ScrapeGraphAI Python SDK

Install

pip install scrapegraph-py
# or
uv add scrapegraph-py

Quick Start

from scrapegraph_py import ScrapeGraphAI

# reads SGAI_API_KEY from env, or pass explicitly: ScrapeGraphAI(api_key="...")
sgai = ScrapeGraphAI()

result = sgai.scrape("https://example.com")

if result.status == "success":
    print(result.data["results"]["markdown"]["data"])
else:
    print(result.error)

@dataclass
class ApiResult(Generic[T]):
    status: Literal["success", "error"]
    data: T | None
    error: str | None
    elapsed_ms: int

🆚 Open Source vs Managed API

API

scrape

from scrapegraph_py import (
    ScrapeGraphAI, FetchConfig,
    MarkdownFormatConfig, ScreenshotFormatConfig, JsonFormatConfig
)

sgai = ScrapeGraphAI()

res = sgai.scrape(
    "https://example.com",
    formats=[
        MarkdownFormatConfig(mode="reader"),
        ScreenshotFormatConfig(full_page=True, width=1440, height=900),
        JsonFormatConfig(prompt="Extract product info"),
    ],
    content_type="text/html",           # optional, auto-detected
    fetch_config=FetchConfig(           # optional
        mode="js",                      # "auto" | "fast" | "js"
        stealth=True,
        timeout=30000,
        wait=2000,
        scrolls=3,
        headers={"Accept-Language": "en"},
        cookies={"session": "abc"},
        country="us",
    ),
)

extract

from scrapegraph_py import ScrapeGraphAI

sgai = ScrapeGraphAI()

res = sgai.extract(
    prompt="Extract product names and prices",
    url="https://example.com",
    schema={"type": "object", "properties": {...}},  # optional
    mode="reader",                                    # optional
    # Or pass html/markdown directly instead of url
)

search

from scrapegraph_py import ScrapeGraphAI

sgai = ScrapeGraphAI()

res = sgai.search(
    "best programming languages 2024",
    num_results=5,                      # 1-20, default 3
    format="markdown",                  # "markdown" | "html"
    prompt="Extract key points",        # optional, for AI extraction
    schema={...},                       # optional
    time_range="past_week",             # optional
    location_geo_code="us",             # optional
    allowed_types=["text/html", "application/pdf"],  # optional MIME allowlist
)

crawl

from scrapegraph_py import ScrapeGraphAI, ScrapeMarkdownFormatEntry

sgai = ScrapeGraphAI()

# Start a crawl
start = sgai.crawl.start(
    "https://example.com",
    formats=[ScrapeMarkdownFormatEntry()],
    max_pages=50,
    max_depth=2,
    max_links_per_page=10,
    include_patterns=["/blog/*"],
    exclude_patterns=["/admin/*"],
)

# Check status
status = sgai.crawl.get(start.data["id"])
pages = sgai.crawl.pages(start.data["id"], cursor=0, limit=50)

# Control
sgai.crawl.stop(crawl_id)
sgai.crawl.resume(crawl_id)
sgai.crawl.delete(crawl_id)

monitor

from scrapegraph_py import ScrapeGraphAI, MarkdownFormatConfig

sgai = ScrapeGraphAI()

# Create a monitor
mon = sgai.monitor.create(
    "https://example.com",
    "0 * * * *",                        # cron expression
    name="Price Monitor",
    formats=[MarkdownFormatConfig()],
    webhook_url="https://...",          # optional
)

# Manage monitors
sgai.monitor.list()
sgai.monitor.get(cron_id)
sgai.monitor.update(cron_id, interval="0 */6 * * *")
sgai.monitor.pause(cron_id)
sgai.monitor.resume(cron_id)
sgai.monitor.delete(cron_id)

history

from scrapegraph_py import ScrapeGraphAI

sgai = ScrapeGraphAI()

history = sgai.history.list(
    service="scrape",                   # optional filter
    page=1,
    limit=20,
)

entry = sgai.history.get("request-id")

credits / health

from scrapegraph_py import ScrapeGraphAI

sgai = ScrapeGraphAI()

credits = sgai.credits()
# { remaining: 1000, used: 500, plan: "pro", jobs: { crawl: {...}, monitor: {...} } }

health = sgai.health()
# { status: "ok", uptime: 12345 }

Async Client

import asyncio
from scrapegraph_py import AsyncScrapeGraphAI

async def main():
    async with AsyncScrapeGraphAI() as sgai:
        result = await sgai.scrape("https://example.com")
        if result.status == "success":
            print(result.data["results"]["markdown"]["data"])
        else:
            print(result.error)

asyncio.run(main())

Async Extract

async with AsyncScrapeGraphAI() as sgai:
    res = await sgai.extract(
        prompt="Extract product names and prices",
        url="https://example.com",
    )

Async Search

async with AsyncScrapeGraphAI() as sgai:
    res = await sgai.search("best programming languages 2024", num_results=5)

Async Crawl

async with AsyncScrapeGraphAI() as sgai:
    start = await sgai.crawl.start("https://example.com", max_pages=50)
    status = await sgai.crawl.get(start.data["id"])
    pages = await sgai.crawl.pages(start.data["id"], cursor=0, limit=50)

Async Monitor

async with AsyncScrapeGraphAI() as sgai:
    mon = await sgai.monitor.create(
        "https://example.com",
        "0 * * * *",
        name="Price Monitor",
    )

Examples

Sync Examples

Async Examples

Environment Variables

License