hyperbrowser 0.23.0__tar.gz → 0.24.0__tar.gz

{hyperbrowser-0.23.0 → hyperbrowser-0.24.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: hyperbrowser
-Version: 0.23.0
+Version: 0.24.0
 Summary: Python SDK for hyperbrowser
 License: MIT
 Author: Nikhil Shahi

hyperbrowser-0.24.0/hyperbrowser/client/managers/async_manager/crawl.py

@@ -0,0 +1,101 @@
+import asyncio
+
+from hyperbrowser.models.consts import POLLING_ATTEMPTS
+from ....models.crawl import (
+    CrawlJobResponse,
+    GetCrawlJobParams,
+    StartCrawlJobParams,
+    StartCrawlJobResponse,
+)
+from ....exceptions import HyperbrowserError
+
+
+class CrawlManager:
+    def __init__(self, client):
+        self._client = client
+
+    async def start(self, params: StartCrawlJobParams) -> StartCrawlJobResponse:
+        response = await self._client.transport.post(
+            self._client._build_url("/crawl"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartCrawlJobResponse(**response.data)
+
+    async def get(
+        self, job_id: str, params: GetCrawlJobParams = GetCrawlJobParams()
+    ) -> CrawlJobResponse:
+        response = await self._client.transport.get(
+            self._client._build_url(f"/crawl/{job_id}"), params=params.__dict__
+        )
+        return CrawlJobResponse(**response.data)
+
+    async def start_and_wait(
+        self, params: StartCrawlJobParams, return_all_pages: bool = True
+    ) -> CrawlJobResponse:
+        job_start_resp = await self.start(params)
+        job_id = job_start_resp.job_id
+        if not job_id:
+            raise HyperbrowserError("Failed to start crawl job")
+
+        job_response: CrawlJobResponse
+        failures = 0
+        while True:
+            try:
+                job_response = await self.get(
+                    job_id,
+                    params=GetCrawlJobParams(batch_size=1),
+                )
+                if (
+                    job_response.status == "completed"
+                    or job_response.status == "failed"
+                ):
+                    break
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to poll crawl job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
+            await asyncio.sleep(2)
+
+        failures = 0
+        if not return_all_pages:
+            while True:
+                try:
+                    job_response = await self.get(job_id)
+                    return job_response
+                except Exception as e:
+                    failures += 1
+                    if failures >= POLLING_ATTEMPTS:
+                        raise HyperbrowserError(
+                            f"Failed to get crawl job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                        )
+                await asyncio.sleep(0.5)
+
+        failures = 0
+        job_response.current_page_batch = 0
+        job_response.data = []
+        while job_response.current_page_batch < job_response.total_page_batches:
+            try:
+                tmp_job_response = await self.get(
+                    job_start_resp.job_id,
+                    GetCrawlJobParams(
+                        page=job_response.current_page_batch + 1, batch_size=100
+                    ),
+                )
+                if tmp_job_response.data:
+                    job_response.data.extend(tmp_job_response.data)
+                job_response.current_page_batch = tmp_job_response.current_page_batch
+                job_response.total_crawled_pages = tmp_job_response.total_crawled_pages
+                job_response.total_page_batches = tmp_job_response.total_page_batches
+                job_response.batch_size = tmp_job_response.batch_size
+                failures = 0
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to get crawl batch page {job_response.current_page_batch} for job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
+            await asyncio.sleep(0.5)
+
+        return job_response

{hyperbrowser-0.23.0 → hyperbrowser-0.24.0}/hyperbrowser/client/managers/async_manager/extract.py

@@ -1,5 +1,6 @@
 import asyncio
 from hyperbrowser.exceptions import HyperbrowserError
+from hyperbrowser.models.consts import POLLING_ATTEMPTS
 from hyperbrowser.models.extract import (
     ExtractJobResponse,
     StartExtractJobParams,
@@ -32,10 +33,24 @@ class ExtractManager:
 
     async def start_and_wait(self, params: StartExtractJobParams) -> ExtractJobResponse:
         job_start_resp = await self.start(params)
-        if not job_start_resp.job_id:
+        job_id = job_start_resp.job_id
+        if not job_id:
             raise HyperbrowserError("Failed to start extract job")
+
+        failures = 0
         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
+            try:
+                job_response = await self.get(job_id)
+                if (
+                    job_response.status == "completed"
+                    or job_response.status == "failed"
+                ):
+                    return job_response
+                failures = 0
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to poll extract job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
             await asyncio.sleep(2)

