🕷️ 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
Python aiai-scrapingautomationcrawlercrawlingcrawling-pythondatadata-extractionmcpmcp-serverplaywrightpythonscrapingselectorsstealthweb-scraperweb-scrapingweb-scraping-pythonwebscrapingxpath
build: pump version and deps
Karim shoair346fe9c25cd5
diff --git a/.github/workflows/docker-build.yml b/.github/workflows/docker-build.ymlindex 5156c6c..aedbefd 100644--- a/.github/workflows/docker-build.yml+++ b/.github/workflows/docker-build.yml@@ -8,7 +8,7 @@ on:workflow_dispatch:inputs:version:- description: "Release version to tag the images with, like 'v0.4.12'. Leave it empty to only push 'latest'"+ description: "Release version to tag the images with, like 'v0.4.13'. Leave it empty to only push 'latest'"required: falsedefault: ''diff --git a/agent-skill/Scrapling-Skill/SKILL.md b/agent-skill/Scrapling-Skill/SKILL.mdindex 71d3834..d0b93e9 100644--- a/agent-skill/Scrapling-Skill/SKILL.md+++ b/agent-skill/Scrapling-Skill/SKILL.md@@ -1,7 +1,7 @@---name: scrapling-officialdescription: 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: "0.4.12"+version: "0.4.13"license: Complete terms in LICENSE.txtmetadata: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 foCreate a virtual Python environment through any way available, like `venv`, then inside the environment do:-`pip install "scrapling[all]>=0.4.12"`+`pip install "scrapling[all]>=0.4.13"`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.mdindex 1c0ed58..083eab0 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]>=0.4.12"+pip install "scrapling[all]>=0.4.13"scrapling install --force```diff --git a/pyproject.toml b/pyproject.tomlindex 3511a85..c20f592 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 = "0.4.12"+version = "0.4.13"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"}@@ -62,7 +62,7 @@ classifiers = []dependencies = ["lxml>=6.1.1",- "cssselect>=1.4.0",+ "cssselect>=1.5.0","orjson>=3.11.8","tld>=0.13.2","w3lib>=2.4.1",@@ -72,7 +72,7 @@ dependencies = [[project.optional-dependencies]fetchers = ["click>=8.3.0",- "curl_cffi>=0.15.0",+ "curl_cffi>=0.16.1b1","playwright>=1.61.0","patchright>=1.61.2","browserforge>=1.2.4",diff --git a/scrapling/__init__.py b/scrapling/__init__.pyindex 0b8276a..9ebc1f9 100644--- a/scrapling/__init__.py+++ b/scrapling/__init__.py@@ -1,5 +1,5 @@__author__ = "Karim Shoair ([email protected])"-__version__ = "0.4.12"+__version__ = "0.4.13"__copyright__ = "Copyright (c) 2024 Karim Shoair"from typing import Any, TYPE_CHECKINGdiff --git a/scrapling/engines/toolbelt/fingerprints.py b/scrapling/engines/toolbelt/fingerprints.pyindex bb77ea5..80b004d 100644--- a/scrapling/engines/toolbelt/fingerprints.py+++ b/scrapling/engines/toolbelt/fingerprints.py@@ -18,6 +18,7 @@ from scrapling.core._types import Dict, Literal, Tuple__OS_NAME__ = platform_system()OSName = Literal["linux", "macos", "windows", "android", "ios"]DESKTOP_OS = ("linux", "macos", "windows")+MINIMUM_VERSION = 149@lru_cache(1, typed=True)@@ -74,7 +75,7 @@ def generate_headers(browser_mode: bool | str = False) -> Dict:)if not browser_mode and os_name in DESKTOP_OS:os_name = DESKTOP_OS- browsers = [Browser(name="chrome", min_version=149)]+ browsers = [Browser(name="chrome", min_version=MINIMUM_VERSION)]if not browser_mode:browsers.extend([Browser(name="firefox", min_version=147), Browser(name="edge", min_version=145)])try:diff --git a/server.json b/server.jsonindex b817067..376a16d 100644--- a/server.json+++ b/server.json@@ -14,12 +14,12 @@"mimeType": "image/png"}],- "version": "0.4.12",+ "version": "0.4.13","packages": [{"registryType": "pypi","identifier": "scrapling",- "version": "0.4.12",+ "version": "0.4.13","runtimeHint": "uvx","packageArguments": [{diff --git a/setup.cfg b/setup.cfgindex 7a34928..fb37013 100644--- a/setup.cfg+++ b/setup.cfg@@ -1,6 +1,6 @@[metadata]name = scrapling-version = 0.4.12+version = 0.4.13author = Karim Shoairauthor_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!