Skip to content

🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev

build: pump up version, browsers and deps

Karim shoair4ced6e4ac268
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index f82605d..930d0a0 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -73,7 +73,7 @@ jobs:
- name: Install all browsers dependencies
run: |
python3 -m pip install --upgrade pip
- python3 -m pip install playwright==1.59.0 patchright==1.59.1
+ python3 -m pip install playwright==1.60.0 patchright==1.60.1
- name: Get Playwright version
id: playwright-version
diff --git a/agent-skill/Scrapling-Skill.zip b/agent-skill/Scrapling-Skill.zip
index 22fbb32..1a8d15b 100644
Binary files a/agent-skill/Scrapling-Skill.zip and b/agent-skill/Scrapling-Skill.zip differ
diff --git a/agent-skill/Scrapling-Skill/SKILL.md b/agent-skill/Scrapling-Skill/SKILL.md
index 27c31c0..ab57268 100644
--- a/agent-skill/Scrapling-Skill/SKILL.md
+++ b/agent-skill/Scrapling-Skill/SKILL.md
@@ -1,7 +1,7 @@
---
name: scrapling-official
description: Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; web_fetch fails; the site has anti-bot protections; write Python code to scrape/crawl; or write spiders.
-version: "0.4.8"
+version: "0.4.9"
license: Complete terms in LICENSE.txt
metadata:
homepage: "https://scrapling.readthedocs.io/en/latest/index.html"
@@ -40,7 +40,7 @@ Blazing fast crawls with real-time stats and streaming. Built by Web Scrapers fo
Create a virtual Python environment through any way available, like `venv`, then inside the environment do:
-`pip install "scrapling[all]>=0.4.8"`
+`pip install "scrapling[all]>=0.4.9"`
Then do this to download all the browsers' dependencies:
diff --git a/agent-skill/Scrapling-Skill/examples/README.md b/agent-skill/Scrapling-Skill/examples/README.md
index d0f9a2b..85de486 100644
--- a/agent-skill/Scrapling-Skill/examples/README.md
+++ b/agent-skill/Scrapling-Skill/examples/README.md
@@ -9,7 +9,7 @@ All examples collect **all 100 quotes across 10 pages**.
Make sure Scrapling is installed:
```bash
-pip install "scrapling[all]>=0.4.8"
+pip install "scrapling[all]>=0.4.9"
scrapling install --force
```
diff --git a/pyproject.toml b/pyproject.toml
index 8cb4768..9c390c0 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
[project]
name = "scrapling"
# Static version instead of a dynamic version so we can get better layer caching while building docker, check the docker file to understand
-version = "0.4.8"
+version = "0.4.9"
description = "Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy and effortless as it should be!"
readme = {file = "README.md", content-type = "text/markdown"}
license = {file = "LICENSE"}
@@ -61,7 +61,7 @@ classifiers = [
"Typing :: Typed",
]
dependencies = [
- "lxml>=6.1.0",
+ "lxml>=6.1.1",
"cssselect>=1.4.0",
"orjson>=3.11.8",
"tld>=0.13.2",
@@ -73,8 +73,8 @@ dependencies = [
fetchers = [
"click>=8.3.0",
"curl_cffi>=0.15.0",
- "playwright==1.59.0",
- "patchright==1.59.1",
+ "playwright==1.60.0",
+ "patchright==1.60.1",
"browserforge>=1.2.4",
"apify-fingerprint-datapoints>=0.13.0",
"msgspec>=0.21.1",
diff --git a/scrapling/__init__.py b/scrapling/__init__.py
index 3420e25..a5ff5eb 100644
--- a/scrapling/__init__.py
+++ b/scrapling/__init__.py
@@ -1,5 +1,5 @@
__author__ = "Karim Shoair ([email protected])"
-__version__ = "0.4.8"
+__version__ = "0.4.9"
__copyright__ = "Copyright (c) 2024 Karim Shoair"
from typing import Any, TYPE_CHECKING
diff --git a/scrapling/engines/toolbelt/fingerprints.py b/scrapling/engines/toolbelt/fingerprints.py
index f4fdfc1..0c02002 100644
--- a/scrapling/engines/toolbelt/fingerprints.py
+++ b/scrapling/engines/toolbelt/fingerprints.py
@@ -13,8 +13,8 @@ from scrapling.core._types import Dict, Literal, Tuple
__OS_NAME__ = platform_system()
OSName = Literal["linux", "macos", "windows"]
# Current versions hardcoded for now (Playwright doesn't allow to know the version of a browser without launching it)
-chromium_version = 147
-chrome_version = 147
+chromium_version = 148
+chrome_version = 148
@lru_cache(1, typed=True)
diff --git a/server.json b/server.json
index e4e813e..deccdda 100644
--- a/server.json
+++ b/server.json
@@ -14,12 +14,12 @@
"mimeType": "image/png"
}
],
- "version": "0.4.8",
+ "version": "0.4.9",
"packages": [
{
"registryType": "pypi",
"identifier": "scrapling",
- "version": "0.4.8",
+ "version": "0.4.9",
"runtimeHint": "uvx",
"packageArguments": [
{
diff --git a/setup.cfg b/setup.cfg
index 1c967c8..4e3d8b6 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,6 +1,6 @@
[metadata]
name = scrapling
-version = 0.4.8
+version = 0.4.9
author = Karim Shoair
author_email = [email protected]
description = Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy and effortless as it should be!
diff --git a/tests/requirements.txt b/tests/requirements.txt
index 83aa3dc..7c9c3ff 100644
--- a/tests/requirements.txt
+++ b/tests/requirements.txt
@@ -1,6 +1,6 @@
pytest>=2.8.0,<9
pytest-cov
-playwright==1.59.0
+playwright==1.60.0
werkzeug<3.0.0
pytest-httpbin==2.1.0
pytest-asyncio
diff --git a/tox.ini b/tox.ini
index e740705..799ceae 100644
--- a/tox.ini
+++ b/tox.ini
@@ -10,8 +10,8 @@ envlist = pre-commit,py{310,311,312,313}
usedevelop = True
changedir = tests
deps =
- playwright==1.59.0
- patchright==1.59.1
+ playwright==1.60.0
+ patchright==1.60.1
-r{toxinidir}/tests/requirements.txt
extras = ai,shell
commands =