mldsveda · mldsveda · Apr 12, 2026 · Apr 12, 2026
diff --git a/src/pyscrappy/__init__.py b/src/pyscrappy/__init__.py
@@ -99,10 +99,10 @@
 
 def scrape(
     url: str,
-    selectors: dict[str, str] | None = None,
+    selectors: "dict[str, str] | None" = None,
     max_pages: int = 1,
     render_js: bool = False,
-    config: ScraperConfig | None = None,
+    config: "ScraperConfig | None" = None,
 ) -> ScrapeResult:
     """One-liner convenience function to scrape any URL.
 

diff --git a/src/pyscrappy/core/config.py b/src/pyscrappy/core/config.py
@@ -6,11 +6,16 @@
 from typing import Literal
 
 _DEFAULT_USER_AGENTS = [
-    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
-    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
-    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
-    "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:125.0) Gecko/20100101 Firefox/125.0",
-    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.4 Safari/605.1.15",
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+    " (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
+    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36"
+    " (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
+    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36"
+    " (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:125.0)"
+    " Gecko/20100101 Firefox/125.0",
+    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15"
+    " (KHTML, like Gecko) Version/17.4 Safari/605.1.15",
 ]
 
 

diff --git a/src/pyscrappy/core/http.py b/src/pyscrappy/core/http.py
@@ -88,7 +88,9 @@ def get(self, url: str, **kwargs: Any) -> httpx.Response:
                     time.sleep(delay)
                     continue
 
-        raise NetworkError(f"Failed to fetch {url} after {self.config.max_retries} attempts") from last_exc
+        raise NetworkError(
+            f"Failed to fetch {url} after {self.config.max_retries} attempts"
+        ) from last_exc
 
     def get_raw(self, url: str, **kwargs: Any) -> httpx.Response:
         """Like :meth:`get` but does NOT raise on non-2xx status codes.

diff --git a/src/pyscrappy/generic/extractors.py b/src/pyscrappy/generic/extractors.py
@@ -88,7 +88,6 @@ def extract(self, soup: BeautifulSoup) -> dict[str, Any]:
         }
 
     def _remove_noise(self, soup: BeautifulSoup) -> BeautifulSoup:
-        from copy import copy
 
         clean = BeautifulSoup(str(soup), "lxml")
         for tag in clean.find_all(self._NOISE_TAGS):

diff --git a/src/pyscrappy/generic/pagination.py b/src/pyscrappy/generic/pagination.py
@@ -7,7 +7,6 @@
 
 from bs4 import BeautifulSoup, Tag
 
-
 _NEXT_PATTERNS = re.compile(
     r"(^next$|^>$|^>>$|^›$|^»$|next\s*page|next\s*›|load\s*more)",
     re.IGNORECASE,

diff --git a/src/pyscrappy/scrapers/alibaba.py b/src/pyscrappy/scrapers/alibaba.py
@@ -8,7 +8,6 @@
 from bs4 import Tag
 
 from pyscrappy.core.base import BaseScraper
-from pyscrappy.core.config import ScraperConfig
 from pyscrappy.core.models import ScrapeError, ScrapeMetadata, ScrapeResult
 
 

diff --git a/src/pyscrappy/scrapers/flipkart.py b/src/pyscrappy/scrapers/flipkart.py
@@ -8,7 +8,6 @@
 from bs4 import Tag
 
 from pyscrappy.core.base import BaseScraper
-from pyscrappy.core.config import ScraperConfig
 from pyscrappy.core.models import ScrapeError, ScrapeMetadata, ScrapeResult
 
 

diff --git a/src/pyscrappy/scrapers/image_search.py b/src/pyscrappy/scrapers/image_search.py
@@ -4,15 +4,12 @@
 
 import logging
 import os
-import re
 from typing import Any
-from urllib.parse import quote_plus, urljoin
-
-from bs4 import Tag
+from urllib.parse import quote_plus
 
 from pyscrappy.core.base import BaseScraper
 from pyscrappy.core.config import ScraperConfig
-from pyscrappy.core.models import ScrapeError, ScrapeMetadata, ScrapeResult
+from pyscrappy.core.models import ScrapeMetadata, ScrapeResult
 
 logger = logging.getLogger("pyscrappy.image_search")
 

diff --git a/src/pyscrappy/scrapers/instagram.py b/src/pyscrappy/scrapers/instagram.py
@@ -15,7 +15,6 @@
 from typing import Any
 
 from pyscrappy.core.base import BaseScraper
-from pyscrappy.core.config import ScraperConfig
 from pyscrappy.core.models import ScrapeError, ScrapeMetadata, ScrapeResult
 
 
@@ -218,7 +217,10 @@ def _parse_hashtag_json(
             node = edge.get("node", {})
             caption_edges = node.get("edge_media_to_caption", {}).get("edges", [])
             posts.append({
-                "caption": caption_edges[0].get("node", {}).get("text", "") if caption_edges else "",
+                "caption": (
+                    caption_edges[0].get("node", {}).get("text", "")
+                    if caption_edges else ""
+                ),
                 "likes": node.get("edge_liked_by", {}).get("count"),
                 "comments": node.get("edge_media_to_comment", {}).get("count"),
                 "url": f"https://www.instagram.com/p/{node.get('shortcode', '')}/",

diff --git a/src/pyscrappy/scrapers/news.py b/src/pyscrappy/scrapers/news.py
@@ -156,7 +156,6 @@ def _parse_feed_xml(self, xml_text: str, max_articles: int) -> list[dict[str, An
             return articles
 
