feat: webcrawl

This commit is contained in:
Harry
2025-06-13 17:36:24 +08:00
parent b2b95412b9
commit 0908f310fc
7 changed files with 31 additions and 60 deletions

View File

@ -15,7 +15,7 @@ from core.plugin.entities.parameters import (
init_frontend_parameter,
)
from core.tools.entities.common_entities import I18nObject
from core.tools.entities.tool_entities import ToolLabelEnum, ToolInvokeMessage
from core.tools.entities.tool_entities import ToolLabelEnum
class DatasourceProviderType(enum.StrEnum):
@ -290,40 +290,13 @@ class WebSiteInfo(BaseModel):
"""
Website info
"""
job_id: str = Field(..., description="The job id")
status: str = Field(..., description="The status of the job")
status: Optional[str] = Field(..., description="crawl job status")
web_info_list: Optional[list[WebSiteInfoDetail]] = []
total: Optional[int] = Field(default=0, description="The total number of websites")
completed: Optional[int] = Field(default=0, description="The number of completed websites")
class GetWebsiteCrawlResponse(BaseModel):
class WebsiteCrawlMessage(BaseModel):
"""
Get website crawl response
"""
result: WebSiteInfo = WebSiteInfo(job_id="", status="", web_info_list=[])
class DatasourceInvokeMessage(ToolInvokeMessage):
"""
Datasource Invoke Message.
"""
class WebsiteCrawlMessage(BaseModel):
"""
Website crawl message
"""
job_id: str = Field(..., description="The job id")
status: str = Field(..., description="The status of the job")
web_info_list: Optional[list[WebSiteInfoDetail]] = []
class OnlineDocumentMessage(BaseModel):
"""
Online document message
"""
workspace_id: str = Field(..., description="The workspace id")
workspace_name: str = Field(..., description="The workspace name")
workspace_icon: str = Field(..., description="The workspace icon")
total: int = Field(..., description="The total number of documents")
pages: list[OnlineDocumentPage] = Field(..., description="The pages of the online document")
result: WebSiteInfo = WebSiteInfo(status="", web_info_list=[], total=0, completed=0)

View File

@ -1,4 +1,4 @@
from collections.abc import Mapping
from collections.abc import Generator, Mapping
from typing import Any
from core.datasource.__base.datasource_plugin import DatasourcePlugin
@ -6,7 +6,7 @@ from core.datasource.__base.datasource_runtime import DatasourceRuntime
from core.datasource.entities.datasource_entities import (
DatasourceEntity,
DatasourceProviderType,
GetWebsiteCrawlResponse,
WebsiteCrawlMessage,
)
from core.plugin.impl.datasource import PluginDatasourceManager
@ -31,12 +31,12 @@ class WebsiteCrawlDatasourcePlugin(DatasourcePlugin):
self.icon = icon
self.plugin_unique_identifier = plugin_unique_identifier
def _get_website_crawl(
def get_website_crawl(
self,
user_id: str,
datasource_parameters: Mapping[str, Any],
provider_type: str,
) -> GetWebsiteCrawlResponse:
) -> Generator[WebsiteCrawlMessage, None, None]:
manager = PluginDatasourceManager()
return manager.get_website_crawl(

View File

@ -1,4 +1,3 @@
from core.datasource.__base import datasource_provider
from core.datasource.__base.datasource_provider import DatasourcePluginProviderController
from core.datasource.__base.datasource_runtime import DatasourceRuntime
from core.datasource.entities.datasource_entities import DatasourceProviderEntityWithPlugin, DatasourceProviderType

View File

@ -1,12 +1,12 @@
from collections.abc import Mapping
from typing import Any, Generator
from collections.abc import Generator, Mapping
from typing import Any
from core.datasource.entities.datasource_entities import (
DatasourceInvokeMessage,
GetOnlineDocumentPageContentRequest,
GetOnlineDocumentPageContentResponse,
GetOnlineDocumentPagesResponse,
GetWebsiteCrawlResponse,
WebsiteCrawlMessage,
)
from core.plugin.entities.plugin import GenericProviderID, ToolProviderID
from core.plugin.entities.plugin_daemon import (
@ -94,17 +94,17 @@ class PluginDatasourceManager(BasePluginClient):
credentials: dict[str, Any],
datasource_parameters: Mapping[str, Any],
provider_type: str,
) -> Generator[DatasourceInvokeMessage, None, None]:
) -> Generator[WebsiteCrawlMessage, None, None]:
"""
Invoke the datasource with the given tenant, user, plugin, provider, name, credentials and parameters.
"""
datasource_provider_id = GenericProviderID(datasource_provider)
response = self._request_with_plugin_daemon_response_stream(
return self._request_with_plugin_daemon_response_stream(
"POST",
f"plugin/{tenant_id}/dispatch/datasource/get_website_crawl",
DatasourceInvokeMessage,
WebsiteCrawlMessage,
data={
"user_id": user_id,
"data": {
@ -119,7 +119,6 @@ class PluginDatasourceManager(BasePluginClient):
"Content-Type": "application/json",
},
)
yield from response
def get_online_document_pages(
self,

View File

@ -1,7 +1,7 @@
import datetime
import logging
from collections.abc import Mapping
import time
from collections.abc import Mapping
from typing import Any, cast
from sqlalchemy import func