</picture>
</a>


<small>Effortless Web Scraping for the Modern Web</small>

<a href="https://discord.gg/EMgGbDceNQ" alt="Discord" target="_blank">
  
</a>
<a href="https://x.com/Scrapling_dev" alt="X (formerly Twitter)">
  
</a>


<a href="https://pypi.org/project/scrapling/" alt="Supported Python versions">
    </a>

from scrapling.fetchers import Fetcher, AsyncFetcher, StealthyFetcher, DynamicFetcher
StealthyFetcher.adaptive = True
p = StealthyFetcher.fetch('https://example.com', headless=True, network_idle=True)  # 隐秘地获取网站！
products = p.css('.product', auto_save=True)                                        # 抓取在网站设计变更后仍能存活的数据！
products = p.css('.product', adaptive=True)                                         # 之后，如果网站结构改变，传递 `adaptive=True` 来找到它们！

from scrapling.spiders import Spider, Response

class MySpider(Spider):
  name = "demo"
  start_urls = ["https://example.com/"]

  async def parse(self, response: Response):
      for item in response.css('.product'):
          yield {"title": item.css('h2::text').get()}

MySpider().start()

</a>

  </a>
</td>
<td> Scrapling 可处理 Cloudflare Turnstile。对于企业级保护，<a href="https://hypersolutions.co?utm_source=github&utm_medium=readme&utm_campaign=scrapling">
    <b>Hyper Solutions</b>
  </a> 提供 API 端点，生成适用于 <b>Akamai</b>、<b>DataDome</b>、<b>Kasada</b> 和 <b>Incapsula</b> 的有效 antibot 令牌。简单的 API 调用，无需浏览器自动化。 </td>

  </a>
</td>
<td>
  <a href="https://evomi.com?utm_source=github&utm_medium=banner&utm_campaign=d4vinci-scrapling">
    <b>Evomi</b>
  </a>：住宅代理低至 0.49 美元/GB。具备完全伪装 Chromium 的爬虫浏览器、住宅 IP、自动验证码解决和反机器人绕过。</br>
  <b>Scraper API 轻松获取结果。支持 MCP 和 N8N 集成。</b>
</td>

  </a>
</td>
<td>
  <a href="https://tikhub.io/?utm_source=github.com/D4Vinci/Scrapling&utm_medium=marketing_social&utm_campaign=retargeting&utm_content=carousel_ad" target="_blank">TikHub.io</a> 提供覆盖 16+ 平台（包括 TikTok、X、YouTube 和 Instagram）的 900+ 稳定 API，拥有 4000 万+ 数据集。

  </a>
</td>
<td>
<a href="https://www.nsocks.com/?keyword=2p67aivg" target="_blank">Nsocks</a> 提供面向开发者和爬虫的快速住宅和 ISP 代理。全球 IP 覆盖、高匿名性、智能轮换，以及可靠的自动化和数据提取性能。使用 <a href="https://www.xcrawl.com/?keyword=2p67aivg" target="_blank">Xcrawl</a> 简化大规模网页爬取。
</td>

  </a>
</td>
<td>
合上笔记本电脑，您的爬虫仍在运行。

<a href="https://petrosky.io/d4vinci" target="_blank">PetroSky VPS</a> - 为不间断自动化而生的云服务器。Windows 和 Linux 系统，完全掌控。低至 €6.99/月。
</td>

  </a>
</td>
<td>
阅读 <a href="https://substack.thewebscraping.club/p/scrapling-hands-on-guide?utm_source=github&utm_medium=repo&utm_campaign=scrapling" target="_blank">The Web Scraping Club 上关于 Scrapling 的完整评测</a>（2025 年 11 月），这是排名第一的网页抓取专业通讯。
</td>

  </a>
</td>
<td>
<a href="http://mangoproxy.com/?utm_source=D4Vinci&utm_medium=GitHub&utm_campaign=D4Vinci" target="_blank">稳定的代理</a>，适用于数据抓取、自动化和多账号管理。干净的 IP、快速响应、高负载下可靠的性能。专为可扩展的工作流程而构建。
</td>

  </a>
</td>
<td>
<a href="https://www.swiftproxy.net/?ref=D4Vinci" target="_blank">Swiftproxy</a> 提供可扩展的住宅代理，覆盖 195+ 国家/地区的 8000 万+ IP，提供快速可靠的连接、自动轮换和强大的反屏蔽性能。提供免费试用。
</td>

from scrapling.fetchers import Fetcher, FetcherSession

with FetcherSession(impersonate='chrome') as session:  # 使用 Chrome 的最新版本 TLS fingerprint
    page = session.get('https://quotes.toscrape.com/', stealthy_headers=True)
    quotes = page.css('.quote .text::text').getall()

# 或使用一次性请求
page = Fetcher.get('https://quotes.toscrape.com/')
quotes = page.css('.quote .text::text').getall()

from scrapling.fetchers import StealthyFetcher, StealthySession

with StealthySession(headless=True, solve_cloudflare=True) as session:  # 保持浏览器打开直到完成
    page = session.fetch('https://nopecha.com/demo/cloudflare', google_search=False)
    data = page.css('#padded_content a').getall()

