|
14 | 14 |
|
15 | 15 | @docs_group('Classes')
|
16 | 16 | class Router(Generic[TCrawlingContext]):
|
17 |
| - """Dispatches requests to registered handlers based on their labels.""" |
| 17 | + """Dispatches requests to registered handlers based on their labels. |
| 18 | +
|
| 19 | + Create a `Router` instance and decorate handlers with it, specifying the `label` parameter to correctly process |
| 20 | + requests requiring different logic. Pass it to the crawler as the `request_handler` parameter. |
| 21 | +
|
| 22 | + ```python |
| 23 | + from crawlee.crawlers import HttpCrawler, HttpCrawlingContext |
| 24 | + from crawlee.router import Router |
| 25 | +
|
| 26 | + router = Router[HttpCrawlingContext]() |
| 27 | +
|
| 28 | +
|
| 29 | + # Handler for requests without a matching label handler |
| 30 | + @router.default_handler |
| 31 | + async def basic_handler(context: HttpCrawlingContext) -> None: |
| 32 | + context.log.info(f'Request without label {context.request.url} ...') |
| 33 | +
|
| 34 | +
|
| 35 | + # Handler for category requests |
| 36 | + @router.handler(label='category') |
| 37 | + async def a_handler(context: HttpCrawlingContext) -> None: |
| 38 | + context.log.info(f'Category request {context.request.url} ...') |
| 39 | +
|
| 40 | +
|
| 41 | + # Handler for product requests |
| 42 | + @router.handler(label='product') |
| 43 | + async def b_handler(context: HttpCrawlingContext) -> None: |
| 44 | + context.log.info(f'Product {context.request.url} ...') |
| 45 | +
|
| 46 | +
|
| 47 | + crawler = HttpCrawler(request_handler=router) |
| 48 | +
|
| 49 | + await crawler.run() |
| 50 | + """ |
18 | 51 |
|
19 | 52 | def __init__(self) -> None:
|
20 | 53 | self._default_handler: RequestHandler[TCrawlingContext] | None = None
|
|
0 commit comments