hyperbrowser 0.4.0__tar.gz → 0.6.0__tar.gz

{hyperbrowser-0.4.0 → hyperbrowser-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hyperbrowser
-Version: 0.4.0
+Version: 0.6.0
 Summary: Python SDK for hyperbrowser
 Home-page: https://github.com/hyperbrowserai/python-sdk
 License: MIT

{hyperbrowser-0.4.0 → hyperbrowser-0.6.0}/hyperbrowser/client/async_client.py

@@ -1,4 +1,16 @@
 from typing import Optional
+
+from hyperbrowser.models.crawl import (
+    CrawlJobResponse,
+    GetCrawlJobParams,
+    StartCrawlJobParams,
+    StartCrawlJobResponse,
+)
+from hyperbrowser.models.scrape import (
+    ScrapeJobResponse,
+    StartScrapeJobParams,
+    StartScrapeJobResponse,
+)
 from ..transport.async_transport import AsyncTransport
 from .base import HyperbrowserBase
 from ..models.session import (
@@ -45,6 +57,36 @@ class AsyncHyperbrowser(HyperbrowserBase):
         )
         return SessionListResponse(**response.data)
 
+    async def start_scrape_job(
+        self, params: StartScrapeJobParams
+    ) -> StartScrapeJobResponse:
+        response = await self.transport.post(
+            self._build_url("/scrape"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartScrapeJobResponse(**response.data)
+
+    async def get_scrape_job(self, job_id: str) -> ScrapeJobResponse:
+        response = await self.transport.get(self._build_url(f"/scrape/{job_id}"))
+        return ScrapeJobResponse(**response.data)
+
+    async def start_crawl_job(
+        self, params: StartCrawlJobParams
+    ) -> StartCrawlJobResponse:
+        response = await self.transport.post(
+            self._build_url("/crawl"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartCrawlJobResponse(**response.data)
+
+    async def get_crawl_job(
+        self, job_id: str, params: GetCrawlJobParams
+    ) -> CrawlJobResponse:
+        response = await self.transport.get(
+            self._build_url(f"/crawl/{job_id}"), params=params.__dict__
+        )
+        return CrawlJobResponse(**response.data)
+
     async def close(self) -> None:
         await self.transport.close()
 

{hyperbrowser-0.4.0 → hyperbrowser-0.6.0}/hyperbrowser/client/sync.py

@@ -1,4 +1,16 @@
 from typing import Optional
+
+from hyperbrowser.models.crawl import (
+    CrawlJobResponse,
+    GetCrawlJobParams,
+    StartCrawlJobParams,
+    StartCrawlJobResponse,
+)
+from hyperbrowser.models.scrape import (
+    ScrapeJobResponse,
+    StartScrapeJobParams,
+    StartScrapeJobResponse,
+)
 from ..transport.sync import SyncTransport
 from .base import HyperbrowserBase
 from ..models.session import (
@@ -43,5 +55,29 @@ class Hyperbrowser(HyperbrowserBase):
         )
         return SessionListResponse(**response.data)
 
+    def start_scrape_job(self, params: StartScrapeJobParams) -> StartScrapeJobResponse:
+        response = self.transport.post(
+            self._build_url("/scrape"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartScrapeJobResponse(**response.data)
+
+    def get_scrape_job(self, job_id: str) -> ScrapeJobResponse:
+        response = self.transport.get(self._build_url(f"/scrape/{job_id}"))
+        return ScrapeJobResponse(**response.data)
+
+    def start_crawl_job(self, params: StartCrawlJobParams) -> StartCrawlJobResponse:
+        response = self.transport.post(
+            self._build_url("/crawl"),
+            data=params.model_dump(exclude_none=True, by_alias=True),
+        )
+        return StartCrawlJobResponse(**response.data)
+
+    def get_crawl_job(self, job_id: str, params: GetCrawlJobParams) -> CrawlJobResponse:
+        response = self.transport.get(
+            self._build_url(f"/crawl/{job_id}"), params=params.__dict__
+        )
+        return CrawlJobResponse(**response.data)
+
     def close(self) -> None:
         self.transport.close()

