs
# 3. Update settings to ignore robots.txt and set export directory
echo -e "\nROBOTSTXT_OBEY = False" >> yew_docs/settings.py
# 4. Create Spider with filters
cat << 'EOF' > yew_docs/spiders/yew_docs_spider.py
import os
import scrapy
from urllib.parse import urlparse, urljoin
import markdownify
class YewDocsSpider(scrapy.Spider):
name = "yew_docs"
allowed_domains = ["yew.rs"]
start_urls = ["https://yew.rs/docs/getting-started/introduction"]
def parse(self, response):
# Extract title
title = response.css("title::text").get() or "Page"
# Extract main content
main = response.css("main").get()
if not main:
self.logger.warning(f"No main content at {response.url}")
return
# Convert to Markdown
md = markdownify.markdownify(main, heading_style="ATX")
# Construct clean file path
parsed = urlparse(response.url)
path = parsed.path.lstrip("/")
if path.endswith("/") or path == "":
path += "index"
filepath = os.path.join("output", f"{path}.md")
os.makedirs(os.path.dirname(filepath), exist_ok=True)
with open(filepath, "w", encoding="utf-8") as f:
f.write(f"# {title.strip()}\n\n{md}")
# Follow only clean internal links under /docs/
for href in response.css("a::attr(href)").getall():
link = urljoin(response.url, href)
parsed = urlparse(link)
path = parsed.path
if parsed.netloc == "yew.rs" and path.startswith("/docs/"):
if (
"/docs/0." in path or
"/docs/next" in path or
"/docs/en" in path or
"#" in parsed.fragment or
path.count("/") > 5
):
continue
yield scrapy.Request(link.split("#")[0], callback=self.parse)
EOF
# 5. Run the spider
scrapy crawl yew_docs

6
pyproject.toml
View File

@ -7,5 +7,9 @@ dependencies = [
"peewee>=3.17.0",
"pygments>=2.16.1",
"toml",
"requests>=2.31.0"
"requests>=2.31.0",
"beautifulsoup4>=4.12.2",
"pydantic>=2.8.0",
"scrapy==2.13.3",
"markdownify=1.1.0"
]

123
uv.lock
View File

@ -2,6 +2,28 @@ version = 1
revision = 1
requires-python = ">=3.13"
[[package]]
name = "annotated-types"
version = "0.7.0"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/ee/67/531ea369ba64dcff5ec9c3402f9f51bf748cec26dde048a2f973a4eea7f5/annotated_types-0.7.0.tar.gz", hash = "sha256:aff07c09a53a08bc8cfccb9c85b05f1aa9a2a6f23728d790723543408344ce89", size = 16081 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53", size = 13643 },
]
[[package]]
name = "beautifulsoup4"
version = "4.13.4"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "soupsieve" },
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/d8/e4/0c4c39e18fd76d6a628d4dd8da40543d136ce2d1752bd6eeeab0791f4d6b/beautifulsoup4-4.13.4.tar.gz", hash = "sha256:dbb3c4e1ceae6aefebdaf2423247260cd062430a410e38c66f2baa50a8437195", size = 621067 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/50/cd/30110dc0ffcf3b131156077b90e9f60ed75711223f306da4db08eff8403b/beautifulsoup4-4.13.4-py3-none-any.whl", hash = "sha256:9bbbb14bfde9d79f38b8cd5f8c7c85f4b8f2523190ebed90e950a8dea4cb1c4b", size = 187285 },
]
[[package]]
name = "certifi"
version = "2025.8.3"
@ -38,7 +60,10 @@ name = "herolib"
version = "0.9.0"
source = { virtual = "." }
dependencies = [
{ name = "beautifulsoup4" },
{ name = "markdownify" },
{ name = "peewee" },
{ name = "pydantic" },
{ name = "pygments" },
{ name = "requests" },
{ name = "toml" },
@ -46,7 +71,10 @@ dependencies = [
[package.metadata]
requires-dist = [
{ name = "beautifulsoup4", specifier = ">=4.12.2" },
{ name = "markdownify" },
{ name = "peewee", specifier = ">=3.17.0" },
{ name = "pydantic", specifier = ">=2.8.0" },
{ name = "pygments", specifier = ">=2.16.1" },
{ name = "requests", specifier = ">=2.31.0" },
{ name = "toml" },
@ -61,12 +89,68 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3", size = 70442 },
]
[[package]]
name = "markdownify"
version = "1.1.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "beautifulsoup4" },
{ name = "six" },
]
sdist = { url = "https://files.pythonhosted.org/packages/2f/78/c48fed23c7aebc2c16049062e72de1da3220c274de59d28c942acdc9ffb2/markdownify-1.1.0.tar.gz", hash = "sha256:449c0bbbf1401c5112379619524f33b63490a8fa479456d41de9dc9e37560ebd", size = 17127 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/64/11/b751af7ad41b254a802cf52f7bc1fca7cabe2388132f2ce60a1a6b9b9622/markdownify-1.1.0-py3-none-any.whl", hash = "sha256:32a5a08e9af02c8a6528942224c91b933b4bd2c7d078f9012943776fc313eeef", size = 13901 },