# 或使用一次性请求样式，为此请求打开浏览器，完成后关闭
page = StealthyFetcher.fetch('https://nopecha.com/demo/cloudflare')
data = page.css('#padded_content a').getall()

from scrapling.fetchers import DynamicFetcher, DynamicSession

with DynamicSession(headless=True, disable_resources=False, network_idle=True) as session:  # 保持浏览器打开直到完成
    page = session.fetch('https://quotes.toscrape.com/', load_dom=False)
    data = page.xpath('//span[@class="text"]/text()').getall()  # 如果您偏好 XPath 选择器

# 或使用一次性请求样式，为此请求打开浏览器，完成后关闭
page = DynamicFetcher.fetch('https://quotes.toscrape.com/')
data = page.css('.quote .text::text').getall()

from scrapling.spiders import Spider, Request, Response

class QuotesSpider(Spider):
    name = "quotes"
    start_urls = ["https://quotes.toscrape.com/"]
    concurrent_requests = 10

    async def parse(self, response: Response):
        for quote in response.css('.quote'):
            yield {
                "text": quote.css('.text::text').get(),
                "author": quote.css('.author::text').get(),
            }

        next_page = response.css('.next a')
        if next_page:
            yield response.follow(next_page[0].attrib['href'])

result = QuotesSpider().start()
print(f"抓取了 {len(result.items)} 条引用")
result.items.to_json("quotes.json")

from scrapling.spiders import Spider, Request, Response
from scrapling.fetchers import FetcherSession, AsyncStealthySession

class MultiSessionSpider(Spider):
    name = "multi"
    start_urls = ["https://example.com/"]

    def configure_sessions(self, manager):
        manager.add("fast", FetcherSession(impersonate="chrome"))
        manager.add("stealth", AsyncStealthySession(headless=True), lazy=True)

    async def parse(self, response: Response):
        for link in response.css('a::attr(href)').getall():
            # 将受保护的页面路由到隐秘 Session
            if "protected" in link:
                yield Request(link, sid="stealth")
            else:
                yield Request(link, sid="fast", callback=self.parse)  # 显式 callback

QuotesSpider(crawldir="./crawl_data").start()

from scrapling.fetchers import Fetcher

# 丰富的元素选择和导航
page = Fetcher.get('https://quotes.toscrape.com/')

# 使用多种选择方法获取引用
quotes = page.css('.quote')  # CSS 选择器
quotes = page.xpath('//div[@class="quote"]')  # XPath
quotes = page.find_all('div', {'class': 'quote'})  # BeautifulSoup 风格
# 等同于
quotes = page.find_all('div', class_='quote')
quotes = page.find_all(['div'], class_='quote')
quotes = page.find_all(class_='quote')  # 等等...
# 按文本内容查找元素
quotes = page.find_by_text('quote', tag='div')

# 高级导航
quote_text = page.css('.quote')[0].css('.text::text').get()
quote_text = page.css('.quote').css('.text::text').getall()  # 链式选择器
first_quote = page.css('.quote')[0]
author = first_quote.next_sibling.css('.author::text')
parent_container = first_quote.parent

# 元素关系和相似性
similar_elements = first_quote.find_similar()
below_elements = first_quote.below_elements()

from scrapling.parser import Selector

page = Selector("<html>...</html>")

import asyncio
from scrapling.fetchers import FetcherSession, AsyncStealthySession, AsyncDynamicSession

async with FetcherSession(http3=True) as session:  # `FetcherSession`是上下文感知的，可以在 sync/async 模式下工作
    page1 = session.get('https://quotes.toscrape.com/')
    page2 = session.get('https://quotes.toscrape.com/', impersonate='firefox135')

# Async Session 用法
async with AsyncStealthySession(max_pages=2) as session:
    tasks = []
    urls = ['https://example.com/page1', 'https://example.com/page2']

    for url in urls:
        task = session.fetch(url)
        tasks.append(task)

    print(session.get_pool_stats())  # 可选 - 浏览器标签池的状态（忙/空闲/错误）
    results = await asyncio.gather(*tasks)
    print(session.get_pool_stats())

scrapling shell

scrapling extract get 'https://example.com' content.md
scrapling extract get 'https://example.com' content.txt --css-selector '#fromSkipToProducts' --impersonate 'chrome'  # 所有匹配 CSS 选择器'#fromSkipToProducts' 的元素
scrapling extract fetch 'https://example.com' content.md --css-selector '#fromSkipToProducts' --no-headless
scrapling extract stealthy-fetch 'https://nopecha.com/demo/cloudflare' captchas.html --css-selector '#padded_content a' --solve-cloudflare

pip install scrapling

docker pull pyd4vinci/scrapling

docker pull ghcr.io/d4vinci/scrapling:latest

  @misc{scrapling,
    author = {Karim Shoair},
    title = {Scrapling},
    year = {2024},
    url = {https://github.com/D4Vinci/Scrapling},
    note = {An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!}
  }