hyperbrowser-0.6.0/hyperbrowser/models/crawl.py

@@ -0,0 +1,98 @@
+from typing import List, Literal, Optional
+from pydantic import BaseModel, ConfigDict, Field
+
+CrawlJobStatus = Literal["pending", "running", "completed", "failed"]
+
+
+class StartCrawlJobParams(BaseModel):
+    """
+    Parameters for creating a new crawl job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    url: str
+    max_pages: int = Field(default=10, ge=1, le=50, serialization_alias="maxPages")
+    follow_links: bool = Field(default=True, serialization_alias="followLinks")
+    exclude_patterns: List[str] = Field(
+        default=[], serialization_alias="excludePatterns"
+    )
+    include_patterns: List[str] = Field(
+        default=[], serialization_alias="includePatterns"
+    )
+    use_proxy: bool = Field(default=False, serialization_alias="useProxy")
+    solve_captchas: bool = Field(default=False, serialization_alias="solveCaptchas")
+
+
+class StartCrawlJobResponse(BaseModel):
+    """
+    Response from creating a crawl job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    job_id: str = Field(alias="jobId")
+
+
+class CrawledPageMetadata(BaseModel):
+    """
+    Metadata for the crawled page.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    title: str
+    description: str
+    robots: str
+    og_title: str = Field(alias="ogTitle")
+    og_description: str = Field(alias="ogDescription")
+    og_url: str = Field(alias="ogUrl")
+    og_image: str = Field(alias="ogImage")
+    og_locale_alternate: List[str] = Field(alias="ogLocaleAlternate")
+    og_site_name: str = Field(alias="ogSiteName")
+    source_url: str = Field(alias="sourceURL")
+
+
+class CrawledPage(BaseModel):
+    """
+    Data from a crawled page.
+    """
+
+    metadata: CrawledPageMetadata
+    markdown: str
+    url: str
+
+
+class GetCrawlJobParams(BaseModel):
+    """
+    Parameters for getting a crawl job.
+    """
+
+    page: Optional[int] = Field(default=None, serialization_alias="page")
+    batch_size: Optional[int] = Field(
+        default=10, ge=1, le=50, serialization_alias="batchSize"
+    )
+
+
+class CrawlJobResponse(BaseModel):
+    """
+    Response from getting a crawl job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    status: CrawlJobStatus
+    error: Optional[str] = None
+    data: List[CrawledPage] = Field(alias="data")
+    total_crawled_pages: int = Field(alias="totalCrawledPages")
+    total_page_batches: int = Field(alias="totalPageBatches")
+    current_page_batch: int = Field(alias="currentPageBatch")
+    batch_size: int = Field(alias="batchSize")

hyperbrowser-0.6.0/hyperbrowser/models/scrape.py

@@ -0,0 +1,74 @@
+from typing import List, Literal, Optional
+from pydantic import BaseModel, ConfigDict, Field
+
+ScrapeJobStatus = Literal["pending", "running", "completed", "failed"]
+
+
+class StartScrapeJobParams(BaseModel):
+    """
+    Parameters for creating a new scrape job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    url: str
+    use_proxy: bool = Field(default=False, serialization_alias="useProxy")
+    solve_captchas: bool = Field(default=False, serialization_alias="solveCaptchas")
+
+
+class StartScrapeJobResponse(BaseModel):
+    """
+    Response from creating a scrape job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    job_id: str = Field(alias="jobId")
+
+
+class ScrapeJobMetadata(BaseModel):
+    """
+    Metadata for the scraped site.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    title: str
+    description: str
+    robots: str
+    og_title: str = Field(alias="ogTitle")
+    og_description: str = Field(alias="ogDescription")
+    og_url: str = Field(alias="ogUrl")
+    og_image: str = Field(alias="ogImage")
+    og_locale_alternate: List[str] = Field(alias="ogLocaleAlternate")
+    og_site_name: str = Field(alias="ogSiteName")
+    source_url: str = Field(alias="sourceURL")
+
+
+class ScrapeJobData(BaseModel):
+    """
+    Data from a scraped site.
+    """
+
+    metadata: ScrapeJobMetadata
+    markdown: str
+
+
+class ScrapeJobResponse(BaseModel):
+    """
+    Response from getting a scrape job.
+    """
+
+    model_config = ConfigDict(
+        populate_by_alias=True,
+    )
+
+    status: ScrapeJobStatus
+    error: Optional[str] = None
+    data: Optional[ScrapeJobData] = None

{hyperbrowser-0.4.0 → hyperbrowser-0.6.0}/hyperbrowser/models/session.py

@@ -96,10 +96,8 @@ class ScreenConfig(BaseModel):
     Screen configuration parameters for browser session.
     """
 
-    max_width: int = Field(default=1280, le=4096, serialization_alias="maxWidth")
-    max_height: int = Field(default=720, le=4096, serialization_alias="maxHeight")
-    min_width: int = Field(default=800, ge=360, serialization_alias="minWidth")
-    min_height: int = Field(default=480, ge=360, serialization_alias="minHeight")
+    width: int = Field(default=1280, le=3840, ge=640, serialization_alias="width")
+    height: int = Field(default=720, le=2160, ge=360, serialization_alias="height")
 
 
 class CreateSessionParams(BaseModel):
@@ -111,6 +109,8 @@ class CreateSessionParams(BaseModel):
         populate_by_alias=True,
     )
 
+    use_stealth: bool = Field(default=False, serialization_alias="useStealth")
+    use_proxy: bool = Field(default=False, serialization_alias="useProxy")
     proxy_server: Optional[str] = Field(default=None, serialization_alias="proxyServer")
     proxy_server_password: Optional[str] = Field(
         default=None, serialization_alias="proxyServerPassword"
@@ -128,3 +128,7 @@ class CreateSessionParams(BaseModel):
     platform: Optional[List[Platform]] = Field(default=None)
     locales: List[ISO639_1] = Field(default=["en"])
     screen: Optional[ScreenConfig] = Field(default=None)
+    solve_captchas: bool = Field(default=False, serialization_alias="solveCaptchas")
+    adblock: bool = Field(default=False, serialization_alias="adblock")
+    trackers: bool = Field(default=False, serialization_alias="trackers")
+    annoyances: bool = Field(default=False, serialization_alias="annoyances")

{hyperbrowser-0.4.0 → hyperbrowser-0.6.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "hyperbrowser"
-version = "0.4.0"
+version = "0.6.0"
 description = "Python SDK for hyperbrowser"
 authors = ["Nikhil Shahi <nshahi1998@gmail.com>"]
 license = "MIT"