hyperbrowser 0.5.0__tar.gz → 0.6.0__tar.gz

{hyperbrowser-0.5.0 → hyperbrowser-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hyperbrowser
-Version: 0.5.0
+Version: 0.6.0
 Summary: Python SDK for hyperbrowser
 Home-page: https://github.com/hyperbrowserai/python-sdk
 License: MIT

{hyperbrowser-0.5.0 → hyperbrowser-0.6.0}/hyperbrowser/client/async_client.py

@@ -1,5 +1,11 @@
 from typing import Optional
 
+from hyperbrowser.models.crawl import (
+    CrawlJobResponse,
+    GetCrawlJobParams,
+    StartCrawlJobParams,
+    StartCrawlJobResponse,
+)
 from hyperbrowser.models.scrape import (
     ScrapeJobResponse,
     StartScrapeJobParams,
@@ -61,9 +67,26 @@ class AsyncHyperbrowser(HyperbrowserBase):
         return StartScrapeJobResponse(**response.data)
 
     async def get_scrape_job(self, job_id: str) -> ScrapeJobResponse:
-        response = await self.transport.get(self._build_url(f"/api/scrape/{job_id}"))
+        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-0.5.0 → hyperbrowser-0.6.0}/hyperbrowser/client/sync.py

@@ -1,5 +1,11 @@
 from typing import Optional
 
+from hyperbrowser.models.crawl import (
+    CrawlJobResponse,
+    GetCrawlJobParams,
+    StartCrawlJobParams,
+    StartCrawlJobResponse,
+)
 from hyperbrowser.models.scrape import (
     ScrapeJobResponse,
     StartScrapeJobParams,
@@ -57,8 +63,21 @@ class Hyperbrowser(HyperbrowserBase):
         return StartScrapeJobResponse(**response.data)
 
     def get_scrape_job(self, job_id: str) -> ScrapeJobResponse:
-        response = self.transport.get(self._build_url(f"/api/scrape/{job_id}"))
+        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-0.5.0 → hyperbrowser-0.6.0}/hyperbrowser/models/scrape.py

@@ -1,4 +1,4 @@
-from typing import Literal, Optional
+from typing import List, Literal, Optional
 from pydantic import BaseModel, ConfigDict, Field
 
 ScrapeJobStatus = Literal["pending", "running", "completed", "failed"]
@@ -14,6 +14,8 @@ class StartScrapeJobParams(BaseModel):
     )
 
     url: str
+    use_proxy: bool = Field(default=False, serialization_alias="useProxy")
+    solve_captchas: bool = Field(default=False, serialization_alias="solveCaptchas")
 
 
 class StartScrapeJobResponse(BaseModel):
@@ -44,7 +46,7 @@ class ScrapeJobMetadata(BaseModel):
     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_locale_alternate: List[str] = Field(alias="ogLocaleAlternate")
     og_site_name: str = Field(alias="ogSiteName")
     source_url: str = Field(alias="sourceURL")
 

{hyperbrowser-0.5.0 → hyperbrowser-0.6.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "hyperbrowser"
-version = "0.5.0"
+version = "0.6.0"
 description = "Python SDK for hyperbrowser"
 authors = ["Nikhil Shahi <nshahi1998@gmail.com>"]
 license = "MIT"