hyperbrowser-0.24.0/hyperbrowser/client/managers/async_manager/scrape.py

@@ -0,0 +1,150 @@
+import asyncio
+from typing import Optional
+
+from hyperbrowser.models.consts import POLLING_ATTEMPTS
+from ....models.scrape import (
+    BatchScrapeJobResponse,
+    GetBatchScrapeJobParams,
+    ScrapeJobResponse,
+    StartBatchScrapeJobParams,
+    StartBatchScrapeJobResponse,
+    StartScrapeJobParams,
+    StartScrapeJobResponse,
+)
+from ....exceptions import HyperbrowserError
+
+
+class BatchScrapeManager:
+    def __init__(self, client):
+        self._client = client
+
+    async def start(
+        self, params: StartBatchScrapeJobParams
+    ) -> StartBatchScrapeJobResponse:
+        response = await self._client.transport.post(
+            self._client._build_url("/scrape/batch"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartBatchScrapeJobResponse(**response.data)
+
+    async def get(
+        self, job_id: str, params: GetBatchScrapeJobParams = GetBatchScrapeJobParams()
+    ) -> BatchScrapeJobResponse:
+        response = await self._client.transport.get(
+            self._client._build_url(f"/scrape/batch/{job_id}"), params=params.__dict__
+        )
+        return BatchScrapeJobResponse(**response.data)
+
+    async def start_and_wait(
+        self, params: StartBatchScrapeJobParams, return_all_pages: bool = True
+    ) -> BatchScrapeJobResponse:
+        job_start_resp = await self.start(params)
+        job_id = job_start_resp.job_id
+        if not job_id:
+            raise HyperbrowserError("Failed to start batch scrape job")
+
+        job_response: BatchScrapeJobResponse
+        failures = 0
+        while True:
+            try:
+                job_response = await self.get(
+                    job_id, params=GetBatchScrapeJobParams(batch_size=1)
+                )
+                if (
+                    job_response.status == "completed"
+                    or job_response.status == "failed"
+                ):
+                    break
+                failures = 0
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to poll batch scrape job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
+            await asyncio.sleep(2)
+
+        failures = 0
+        if not return_all_pages:
+            while True:
+                try:
+                    job_response = await self.get(job_id)
+                    return job_response
+                except Exception as e:
+                    failures += 1
+                    if failures >= POLLING_ATTEMPTS:
+                        raise HyperbrowserError(
+                            f"Failed to get batch scrape job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                        )
+                await asyncio.sleep(0.5)
+
+        failures = 0
+        job_response.current_page_batch = 0
+        job_response.data = []
+        while job_response.current_page_batch < job_response.total_page_batches:
+            try:
+                tmp_job_response = await self.get(
+                    job_id,
+                    params=GetBatchScrapeJobParams(
+                        page=job_response.current_page_batch + 1, batch_size=100
+                    ),
+                )
+                if tmp_job_response.data:
+                    job_response.data.extend(tmp_job_response.data)
+                job_response.current_page_batch = tmp_job_response.current_page_batch
+                job_response.total_scraped_pages = tmp_job_response.total_scraped_pages
+                job_response.total_page_batches = tmp_job_response.total_page_batches
+                job_response.batch_size = tmp_job_response.batch_size
+                failures = 0
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to get batch page {job_response.current_page_batch} for job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
+            await asyncio.sleep(0.5)
+
+        return job_response
+
+
+class ScrapeManager:
+    def __init__(self, client):
+        self._client = client
+        self.batch = BatchScrapeManager(client)
+
+    async def start(self, params: StartScrapeJobParams) -> StartScrapeJobResponse:
+        response = await self._client.transport.post(
+            self._client._build_url("/scrape"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartScrapeJobResponse(**response.data)
+
+    async def get(self, job_id: str) -> ScrapeJobResponse:
+        response = await self._client.transport.get(
+            self._client._build_url(f"/scrape/{job_id}")
+        )
+        return ScrapeJobResponse(**response.data)
+
+    async def start_and_wait(self, params: StartScrapeJobParams) -> ScrapeJobResponse:
+        job_start_resp = await self.start(params)
+        job_id = job_start_resp.job_id
+        if not job_id:
+            raise HyperbrowserError("Failed to start scrape job")
+
+        failures = 0
+        while True:
+            try:
+                job_response = await self.get(job_id)
+                if (
+                    job_response.status == "completed"
+                    or job_response.status == "failed"
+                ):
+                    return job_response
+                failures = 0
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to poll scrape job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
+            await asyncio.sleep(2)

