chore: format code with ruff, add ruff config

- Run ruff format on src/
- Add ruff config to pyproject.toml (line-length=100, ignore E501)
- Fix import ordering

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: FrancescoSaverioZuppichini

pyproject.toml

@@ -45,3 +45,10 @@ dev = [
     "python-dotenv>=1.0.0",
     "ruff>=0.4.0",
 ]
+
+[tool.ruff]
+line-length = 100
+
+[tool.ruff.lint]
+select = ["E", "F", "I"]
+ignore = ["E501"]

src/scrapegraph_py/__init__.py

@@ -1,38 +1,37 @@
-from .client import ScrapeGraphAI
 from .async_client import AsyncScrapeGraphAI
-
+from .client import ScrapeGraphAI
 from .schemas import (
     ApiResult,
-    ScrapeRequest,
-    ScrapeResponse,
-    ExtractRequest,
-    ExtractResponse,
-    SearchRequest,
-    SearchResponse,
-    SearchResult,
+    BrandingFormatConfig,
+    CrawlPage,
     CrawlRequest,
     CrawlResponse,
-    CrawlPage,
-    MonitorCreateRequest,
-    MonitorUpdateRequest,
-    MonitorResponse,
-    MonitorResult,
-    MonitorDiffs,
-    HistoryFilter,
-    HistoryPage,
-    HistoryEntry,
     CreditsResponse,
-    HealthResponse,
-    TokenUsage,
+    ExtractRequest,
+    ExtractResponse,
     FetchConfig,
-    MarkdownFormatConfig,
+    HealthResponse,
+    HistoryEntry,
+    HistoryFilter,
+    HistoryPage,
     HtmlFormatConfig,
-    ScreenshotFormatConfig,
+    ImagesFormatConfig,
     JsonFormatConfig,
     LinksFormatConfig,
-    ImagesFormatConfig,
+    MarkdownFormatConfig,
+    MonitorCreateRequest,
+    MonitorDiffs,
+    MonitorResponse,
+    MonitorResult,
+    MonitorUpdateRequest,
+    ScrapeRequest,
+    ScrapeResponse,
+    ScreenshotFormatConfig,
+    SearchRequest,
+    SearchResponse,
+    SearchResult,
     SummaryFormatConfig,
-    BrandingFormatConfig,
+    TokenUsage,
 )
 
 __all__ = [

src/scrapegraph_py/async_client.py

@@ -1,42 +1,50 @@
 from __future__ import annotations
+
 import os
 import re
 import time
+
 import httpx
 from pydantic import BaseModel
 
 from .env import env
-
-_SERVER_TIMING_RE = re.compile(r"dur=(\d+(?:\.\d+)?)")
 from .schemas import (
     ApiResult,
-    ScrapeRequest,
-    ScrapeResponse,
-    ExtractRequest,
-    ExtractResponse,
-    SearchRequest,
-    SearchResponse,
     CrawlRequest,
     CrawlResponse,
-    MonitorCreateRequest,
-    MonitorUpdateRequest,
-    MonitorResponse,
-    HistoryFilter,
-    HistoryPage,
-    HistoryEntry,
     CreditsResponse,
+    ExtractRequest,
+    ExtractResponse,
     HealthResponse,
+    HistoryEntry,
+    HistoryFilter,
+    HistoryPage,
+    MonitorCreateRequest,
+    MonitorResponse,
+    MonitorUpdateRequest,
+    ScrapeRequest,
+    ScrapeResponse,
+    SearchRequest,
+    SearchResponse,
 )
 
+_SERVER_TIMING_RE = re.compile(r"dur=(\d+(?:\.\d+)?)")
+
 
 def _debug(label: str, data: object = None) -> None:
     if not env.debug:
         return
     from datetime import datetime
+
     ts = datetime.now().isoformat()
     if data is not None:
         import json
-        print(f"[{ts}] {label}", json.dumps(data, indent=2, default=str), file=__import__("sys").stderr)
+
+        print(
+            f"[{ts}] {label}",
+            json.dumps(data, indent=2, default=str),
+            file=__import__("sys").stderr,
+        )
     else:
         print(f"[{ts}] {label}", file=__import__("sys").stderr)
 
@@ -198,7 +206,9 @@ async def _request[T](
         except Exception as e:
             return ApiResult(status="error", data=None, error=str(e), elapsed_ms=0)
 