         # Namespace handling for Atom
-        ns = {"atom": "http://www.w3.org/2005/Atom"}
 
         # RSS 2.0: <channel><item>
         for item in root.iter("item"):

diff --git a/src/pyscrappy/scrapers/soundcloud.py b/src/pyscrappy/scrapers/soundcloud.py
@@ -8,7 +8,6 @@
 from urllib.parse import quote_plus
 
 from pyscrappy.core.base import BaseScraper
-from pyscrappy.core.config import ScraperConfig
 from pyscrappy.core.models import ScrapeError, ScrapeMetadata, ScrapeResult
 
 

diff --git a/src/pyscrappy/scrapers/spotify.py b/src/pyscrappy/scrapers/spotify.py
@@ -15,7 +15,6 @@
 from urllib.parse import quote_plus
 
 from pyscrappy.core.base import BaseScraper
-from pyscrappy.core.config import ScraperConfig
 from pyscrappy.core.models import ScrapeError, ScrapeMetadata, ScrapeResult
 
 

diff --git a/src/pyscrappy/scrapers/swiggy.py b/src/pyscrappy/scrapers/swiggy.py
@@ -8,7 +8,6 @@
 from bs4 import Tag
 
 from pyscrappy.core.base import BaseScraper
-from pyscrappy.core.config import ScraperConfig
 from pyscrappy.core.models import ScrapeError, ScrapeMetadata, ScrapeResult
 
 
@@ -68,7 +67,10 @@ def scrape(  # type: ignore[override]
         if not restaurants:
             errors.append(ScrapeError(
                 url=url,
-                message="No restaurants extracted. Swiggy requires JS rendering — use render_js=True.",
+                message=(
+                    "No restaurants extracted. Swiggy requires JS rendering"
+                    " — use render_js=True."
+                ),
             ))
 
         return ScrapeResult(

diff --git a/src/pyscrappy/scrapers/twitter.py b/src/pyscrappy/scrapers/twitter.py
@@ -14,7 +14,6 @@
 from typing import Any
 
 from pyscrappy.core.base import BaseScraper
-from pyscrappy.core.config import ScraperConfig
 from pyscrappy.core.models import ScrapeError, ScrapeMetadata, ScrapeResult
 
 
@@ -83,7 +82,11 @@ def _scrape_search(
         if not tweets:
             errors.append(ScrapeError(
                 url=url,
-                message="No tweets extracted. Twitter/X likely requires authentication. Use render_js=True with a logged-in browser session.",
+                message=(
+                    "No tweets extracted. Twitter/X likely requires"
+                    " authentication. Use render_js=True with a"
+                    " logged-in browser session."
+                ),
             ))
 
         return ScrapeResult(

diff --git a/src/pyscrappy/scrapers/wikipedia.py b/src/pyscrappy/scrapers/wikipedia.py
@@ -6,7 +6,7 @@
 from typing import Any
 from urllib.parse import quote
 
-from bs4 import BeautifulSoup, Tag
+from bs4 import Tag
 
 from pyscrappy.core.base import BaseScraper
 from pyscrappy.core.config import ScraperConfig

diff --git a/src/pyscrappy/scrapers/youtube.py b/src/pyscrappy/scrapers/youtube.py
@@ -8,8 +8,7 @@
 from urllib.parse import quote_plus
 
 from pyscrappy.core.base import BaseScraper
-from pyscrappy.core.config import ScraperConfig
-from pyscrappy.core.models import ScrapeError, ScrapeMetadata, ScrapeResult
+from pyscrappy.core.models import ScrapeMetadata, ScrapeResult
 
 
 class YouTubeScraper(BaseScraper):

diff --git a/src/pyscrappy/scrapers/zomato.py b/src/pyscrappy/scrapers/zomato.py
@@ -10,7 +10,6 @@
 from bs4 import Tag
 
 from pyscrappy.core.base import BaseScraper
-from pyscrappy.core.config import ScraperConfig
 from pyscrappy.core.models import ScrapeError, ScrapeMetadata, ScrapeResult
 
 
@@ -72,7 +71,10 @@ def scrape(  # type: ignore[override]
         if not restaurants:
             errors.append(ScrapeError(
                 url=url,
-                message="No restaurants extracted. Zomato requires JS rendering — use render_js=True.",
+                message=(
+                    "No restaurants extracted. Zomato requires JS rendering"
+                    " — use render_js=True."
+                ),
             ))
 
         return ScrapeResult(
@@ -198,7 +200,10 @@ def _find_restaurants(
                     "rating": info.get("rating", {}).get("aggregate_rating")
                     if isinstance(info.get("rating"), dict)
                     else info.get("rating"),
-                    "price": info.get("average_cost_for_two") or info.get("cfo", {}).get("text", ""),
+                    "price": (
+                        info.get("average_cost_for_two")
+                        or info.get("cfo", {}).get("text", "")
+                    ),
                     "address": info.get("location", {}).get("address", "")
                     if isinstance(info.get("location"), dict) else "",
                     "url": f"https://www.zomato.com/restaurant/{info.get('id', '')}",