hyperbrowser-0.24.0/hyperbrowser/client/managers/sync_manager/crawl.py

@@ -0,0 +1,102 @@
+import time
+from typing import Optional
+
+from hyperbrowser.models.consts import POLLING_ATTEMPTS
+from ....models.crawl import (
+    CrawlJobResponse,
+    GetCrawlJobParams,
+    StartCrawlJobParams,
+    StartCrawlJobResponse,
+)
+from ....exceptions import HyperbrowserError
+
+
+class CrawlManager:
+    def __init__(self, client):
+        self._client = client
+
+    def start(self, params: StartCrawlJobParams) -> StartCrawlJobResponse:
+        response = self._client.transport.post(
+            self._client._build_url("/crawl"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartCrawlJobResponse(**response.data)
+
+    def get(
+        self, job_id: str, params: GetCrawlJobParams = GetCrawlJobParams()
+    ) -> CrawlJobResponse:
+        response = self._client.transport.get(
+            self._client._build_url(f"/crawl/{job_id}"), params=params.__dict__
+        )
+        return CrawlJobResponse(**response.data)
+
+    def start_and_wait(
+        self, params: StartCrawlJobParams, return_all_pages: bool = True
+    ) -> CrawlJobResponse:
+        job_start_resp = self.start(params)
+        job_id = job_start_resp.job_id
+        if not job_id:
+            raise HyperbrowserError("Failed to start crawl job")
+
+        job_response: CrawlJobResponse
+        failures = 0
+        while True:
+            try:
+                job_response = self.get(
+                    job_id,
+                    params=GetCrawlJobParams(batch_size=1),
+                )
+                if (
+                    job_response.status == "completed"
+                    or job_response.status == "failed"
+                ):
+                    break
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to poll crawl job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
+            time.sleep(2)
+
+        failures = 0
+        if not return_all_pages:
+            while True:
+                try:
+                    job_response = self.get(job_id)
+                    return job_response
+                except Exception as e:
+                    failures += 1
+                    if failures >= POLLING_ATTEMPTS:
+                        raise HyperbrowserError(
+                            f"Failed to get crawl job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                        )
+                time.sleep(0.5)
+
+        failures = 0
+        job_response.current_page_batch = 0
+        job_response.data = []
+        while job_response.current_page_batch < job_response.total_page_batches:
+            try:
+                tmp_job_response = self.get(
+                    job_id,
+                    GetCrawlJobParams(
+                        page=job_response.current_page_batch + 1, batch_size=100
+                    ),
+                )
+                if tmp_job_response.data:
+                    job_response.data.extend(tmp_job_response.data)
+                job_response.current_page_batch = tmp_job_response.current_page_batch
+                job_response.total_crawled_pages = tmp_job_response.total_crawled_pages
+                job_response.total_page_batches = tmp_job_response.total_page_batches
+                job_response.batch_size = tmp_job_response.batch_size
+                failures = 0
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to get crawl batch page {job_response.current_page_batch} for job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
+            time.sleep(0.5)
+
+        return job_response

{hyperbrowser-0.23.0 → hyperbrowser-0.24.0}/hyperbrowser/client/managers/sync_manager/extract.py

@@ -1,5 +1,6 @@
 import time
 from hyperbrowser.exceptions import HyperbrowserError
+from hyperbrowser.models.consts import POLLING_ATTEMPTS
 from hyperbrowser.models.extract import (
     ExtractJobResponse,
     StartExtractJobParams,
@@ -32,10 +33,23 @@ class ExtractManager:
 
     def start_and_wait(self, params: StartExtractJobParams) -> ExtractJobResponse:
         job_start_resp = self.start(params)
-        if not job_start_resp.job_id:
+        job_id = job_start_resp.job_id
+        if not job_id:
             raise HyperbrowserError("Failed to start extract job")
+
+        failures = 0
         while True:
-            job_response = self.get(job_start_resp.job_id)
-            if job_response.status == "completed" or job_response.status == "failed":
-                return job_response
+            try:
+                job_response = self.get(job_start_resp.job_id)
+                if (
+                    job_response.status == "completed"
+                    or job_response.status == "failed"
+                ):
+                    return job_response
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to poll extract job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
             time.sleep(2)