]
[[package]]
name = "peewee"
version = "3.18.2"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/04/89/76f6f1b744c8608e0d416b588b9d63c2a500ff800065ae610f7c80f532d6/peewee-3.18.2.tar.gz", hash = "sha256:77a54263eb61aff2ea72f63d2eeb91b140c25c1884148e28e4c0f7c4f64996a0", size = 949220 }
[[package]]
name = "pydantic"
version = "2.11.7"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "annotated-types" },
{ name = "pydantic-core" },
{ name = "typing-extensions" },
{ name = "typing-inspection" },
]
sdist = { url = "https://files.pythonhosted.org/packages/00/dd/4325abf92c39ba8623b5af936ddb36ffcfe0beae70405d456ab1fb2f5b8c/pydantic-2.11.7.tar.gz", hash = "sha256:d989c3c6cb79469287b1569f7447a17848c998458d49ebe294e975b9baf0f0db", size = 788350 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/6a/c0/ec2b1c8712ca690e5d61979dee872603e92b8a32f94cc1b72d53beab008a/pydantic-2.11.7-py3-none-any.whl", hash = "sha256:dde5df002701f6de26248661f6835bbe296a47bf73990135c7d07ce741b9623b", size = 444782 },
]
[[package]]
name = "pydantic-core"
version = "2.33.2"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/ad/88/5f2260bdfae97aabf98f1778d43f69574390ad787afb646292a638c923d4/pydantic_core-2.33.2.tar.gz", hash = "sha256:7cb8bc3605c29176e1b105350d2e6474142d7c1bd1d9327c4a9bdb46bf827acc", size = 435195 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/46/8c/99040727b41f56616573a28771b1bfa08a3d3fe74d3d513f01251f79f172/pydantic_core-2.33.2-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:1082dd3e2d7109ad8b7da48e1d4710c8d06c253cbc4a27c1cff4fbcaa97a9e3f", size = 2015688 },
{ url = "https://files.pythonhosted.org/packages/3a/cc/5999d1eb705a6cefc31f0b4a90e9f7fc400539b1a1030529700cc1b51838/pydantic_core-2.33.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:f517ca031dfc037a9c07e748cefd8d96235088b83b4f4ba8939105d20fa1dcd6", size = 1844808 },
{ url = "https://files.pythonhosted.org/packages/6f/5e/a0a7b8885c98889a18b6e376f344da1ef323d270b44edf8174d6bce4d622/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0a9f2c9dd19656823cb8250b0724ee9c60a82f3cdf68a080979d13092a3b0fef", size = 1885580 },
{ url = "https://files.pythonhosted.org/packages/3b/2a/953581f343c7d11a304581156618c3f592435523dd9d79865903272c256a/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2b0a451c263b01acebe51895bfb0e1cc842a5c666efe06cdf13846c7418caa9a", size = 1973859 },
{ url = "https://files.pythonhosted.org/packages/e6/55/f1a813904771c03a3f97f676c62cca0c0a4138654107c1b61f19c644868b/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1ea40a64d23faa25e62a70ad163571c0b342b8bf66d5fa612ac0dec4f069d916", size = 2120810 },
{ url = "https://files.pythonhosted.org/packages/aa/c3/053389835a996e18853ba107a63caae0b9deb4a276c6b472931ea9ae6e48/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0fb2d542b4d66f9470e8065c5469ec676978d625a8b7a363f07d9a501a9cb36a", size = 2676498 },
{ url = "https://files.pythonhosted.org/packages/eb/3c/f4abd740877a35abade05e437245b192f9d0ffb48bbbbd708df33d3cda37/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9fdac5d6ffa1b5a83bca06ffe7583f5576555e6c8b3a91fbd25ea7780f825f7d", size = 2000611 },
{ url = "https://files.pythonhosted.org/packages/59/a7/63ef2fed1837d1121a894d0ce88439fe3e3b3e48c7543b2a4479eb99c2bd/pydantic_core-2.33.2-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:04a1a413977ab517154eebb2d326da71638271477d6ad87a769102f7c2488c56", size = 2107924 },
{ url = "https://files.pythonhosted.org/packages/04/8f/2551964ef045669801675f1cfc3b0d74147f4901c3ffa42be2ddb1f0efc4/pydantic_core-2.33.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:c8e7af2f4e0194c22b5b37205bfb293d166a7344a5b0d0eaccebc376546d77d5", size = 2063196 },
{ url = "https://files.pythonhosted.org/packages/26/bd/d9602777e77fc6dbb0c7db9ad356e9a985825547dce5ad1d30ee04903918/pydantic_core-2.33.2-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:5c92edd15cd58b3c2d34873597a1e20f13094f59cf88068adb18947df5455b4e", size = 2236389 },
