scrapfly-scraper（废品刮刀）

Scrapfly Scraper

Use the Scrapfly Scraper API to collect web page data with proxy rotation, anti-bot bypass, JavaScript rendering, and JavaScript scenarios for browser control.

When to use

• Scraping web pages (HTML, JSON, text, markdown)
• Bypassing anti-bot protections (Cloudflare, DataDome, PerimeterX, Kasada, and more)
• Collecting data through rotating proxies with geo-targeting
• Rendering JavaScript-heavy pages with headless browsers
• Control the browser using JavaScript scenario for common actions (waiting for selectors, clicking, filling elements, etc.)
• Session-reuse for session-presited scraping
• Capturing browser XHR call data

Setup

pip install scrapfly-sdk

The API key must be provided via environment variable SCRAPFLY_API_KEY or passed directly to the client.

API Reference

Endpoint: https://api.scrapfly.io/scrape The HTTP method is forwarded to the upstream URL. To retrieve data from a web page or an API, use the GET method, which is the default method. If the API resource like an API requries other methods, like POST. You can use it via the method parameter of the ScrapeConfig

ScrapflyClient

from scrapfly import ScrapflyClient, ScrapeConfig, ScrapeApiResponse
import os

client = ScrapflyClient(key=os.environ["SCRAPFLY_API_KEY"])

ScrapeConfig Parameters

ScrapeApiResponse

response = client.scrape(ScrapeConfig(url="https://httpbin.dev"))

response.content                      # Page content (HTML/JSON/text)
response.scrape_result                # Full result dict
response.status_code                  # Scrapfly API HTTP status code
response.scrape_result["status_code"] # Upsteam HTTP status code
response.headers                      # Response headers
response.context                      # Metadata about features used

Examples

Basic scrape

from scrapfly import ScrapflyClient, ScrapeConfig
import os

client = ScrapflyClient(key=os.environ["SCRAPFLY_API_KEY"])

result = client.scrape(ScrapeConfig(
    url="https://httpbin.dev",
))
print(result.content)

Scrape with anti-bot bypass and geo-targeting

result = client.scrape(ScrapeConfig(
    url="https://httpbin.dev",
    asp=True, # enable the asp to bypass antibots
    country="us", # match the proxy with the domain country
    proxy_pool="public_residential_pool", # use the residential proxy pool to match real ISP IPs
))

Scrape with JavaScript rendering

result = client.scrape(ScrapeConfig(
    url="https://web-scraping.dev/products",
    render_js=True, # enable JavaScript rendering using a cloud browser
    rendering_wait=5000, # rendering wait for wait for
    wait_for_selector="div.product", # wait a for a selector to be present on the page
))

Scrape as markdown

result = client.scrape(ScrapeConfig(
    url="https://web-scraping.dev/products",
    format="markdown", # other supported formats are: json, text, clean_html
))
print(result.content)

POST request with body

result = client.scrape(ScrapeConfig(
    url="https://httpbin.dev/anything",
    method="POST",
    headers={"Content-Type": "application/json"},
    body='{"query": "search term"}',
))
print(result.content)

JavaScript scenario (browser actions)

result = client.scrape(ScrapeConfig(
    url="https://web-scraping.dev/login",
    render_js=True,
    # browser control
    js_scenario=[
        {
            "fill":{
                "selector":"input[name='username']","clear":True,"value":"user123"
                }
            },{
            "fill":{
                "selector":"input[name='password']","clear":True,"value":"password"
                }
            },{
            "click":{
                "selector":"form > button[type='submit']"
                }
            },{
            "wait_for_navigation":{
                "timeout":5000
                }
            }
    ],
    # request headers
    headers={
        "cookie":"cookiesAccepted=true"
    }
))

# access the element under login
print(result.selector.css("div#secret-message::text").get())

Built-in Parsel selector

result = client.scrape(ScrapeConfig(
    url="https://web-scraping.dev/products",
    render_js=True
))

# access the built-in Parsel selector
selector = result.selector
for product in selector.css("div.product"):
    print("product name:", product.xpath(".//a/text()").get()) # using xpath
    print("product price:", product.css("div.price::text").get()) # using css

Concurrent scraping

import asyncio
from scrapfly import ScrapflyClient, ScrapeConfig

client = ScrapflyClient(key=os.environ["SCRAPFLY_API_KEY"])

urls = [
    "https://web-scraping.dev/products",
    "https://web-scraping.dev/products?page=2",
    "https://web-scraping.dev/products?page=3",
]

configs = [ScrapeConfig(url=url) for url in urls]

async def concurrent_scraping():
    results = []
    async for result in client.concurrent_scrape(configs):
        results.append(result)

    for result in results:
        print(result.content[:100])
        print("===========")

asyncio.run(concurrent_scraping())

Using sessions for stateful scraping

# First request: login
result = client.scrape(ScrapeConfig(
    url="https://web-scraping.dev/login",
    render_js=True,
    # browser control
    js_scenario=[
        {
            "fill":{
                "selector":"input[name='username']","clear":True,"value":"user123"
                }
            },{
            "fill":{
                "selector":"input[name='password']","clear":True,"value":"password"
                }
            },{
            "click":{
                "selector":"form > button[type='submit']"
                }
            },{
            "wait_for_navigation":{
                "timeout":5000
                }
            }
    ],
    # request headers
    headers={
        "cookie":"cookiesAccepted=true"
    },
    session="logged-in-session"
))

# Second request: access protected page with same session
result = client.scrape(ScrapeConfig(
    url="https://web-scraping.dev/login",
    session="logged-in-session"
))

# access the built-in selector
print(result.selector.css("div#secret-message::text").get())

Caching responses

result = client.scrape(ScrapeConfig(
    url="https://example.com",
    cache=True,
    cache_ttl=3600,  # Cache for 1 hour
))

Error Handling

from scrapfly import ScrapflyClient, ScrapeConfig
from scrapfly.errors import (
    ScrapflyError,
    UpstreamHttpClientError,
    UpstreamHttpServerError,
    ScrapflyProxyError,
    ScrapflyThrottleError,
)

try:
    result = client.scrape(ScrapeConfig(url="https://httpbin.dev", asp=True))
except ScrapflyThrottleError as e:
    print(f"Rate limited, retry after {e.retry_delay}s")
except UpstreamHttpClientError as e:
    print(f"Target returned 4xx: {e.message}")
except UpstreamHttpServerError as e:
    print(f"Target returned 5xx: {e.message}")
except ScrapflyProxyError as e:
    print(f"Proxy error: {e.message}")
except ScrapflyError as e:
    print(f"Scrapfly error: {e.message}")

Important Notes

• render_js=True is required for rendering_wait, wait_for_selector, js, js_scenario, and screenshots
• proxy_pool="public_residential_pool" is recommended when using asp=True
• Use format="markdown" for clean content accessible for LLMs
• Use session parameter to maintain state across multiple requests
• The concurrent_scrape method handles rate limiting automatically