hyperbrowser-0.24.0/hyperbrowser/client/managers/sync_manager/scrape.py

@@ -0,0 +1,148 @@
+import time
+from typing import Optional
+
+from hyperbrowser.models.consts import POLLING_ATTEMPTS
+from ....models.scrape import (
+    BatchScrapeJobResponse,
+    GetBatchScrapeJobParams,
+    ScrapeJobResponse,
+    StartBatchScrapeJobParams,
+    StartBatchScrapeJobResponse,
+    StartScrapeJobParams,
+    StartScrapeJobResponse,
+)
+from ....exceptions import HyperbrowserError
+
+
+class BatchScrapeManager:
+    def __init__(self, client):
+        self._client = client
+
+    def start(self, params: StartBatchScrapeJobParams) -> StartBatchScrapeJobResponse:
+        response = self._client.transport.post(
+            self._client._build_url("/scrape/batch"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartBatchScrapeJobResponse(**response.data)
+
+    def get(
+        self, job_id: str, params: GetBatchScrapeJobParams = GetBatchScrapeJobParams()
+    ) -> BatchScrapeJobResponse:
+        response = self._client.transport.get(
+            self._client._build_url(f"/scrape/batch/{job_id}"), params=params.__dict__
+        )
+        return BatchScrapeJobResponse(**response.data)
+
+    def start_and_wait(
+        self, params: StartBatchScrapeJobParams, return_all_pages: bool = True
+    ) -> BatchScrapeJobResponse:
+        job_start_resp = self.start(params)
+        job_id = job_start_resp.job_id
+        if not job_id:
+            raise HyperbrowserError("Failed to start batch scrape job")
+
+        job_response: BatchScrapeJobResponse
+        failures = 0
+        while True:
+            try:
+                job_response = self.get(
+                    job_id, params=GetBatchScrapeJobParams(batch_size=1)
+                )
+                if (
+                    job_response.status == "completed"
+                    or job_response.status == "failed"
+                ):
+                    break
+                failures = 0
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to poll batch scrape job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
+            time.sleep(2)
+
+        failures = 0
+        if not return_all_pages:
+            while True:
+                try:
+                    job_response = self.get(job_id)
+                    return job_response
+                except Exception as e:
+                    failures += 1
+                    if failures >= POLLING_ATTEMPTS:
+                        raise HyperbrowserError(
+                            f"Failed to get batch scrape job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                        )
+                time.sleep(0.5)
+
+        failures = 0
+        job_response.current_page_batch = 0
+        job_response.data = []
+        while job_response.current_page_batch < job_response.total_page_batches:
+            try:
+                tmp_job_response = self.get(
+                    job_start_resp.job_id,
+                    GetBatchScrapeJobParams(
+                        page=job_response.current_page_batch + 1, batch_size=100
+                    ),
+                )
+                if tmp_job_response.data:
+                    job_response.data.extend(tmp_job_response.data)
+                job_response.current_page_batch = tmp_job_response.current_page_batch
+                job_response.total_scraped_pages = tmp_job_response.total_scraped_pages
+                job_response.total_page_batches = tmp_job_response.total_page_batches
+                job_response.batch_size = tmp_job_response.batch_size
+                failures = 0
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to get batch page {job_response.current_page_batch} for job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
+            time.sleep(0.5)
+
+        return job_response
+
+
+class ScrapeManager:
+    def __init__(self, client):
+        self._client = client
+        self.batch = BatchScrapeManager(client)
+
+    def start(self, params: StartScrapeJobParams) -> StartScrapeJobResponse:
+        response = self._client.transport.post(
+            self._client._build_url("/scrape"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartScrapeJobResponse(**response.data)
+
+    def get(self, job_id: str) -> ScrapeJobResponse:
+        response = self._client.transport.get(
+            self._client._build_url(f"/scrape/{job_id}")
+        )
+        return ScrapeJobResponse(**response.data)
+
+    def start_and_wait(self, params: StartScrapeJobParams) -> ScrapeJobResponse:
+        job_start_resp = self.start(params)
+        job_id = job_start_resp.job_id
+        if not job_id:
+            raise HyperbrowserError("Failed to start scrape job")
+
+        failures = 0
+        while True:
+            try:
+                job_response = self.get(job_id)
+                if (
+                    job_response.status == "completed"
+                    or job_response.status == "failed"
+                ):
+                    return job_response
+                failures = 0
+            except Exception as e:
+                failures += 1
+                if failures >= POLLING_ATTEMPTS:
+                    raise HyperbrowserError(
+                        f"Failed to poll scrape job {job_id} after {POLLING_ATTEMPTS} attempts: {e}"
+                    )
+            time.sleep(2)