{ url = "https://files.pythonhosted.org/packages/42/db/0e950daa7e2230423ab342ae918a794964b053bec24ba8af013fc7c94846/pydantic_core-2.33.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:65132b7b4a1c0beded5e057324b7e16e10910c106d43675d9bd87d4f38dde162", size = 2239223 },
{ url = "https://files.pythonhosted.org/packages/58/4d/4f937099c545a8a17eb52cb67fe0447fd9a373b348ccfa9a87f141eeb00f/pydantic_core-2.33.2-cp313-cp313-win32.whl", hash = "sha256:52fb90784e0a242bb96ec53f42196a17278855b0f31ac7c3cc6f5c1ec4811849", size = 1900473 },
{ url = "https://files.pythonhosted.org/packages/a0/75/4a0a9bac998d78d889def5e4ef2b065acba8cae8c93696906c3a91f310ca/pydantic_core-2.33.2-cp313-cp313-win_amd64.whl", hash = "sha256:c083a3bdd5a93dfe480f1125926afcdbf2917ae714bdb80b36d34318b2bec5d9", size = 1955269 },
{ url = "https://files.pythonhosted.org/packages/f9/86/1beda0576969592f1497b4ce8e7bc8cbdf614c352426271b1b10d5f0aa64/pydantic_core-2.33.2-cp313-cp313-win_arm64.whl", hash = "sha256:e80b087132752f6b3d714f041ccf74403799d3b23a72722ea2e6ba2e892555b9", size = 1893921 },
{ url = "https://files.pythonhosted.org/packages/a4/7d/e09391c2eebeab681df2b74bfe6c43422fffede8dc74187b2b0bf6fd7571/pydantic_core-2.33.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:61c18fba8e5e9db3ab908620af374db0ac1baa69f0f32df4f61ae23f15e586ac", size = 1806162 },
{ url = "https://files.pythonhosted.org/packages/f1/3d/847b6b1fed9f8ed3bb95a9ad04fbd0b212e832d4f0f50ff4d9ee5a9f15cf/pydantic_core-2.33.2-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95237e53bb015f67b63c91af7518a62a8660376a6a0db19b89acc77a4d6199f5", size = 1981560 },
{ url = "https://files.pythonhosted.org/packages/6f/9a/e73262f6c6656262b5fdd723ad90f518f579b7bc8622e43a942eec53c938/pydantic_core-2.33.2-cp313-cp313t-win_amd64.whl", hash = "sha256:c2fc0a768ef76c15ab9238afa6da7f69895bb5d1ee83aeea2e3509af4472d0b9", size = 1935777 },
]
[[package]]
name = "pygments"
version = "2.19.2"
@ -91,6 +175,24 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/7c/e4/56027c4a6b4ae70ca9de302488c5ca95ad4a39e190093d6c1a8ace08341b/requests-2.32.4-py3-none-any.whl", hash = "sha256:27babd3cda2a6d50b30443204ee89830707d396671944c998b5975b031ac2b2c", size = 64847 },
]
[[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 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274", size = 11050 },
]
[[package]]
name = "soupsieve"
version = "2.7"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/3f/f4/4a80cd6ef364b2e8b65b15816a843c0980f7a5a2b4dc701fc574952aa19f/soupsieve-2.7.tar.gz", hash = "sha256:ad282f9b6926286d2ead4750552c8a6142bc4c783fd66b0293547c8fe6ae126a", size = 103418 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/e7/9c/0e6afc12c269578be5c0c1c9f4b49a8d32770a080260c333ac04cc1c832d/soupsieve-2.7-py3-none-any.whl", hash = "sha256:6e60cc5c1ffaf1cebcc12e8188320b72071e922c2e897f737cadce79ad5d30c4", size = 36677 },
]
[[package]]
name = "toml"
version = "0.10.2"
@ -100,6 +202,27 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/44/6f/7120676b6d73228c96e17f1f794d8ab046fc910d781c8d151120c3f1569e/toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b", size = 16588 },
]
[[package]]
name = "typing-extensions"
version = "4.14.1"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/98/5a/da40306b885cc8c09109dc2e1abd358d5684b1425678151cdaed4731c822/typing_extensions-4.14.1.tar.gz", hash = "sha256:38b39f4aeeab64884ce9f74c94263ef78f3c22467c8724005483154c26648d36", size = 107673 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/b5/00/d631e67a838026495268c2f6884f3711a15a9a2a96cd244fdaea53b823fb/typing_extensions-4.14.1-py3-none-any.whl", hash = "sha256:d1e1e3b58374dc93031d6eda2420a48ea44a36c2b4766a4fdeb3710755731d76", size = 43906 },
]
[[package]]
name = "typing-inspection"
version = "0.4.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/f8/b1/0c11f5058406b3af7609f121aaa6b609744687f1d158b3c3a5bf4cc94238/typing_inspection-0.4.1.tar.gz", hash = "sha256:6ae134cc0203c33377d43188d4064e9b357dba58cff3185f22924610e70a9d28", size = 75726 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/17/69/cd203477f944c353c31bade965f880aa1061fd6bf05ded0726ca845b6ff7/typing_inspection-0.4.1-py3-none-any.whl", hash = "sha256:389055682238f53b04f7badcb49b989835495a96700ced5dab2d8feae4b26f51", size = 14552 },
]
[[package]]
name = "urllib3"
version = "2.5.0"