Scrapling

from scrapling.fetchers import Fetcher, FetcherSession

with FetcherSession(impersonate='chrome') as session:  # Use latest version of Chrome's TLS fingerprint
    page = session.get('https://quotes.toscrape.com/', stealthy_headers=True)
    quotes = page.css('.quote .text::text').getall()

# Or use one-off requests
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:  # Keep the browser open until you finish
    page = session.fetch('https://nopecha.com/demo/cloudflare', google_search=False)
    data = page.css('#padded_content a').getall()

# Or use one-off request style, it opens the browser for this request, then closes it after finishing
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:  # Keep the browser open until you finish
    page = session.fetch('https://quotes.toscrape.com/', load_dom=False)
    data = page.xpath('//span[@class="text"]/text()').getall()  # XPath selector if you prefer it

# Or use one-off request style, it opens the browser for this request, then closes it after finishing
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"Scraped {len(result.items)} quotes")
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():
            # Route protected pages through the stealth session
            if "protected" in link:
                yield Request(link, sid="stealth")
            else:
                yield Request(link, sid="fast", callback=self.parse)  # explicit callback

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

from scrapling.fetchers import Fetcher

# Rich element selection and navigation
page = Fetcher.get('https://quotes.toscrape.com/')

# Get quotes with multiple selection methods
quotes = page.css('.quote')  # CSS selector
quotes = page.xpath('//div[@class="quote"]')  # XPath
quotes = page.find_all('div', {'class': 'quote'})  # BeautifulSoup-style
# Same as
quotes = page.find_all('div', class_='quote')
quotes = page.find_all(['div'], class_='quote')
quotes = page.find_all(class_='quote')  # and so on...
# Find element by text content
quotes = page.find_by_text('quote', tag='div')

# Advanced navigation
quote_text = page.css('.quote')[0].css('.text::text').get()
quote_text = page.css('.quote').css('.text::text').getall()  # Chained selectors
first_quote = page.css('.quote')[0]
author = first_quote.next_sibling.css('.author::text')
parent_container = first_quote.parent

# Element relationships and similarity
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` is context-aware and can work in both sync/async patterns
    page1 = session.get('https://quotes.toscrape.com/')
    page2 = session.get('https://quotes.toscrape.com/', impersonate='firefox135')

# Async session usage
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())  # Optional - The status of the browser tabs pool (busy/free/error)
    results = await asyncio.gather(*tasks)
    print(session.get_pool_stats())