{hyperbrowser-0.23.0 → hyperbrowser-0.24.0}/hyperbrowser/models/consts.py

@@ -2,6 +2,8 @@ from typing import Literal
 
 ScrapeFormat = Literal["markdown", "html", "links", "screenshot"]
 ScrapeWaitUntil = Literal["load", "domcontentloaded", "networkidle"]
+ScrapePageStatus = Literal["completed", "failed", "pending", "running"]
+POLLING_ATTEMPTS = 5
 
 Country = Literal[
     "AD",

{hyperbrowser-0.23.0 → hyperbrowser-0.24.0}/hyperbrowser/models/crawl.py

@@ -18,7 +18,7 @@ class StartCrawlJobParams(BaseModel):
     )
 
     url: str
-    max_pages: int = Field(default=10, ge=1, serialization_alias="maxPages")
+    max_pages: Optional[int] = Field(default=None, ge=1, serialization_alias="maxPages")
     follow_links: bool = Field(default=True, serialization_alias="followLinks")
     ignore_sitemap: bool = Field(default=False, serialization_alias="ignoreSitemap")
     exclude_patterns: List[str] = Field(
@@ -69,7 +69,7 @@ class GetCrawlJobParams(BaseModel):
 
     page: Optional[int] = Field(default=None, serialization_alias="page")
     batch_size: Optional[int] = Field(
-        default=20, ge=1, le=30, serialization_alias="batchSize"
+        default=None, ge=1, serialization_alias="batchSize"
     )
 
 

{hyperbrowser-0.23.0 → hyperbrowser-0.24.0}/hyperbrowser/models/extract.py

@@ -17,13 +17,17 @@ class StartExtractJobParams(BaseModel):
     )
 
     urls: List[str]
-    prompt: Optional[str] = None
+    system_prompt: Optional[str] = Field(
+        default=None, serialization_alias="systemPrompt"
+    )
+    prompt: Optional[str] = Field(default=None, serialization_alias="prompt")
     schema_: Optional[Any] = pydantic.Field(
         None, alias="schema", serialization_alias="schema"
     )
     session_options: Optional[CreateSessionParams] = Field(
         default=None, serialization_alias="sessionOptions"
     )
+    max_links: Optional[int] = Field(default=None, serialization_alias="maxLinks")
 
 
 class StartExtractJobResponse(BaseModel):

{hyperbrowser-0.23.0 → hyperbrowser-0.24.0}/hyperbrowser/models/scrape.py

@@ -1,7 +1,7 @@
 from typing import List, Literal, Optional, Union
 from pydantic import BaseModel, ConfigDict, Field
 
-from hyperbrowser.models.consts import ScrapeFormat, ScrapeWaitUntil
+from hyperbrowser.models.consts import ScrapeFormat, ScrapePageStatus, ScrapeWaitUntil
 from hyperbrowser.models.session import CreateSessionParams
 
