import os
from bulkgrid import BulkgridClient
with BulkgridClient(
api_key=os.environ["BULKGRID_API_KEY"],
base_url=os.environ.get("BULKGRID_BASE_URL", "https://bulkgrid.com"),
) as client:
data = client.deep_crawl(
{
"url": "https://example.com/docs",
"config": {
"maxDepth": 3,
"maxPages": 100,
"includePaths": ["/docs", "/blog"],
"excludePaths": ["/legal"],
"includeExternal": False,
"includeDocumentLinks": True,
"restrictToStartPath": True,
},
"options": {
"formats": ["markdown", "cleanHtml", "links"],
"timeout": 30000,
"blockAds": True,
"useInteractions": True,
},
}
)
print(data)