-    async def _get[T](self, path: str, response_type: type[T], params: dict | None = None) -> ApiResult[T]:
+    async def _get[T](
+        self, path: str, response_type: type[T], params: dict | None = None
+    ) -> ApiResult[T]:
         return await self._request("GET", path, response_type, params=params)
 
     async def _post[T](self, path: str, body: BaseModel, response_type: type[T]) -> ApiResult[T]:

src/scrapegraph_py/client.py

@@ -1,42 +1,50 @@
 from __future__ import annotations
+
 import os
 import re
 import time
+
 import httpx
 from pydantic import BaseModel
 
 from .env import env
-
-_SERVER_TIMING_RE = re.compile(r"dur=(\d+(?:\.\d+)?)")
 from .schemas import (
     ApiResult,
-    ScrapeRequest,
-    ScrapeResponse,
-    ExtractRequest,
-    ExtractResponse,
-    SearchRequest,
-    SearchResponse,
     CrawlRequest,
     CrawlResponse,
-    MonitorCreateRequest,
-    MonitorUpdateRequest,
-    MonitorResponse,
-    HistoryFilter,
-    HistoryPage,
-    HistoryEntry,
     CreditsResponse,
+    ExtractRequest,
+    ExtractResponse,
     HealthResponse,
+    HistoryEntry,
+    HistoryFilter,
+    HistoryPage,
+    MonitorCreateRequest,
+    MonitorResponse,
+    MonitorUpdateRequest,
+    ScrapeRequest,
+    ScrapeResponse,
+    SearchRequest,
+    SearchResponse,
 )
 
+_SERVER_TIMING_RE = re.compile(r"dur=(\d+(?:\.\d+)?)")
+
 
 def _debug(label: str, data: object = None) -> None:
     if not env.debug:
         return
     from datetime import datetime
+
     ts = datetime.now().isoformat()
     if data is not None:
         import json
-        print(f"[{ts}] {label}", json.dumps(data, indent=2, default=str), file=__import__("sys").stderr)
+
+        print(
+            f"[{ts}] {label}",
+            json.dumps(data, indent=2, default=str),
+            file=__import__("sys").stderr,
+        )
     else:
         print(f"[{ts}] {label}", file=__import__("sys").stderr)
 
@@ -198,7 +206,9 @@ def _request[T](
         except Exception as e:
             return ApiResult(status="error", data=None, error=str(e), elapsed_ms=0)
 
-    def _get[T](self, path: str, response_type: type[T], params: dict | None = None) -> ApiResult[T]:
+    def _get[T](
+        self, path: str, response_type: type[T], params: dict | None = None
+    ) -> ApiResult[T]:
         return self._request("GET", path, response_type, params=params)
 
     def _post[T](self, path: str, body: BaseModel, response_type: type[T]) -> ApiResult[T]:

src/scrapegraph_py/env.py

@@ -1,4 +1,5 @@
 from __future__ import annotations
+
 import os
 
 
@@ -21,6 +22,7 @@ def health_url(self) -> str:
         custom = os.environ.get("SGAI_API_URL")
         if custom:
             import re
+
             return re.sub(r"/v\d+$", "", custom)
         return "https://api.scrapegraphai.com"
 

src/scrapegraph_py/schemas.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
-from typing import Literal, Annotated, Generic, TypeVar
+
+from typing import Annotated, Generic, Literal, TypeVar
+
 from pydantic import BaseModel, ConfigDict, Field, HttpUrl, model_validator
 from pydantic.alias_generators import to_camel
 
@@ -9,11 +11,14 @@
 class CamelModel(BaseModel):
     model_config = ConfigDict(alias_generator=to_camel, populate_by_name=True)
 
+
 ApiService = Literal["scrape", "extract", "search", "monitor", "crawl"]
 ApiStatus = Literal["completed", "failed"]
 ApiHtmlMode = Literal["normal", "reader", "prune"]
 ApiFetchMode = Literal["auto", "fast", "js"]
-ApiScrapeFormat = Literal["markdown", "html", "links", "images", "summary", "json", "branding", "screenshot"]
+ApiScrapeFormat = Literal[
+    "markdown", "html", "links", "images", "summary", "json", "branding", "screenshot"
+]
 ApiTimeRange = Literal["past_hour", "past_24_hours", "past_week", "past_month", "past_year"]
 ApiCrawlStatus = Literal["running", "completed", "failed", "paused", "deleted"]
 ApiCrawlPageStatus = Literal["completed", "failed", "skipped"]