 ScrapeJobStatus = Literal["pending", "running", "completed", "failed"]
@@ -84,3 +84,78 @@ class ScrapeJobResponse(BaseModel):
     status: ScrapeJobStatus
     error: Optional[str] = None
     data: Optional[ScrapeJobData] = None
+
+
+class StartBatchScrapeJobParams(BaseModel):
+    """
+    Parameters for creating a new batch scrape job.
+    """
+
+    urls: List[str]
+    session_options: Optional[CreateSessionParams] = Field(
+        default=None, serialization_alias="sessionOptions"
+    )
+    scrape_options: Optional[ScrapeOptions] = Field(
+        default=None, serialization_alias="scrapeOptions"
+    )
+
+
+class ScrapedPage(BaseModel):
+    """
+    A scraped page.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    url: str
+    status: ScrapePageStatus
+    error: Optional[str] = None
+    metadata: Optional[dict[str, Union[str, list[str]]]] = None
+    html: Optional[str] = None
+    markdown: Optional[str] = None
+    links: Optional[List[str]] = None
+    screenshot: Optional[str] = None
+
+
+class GetBatchScrapeJobParams(BaseModel):
+    """
+    Parameters for getting a batch scrape job.
+    """
+
+    page: Optional[int] = Field(default=None, serialization_alias="page")
+    batch_size: Optional[int] = Field(
+        default=None, ge=1, serialization_alias="batchSize"
+    )
+
+
+class StartBatchScrapeJobResponse(BaseModel):
+    """
+    Response from starting a batch scrape job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    job_id: str = Field(alias="jobId")
+
+
+class BatchScrapeJobResponse(BaseModel):
+    """
+    Response from getting a batch scrape job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    job_id: str = Field(alias="jobId")
+    status: ScrapeJobStatus
+    error: Optional[str] = None
+    data: Optional[List[ScrapedPage]] = Field(alias="data")
+    total_scraped_pages: int = Field(alias="totalScrapedPages")
+    total_page_batches: int = Field(alias="totalPageBatches")
+    current_page_batch: int = Field(alias="currentPageBatch")
+    batch_size: int = Field(alias="batchSize")

{hyperbrowser-0.23.0 → hyperbrowser-0.24.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "hyperbrowser"
-version = "0.23.0"
+version = "0.24.0"
 description = "Python SDK for hyperbrowser"
 authors = ["Nikhil Shahi <nshahi1998@gmail.com>"]
 license = "MIT"

hyperbrowser-0.23.0/hyperbrowser/client/managers/async_manager/crawl.py

@@ -1,60 +0,0 @@
-import asyncio
-from typing import Optional
-from ....models.crawl import (
-    CrawlJobResponse,
-    GetCrawlJobParams,
-    StartCrawlJobParams,
-    StartCrawlJobResponse,
-)
-from ....exceptions import HyperbrowserError
-
-
-class CrawlManager:
-    def __init__(self, client):
-        self._client = client
-
-    async def start(self, params: StartCrawlJobParams) -> StartCrawlJobResponse:
-        response = await self._client.transport.post(
-            self._client._build_url("/crawl"),
-            data=params.model_dump(exclude_none=True, by_alias=True),
-        )
-        return StartCrawlJobResponse(**response.data)
-
-    async def get(
-        self, job_id: str, params: GetCrawlJobParams = GetCrawlJobParams()
-    ) -> CrawlJobResponse:
-        response = await self._client.transport.get(
-            self._client._build_url(f"/crawl/{job_id}"), params=params.__dict__
-        )
-        return CrawlJobResponse(**response.data)
-
-    async def start_and_wait(
-        self, params: StartCrawlJobParams, return_all_pages: bool = True
-    ) -> CrawlJobResponse:
-        job_start_resp = await self.start(params)
-        if not job_start_resp.job_id:
-            raise HyperbrowserError("Failed to start crawl job")
-
-        job_response: CrawlJobResponse
-        while True:
-            job_response = await self.get(job_start_resp.job_id)
-            if job_response.status == "completed" or job_response.status == "failed":
-                break
-            await asyncio.sleep(2)
-
-        if not return_all_pages:
-            return job_response
-
-        while job_response.current_page_batch < job_response.total_page_batches:
-            tmp_job_response = await self.get(
-                job_start_resp.job_id,
-                GetCrawlJobParams(page=job_response.current_page_batch + 1),
-            )
-            if tmp_job_response.data:
-                job_response.data.extend(tmp_job_response.data)
-            job_response.current_page_batch = tmp_job_response.current_page_batch
-            job_response.total_crawled_pages = tmp_job_response.total_crawled_pages
-            job_response.total_page_batches = tmp_job_response.total_page_batches
-            job_response.batch_size = tmp_job_response.batch_size
-            await asyncio.sleep(0.5)
-        return job_response

