hyperbrowser 0.18.0__tar.gz → 0.20.0__tar.gz

{hyperbrowser-0.18.0 → hyperbrowser-0.20.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: hyperbrowser
-Version: 0.18.0
+Version: 0.20.0
 Summary: Python SDK for hyperbrowser
 License: MIT
 Author: Nikhil Shahi

{hyperbrowser-0.18.0 → hyperbrowser-0.20.0}/hyperbrowser/client/async_client.py

@@ -1,5 +1,6 @@
 from typing import Optional
 
+from .managers.async_manager.extract import ExtractManager
 from .managers.async_manager.profile import ProfileManager
 from .managers.async_manager.session import SessionManager
 from .managers.async_manager.scrape import ScrapeManager
@@ -25,6 +26,7 @@ class AsyncHyperbrowser(HyperbrowserBase):
         self.sessions = SessionManager(self)
         self.scrape = ScrapeManager(self)
         self.crawl = CrawlManager(self)
+        self.extract = ExtractManager(self)
         self.profiles = ProfileManager(self)
         self.extensions = ExtensionManager(self)
 

hyperbrowser-0.20.0/hyperbrowser/client/managers/async_manager/extract.py

@@ -0,0 +1,41 @@
+import asyncio
+from hyperbrowser.exceptions import HyperbrowserError
+from hyperbrowser.models.extract import (
+    ExtractJobResponse,
+    StartExtractJobParams,
+    StartExtractJobResponse,
+)
+
+
+class ExtractManager:
+    def __init__(self, client):
+        self._client = client
+
+    async def start(self, params: StartExtractJobParams) -> StartExtractJobResponse:
+        if not params.schema_ and not params.prompt:
+            raise HyperbrowserError("Either schema or prompt must be provided")
+        if params.schema_:
+            if hasattr(params.schema_, "model_json_schema"):
+                params.schema_ = params.schema_.model_json_schema()
+
+        response = await self._client.transport.post(
+            self._client._build_url("/extract"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartExtractJobResponse(**response.data)
+
+    async def get(self, job_id: str) -> ExtractJobResponse:
+        response = await self._client.transport.get(
+            self._client._build_url(f"/extract/{job_id}")
+        )
+        return ExtractJobResponse(**response.data)
+
+    async def start_and_wait(self, params: StartExtractJobParams) -> ExtractJobResponse:
+        job_start_resp = await self.start(params)
+        if not job_start_resp.job_id:
+            raise HyperbrowserError("Failed to start extract job")
+        while True:
+            job_response = await self.get(job_start_resp.job_id)
+            if job_response.status == "completed" or job_response.status == "failed":
+                return job_response
+            await asyncio.sleep(2)

hyperbrowser-0.20.0/hyperbrowser/client/managers/sync_manager/extract.py

@@ -0,0 +1,41 @@
+import time
+from hyperbrowser.exceptions import HyperbrowserError
+from hyperbrowser.models.extract import (
+    ExtractJobResponse,
+    StartExtractJobParams,
+    StartExtractJobResponse,
+)
+
+
+class ExtractManager:
+    def __init__(self, client):
+        self._client = client
+
+    def start(self, params: StartExtractJobParams) -> StartExtractJobResponse:
+        if not params.schema_ and not params.prompt:
+            raise HyperbrowserError("Either schema or prompt must be provided")
+        if params.schema_:
+            if hasattr(params.schema_, "model_json_schema"):
+                params.schema_ = params.schema_.model_json_schema()
+
+        response = self._client.transport.post(
+            self._client._build_url("/extract"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartExtractJobResponse(**response.data)
+
+    def get(self, job_id: str) -> ExtractJobResponse:
+        response = self._client.transport.get(
+            self._client._build_url(f"/extract/{job_id}")
+        )
+        return ExtractJobResponse(**response.data)
+
+    def start_and_wait(self, params: StartExtractJobParams) -> ExtractJobResponse:
+        job_start_resp = self.start(params)
+        if not job_start_resp.job_id:
+            raise HyperbrowserError("Failed to start extract job")
+        while True:
+            job_response = self.get(job_start_resp.job_id)
+            if job_response.status == "completed" or job_response.status == "failed":
+                return job_response
+            time.sleep(2)

{hyperbrowser-0.18.0 → hyperbrowser-0.20.0}/hyperbrowser/client/sync.py

@@ -1,4 +1,6 @@
 from typing import Optional
+
+from .managers.sync_manager.extract import ExtractManager
 from .managers.sync_manager.profile import ProfileManager
 from .managers.sync_manager.session import SessionManager
 from .managers.sync_manager.scrape import ScrapeManager
@@ -24,6 +26,7 @@ class Hyperbrowser(HyperbrowserBase):
         self.sessions = SessionManager(self)
         self.scrape = ScrapeManager(self)
         self.crawl = CrawlManager(self)
+        self.extract = ExtractManager(self)
         self.profiles = ProfileManager(self)
         self.extensions = ExtensionManager(self)
 

hyperbrowser-0.20.0/hyperbrowser/models/extract.py

@@ -0,0 +1,53 @@
+from typing import Any, List, Literal, Optional
+from pydantic import BaseModel, ConfigDict, Field
+import pydantic
+
+from hyperbrowser.models.session import CreateSessionParams
+
+ExtractJobStatus = Literal["pending", "running", "completed", "failed"]
+
+
+class StartExtractJobParams(BaseModel):
+    """
+    Parameters for creating a new extract job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    urls: List[str]
+    prompt: Optional[str] = None
+    schema_: Optional[Any] = pydantic.Field(
+        None, alias="schema", serialization_alias="schema"
+    )
+    session_options: Optional[CreateSessionParams] = Field(
+        default=None, serialization_alias="sessionOptions"
+    )
+
+
+class StartExtractJobResponse(BaseModel):
+    """
+    Response from creating a extract job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    job_id: str = Field(alias="jobId")
+
+
+class ExtractJobResponse(BaseModel):
+    """
+    Response from a extract job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    job_id: str = Field(alias="jobId")
+    status: ExtractJobStatus
+    error: Optional[str] = None
+    data: Optional[Any] = None

{hyperbrowser-0.18.0 → hyperbrowser-0.20.0}/hyperbrowser/models/session.py

@@ -152,6 +152,7 @@ class CreateSessionParams(BaseModel):
     extension_ids: Optional[List[str]] = Field(
         default=None, serialization_alias="extensionIds"
     )
+    static_ip_id: Optional[str] = Field(default=None, serialization_alias="staticIpId")
 
 
 class SessionRecording(BaseModel):

{hyperbrowser-0.18.0 → hyperbrowser-0.20.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "hyperbrowser"
-version = "0.18.0"
+version = "0.20.0"
 description = "Python SDK for hyperbrowser"
 authors = ["Nikhil Shahi <nshahi1998@gmail.com>"]
 license = "MIT"