hyperbrowser-0.23.0/hyperbrowser/client/managers/async_manager/scrape.py

@@ -1,36 +0,0 @@
-import asyncio
-from typing import Optional
-from ....models.scrape import (
-    ScrapeJobResponse,
-    StartScrapeJobParams,
-    StartScrapeJobResponse,
-)
-from ....exceptions import HyperbrowserError
-
-
-class ScrapeManager:
-    def __init__(self, client):
-        self._client = client
-
-    async def start(self, params: StartScrapeJobParams) -> StartScrapeJobResponse:
-        response = await self._client.transport.post(
-            self._client._build_url("/scrape"),
-            data=params.model_dump(exclude_none=True, by_alias=True),
-        )
-        return StartScrapeJobResponse(**response.data)
-
-    async def get(self, job_id: str) -> ScrapeJobResponse:
-        response = await self._client.transport.get(
-            self._client._build_url(f"/scrape/{job_id}")
-        )
-        return ScrapeJobResponse(**response.data)
-
-    async def start_and_wait(self, params: StartScrapeJobParams) -> ScrapeJobResponse:
-        job_start_resp = await self.start(params)
-        if not job_start_resp.job_id:
-            raise HyperbrowserError("Failed to start scrape 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-0.23.0/hyperbrowser/client/managers/sync_manager/crawl.py

@@ -1,60 +0,0 @@
-import time
-from typing import Optional
-from ....models.crawl import (
-    CrawlJobResponse,
-    GetCrawlJobParams,
-    StartCrawlJobParams,
-    StartCrawlJobResponse,
-)
-from ....exceptions import HyperbrowserError
-
-
-class CrawlManager:
-    def __init__(self, client):
-        self._client = client
-
-    def start(self, params: StartCrawlJobParams) -> StartCrawlJobResponse:
-        response = self._client.transport.post(
-            self._client._build_url("/crawl"),
-            data=params.model_dump(exclude_none=True, by_alias=True),
-        )
-        return StartCrawlJobResponse(**response.data)
-
-    def get(
-        self, job_id: str, params: GetCrawlJobParams = GetCrawlJobParams()
-    ) -> CrawlJobResponse:
-        response = self._client.transport.get(
-            self._client._build_url(f"/crawl/{job_id}"), params=params.__dict__
-        )
-        return CrawlJobResponse(**response.data)
-
-    def start_and_wait(
-        self, params: StartCrawlJobParams, return_all_pages: bool = True
-    ) -> CrawlJobResponse:
-        job_start_resp = self.start(params)
-        if not job_start_resp.job_id:
-            raise HyperbrowserError("Failed to start crawl job")
-
-        job_response: CrawlJobResponse
-        while True:
-            job_response = self.get(job_start_resp.job_id)
-            if job_response.status == "completed" or job_response.status == "failed":
-                break
-            time.sleep(2)
-
-        if not return_all_pages:
-            return job_response
-
-        while job_response.current_page_batch < job_response.total_page_batches:
-            tmp_job_response = self.get(
-                job_start_resp.job_id,
-                GetCrawlJobParams(page=job_response.current_page_batch + 1),
-            )
-            if tmp_job_response.data:
-                job_response.data.extend(tmp_job_response.data)
-            job_response.current_page_batch = tmp_job_response.current_page_batch
-            job_response.total_crawled_pages = tmp_job_response.total_crawled_pages
-            job_response.total_page_batches = tmp_job_response.total_page_batches
-            job_response.batch_size = tmp_job_response.batch_size
-            time.sleep(0.5)
-        return job_response

hyperbrowser-0.23.0/hyperbrowser/client/managers/sync_manager/scrape.py

@@ -1,36 +0,0 @@
-import time
-from typing import Optional
-from ....models.scrape import (
-    ScrapeJobResponse,
-    StartScrapeJobParams,
-    StartScrapeJobResponse,
-)
-from ....exceptions import HyperbrowserError
-
-
-class ScrapeManager:
-    def __init__(self, client):
-        self._client = client
-
-    def start(self, params: StartScrapeJobParams) -> StartScrapeJobResponse:
-        response = self._client.transport.post(
-            self._client._build_url("/scrape"),
-            data=params.model_dump(exclude_none=True, by_alias=True),
-        )
-        return StartScrapeJobResponse(**response.data)
-
-    def get(self, job_id: str) -> ScrapeJobResponse:
-        response = self._client.transport.get(
-            self._client._build_url(f"/scrape/{job_id}")
-        )
-        return ScrapeJobResponse(**response.data)
-
-    def start_and_wait(self, params: StartScrapeJobParams) -> ScrapeJobResponse:
-        job_start_resp = self.start(params)
-        if not job_start_resp.job_id:
-            raise HyperbrowserError("Failed to start scrape 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)