Fix many ruff lints

comics/aggregator/command.py

@@ -90,7 +90,7 @@ def _get_valid_date(self, crawler, date):
         elif date < crawler.history_capable:
             logger.info(
                 "%s: Adjusting date from %s to %s because of "
-                + "limited history capability",
+                "limited history capability",
                 crawler.comic.slug,
                 date,
                 crawler.history_capable,
@@ -99,7 +99,7 @@ def _get_valid_date(self, crawler, date):
         elif date > crawler.current_date:
             logger.info(
                 "%s: Adjusting date from %s to %s because the given "
-                + "date is in the future in the comic's time zone",
+                "date is in the future in the comic's time zone",
                 crawler.comic.slug,
                 date,
                 crawler.current_date,
@@ -143,10 +143,10 @@ def _get_comic_by_slug(self, comic_slug):
 
         try:
             comic = Comic.objects.get(slug=comic_slug)
-        except Comic.DoesNotExist:
+        except Comic.DoesNotExist as exc:
             error_msg = "Comic %s not found" % comic_slug
             logger.error(error_msg)
-            raise ComicsError(error_msg)
+            raise ComicsError(error_msg) from exc
         return comic
 
     def set_date_interval(self, from_date, to_date):

comics/aggregator/crawler.py

@@ -5,7 +5,7 @@
 import time
 import xml.sax
 from dataclasses import dataclass, field
-from typing import Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING
 
 import httpx
 import pytz
@@ -19,29 +19,31 @@
 )
 from comics.aggregator.feedparser import FeedParser
 from comics.aggregator.lxmlparser import LxmlParser
-from comics.core.models import Comic
+
+if TYPE_CHECKING:
+    from comics.core.models import Comic
 
 # For testability
 now = timezone.now
 today = datetime.date.today
 
 
-RequestHeaders = Dict[str, str]
+RequestHeaders = dict[str, str]
 
 
 @dataclass
 class CrawlerRelease:
     comic: Comic
     pub_date: datetime.date
     has_rerun_releases: bool = False
-    _images: List[CrawlerImage] = field(default_factory=list)
+    _images: list[CrawlerImage] = field(default_factory=list)
 
     @property
     def identifier(self) -> str:
         return f"{self.comic.slug}/{self.pub_date}"
 
     @property
-    def images(self) -> List[CrawlerImage]:
+    def images(self) -> list[CrawlerImage]:
         return self._images
 
     def add_image(self, image: CrawlerImage) -> None:
@@ -52,8 +54,8 @@ def add_image(self, image: CrawlerImage) -> None:
 @dataclass
 class CrawlerImage:
     url: str
-    title: Optional[str] = None
-    text: Optional[str] = None
+    title: str | None = None
+    text: str | None = None
     request_headers: RequestHeaders = field(default_factory=dict)
 
     def __post_init__(self) -> None:
@@ -68,7 +70,7 @@ def validate(self, identifier: str) -> None:
             raise ImageURLNotFound(identifier)
 
 
-CrawlerResult = Union[None, CrawlerImage, List[CrawlerImage]]
+CrawlerResult = list[CrawlerImage] | CrawlerImage | None
 
 
 @dataclass
@@ -77,11 +79,11 @@ class CrawlerBase:
 
     # ### Crawler settings
     # Date of oldest release available for crawling
-    history_capable_date: Optional[str] = None
+    history_capable_date: str | None = None
     # Number of days a release is available for crawling
-    history_capable_days: Optional[int] = None
+    history_capable_days: int | None = None
     # On what weekdays the comic is published (example: "Mo,We,Fr")
-    schedule: Optional[str] = None
+    schedule: str | None = None
     # In approximately what time zone the comic is published
     # (example: "Europe/Oslo")
     time_zone: str = "UTC"
@@ -97,14 +99,14 @@ class CrawlerBase:
     headers: RequestHeaders = field(default_factory=dict)
 
     # Feed object which is reused when crawling multiple dates
-    feed: Optional[FeedParser] = None
+    feed: FeedParser | None = None
 
     # Page objects mapped against URL for use when crawling multiple dates
-    pages: Dict[str, LxmlParser] = field(default_factory=dict)
+    pages: dict[str, LxmlParser] = field(default_factory=dict)
 
     def get_crawler_release(
-        self, pub_date: Optional[datetime.date] = None
-    ) -> Optional[CrawlerRelease]:
+        self, pub_date: datetime.date | None = None
+    ) -> CrawlerRelease | None:
         """Get meta data for release at pub_date, or the latest release"""
 
         pub_date = self._get_date_to_crawl(pub_date)
@@ -115,9 +117,9 @@ def get_crawler_release(
         try:
             results = self.crawl(pub_date)
         except (httpx.HTTPError, httpx.InvalidURL, OSError) as error:
-            raise CrawlerHTTPError(release.identifier, error)
+            raise CrawlerHTTPError(release.identifier, error) from error
         except xml.sax.SAXException as error:
-            raise CrawlerHTTPError(release.identifier, str(error))
+            raise CrawlerHTTPError(release.identifier, str(error)) from error
 
         if not results:
             return None
@@ -132,7 +134,7 @@ def get_crawler_release(
 
         return release
 
-    def _get_date_to_crawl(self, pub_date: Optional[datetime.date]) -> datetime.date:
+    def _get_date_to_crawl(self, pub_date: datetime.date | None) -> datetime.date:
         identifier = f"{self.comic.slug}/{pub_date}"
 
         if pub_date is None:
@@ -141,9 +143,11 @@ def _get_date_to_crawl(self, pub_date: Optional[datetime.date]) -> datetime.date
         if pub_date < self.history_capable:
             raise NotHistoryCapable(identifier, self.history_capable)
 
-        if self.multiple_releases_per_day is False:
-            if self.comic.release_set.filter(pub_date=pub_date).count() > 0:
-                raise ReleaseAlreadyExists(identifier)
+        if (
+            self.multiple_releases_per_day is False
+            and self.comic.release_set.filter(pub_date=pub_date).count() > 0
+        ):
+            raise ReleaseAlreadyExists(identifier)
 
         return pub_date
 
@@ -192,8 +196,8 @@ def parse_page(self, page_url: str) -> LxmlParser:
             self.pages[page_url] = LxmlParser(page_url, headers=self.headers)
         return self.pages[page_url]
 
-    def string_to_date(self, string: str, format: str) -> datetime.date:
-        return datetime.datetime.strptime(string, format).date()
+    def string_to_date(self, string: str, fmt: str) -> datetime.date:
+        return datetime.datetime.strptime(string, fmt).date()
 
     def date_to_epoch(self, date: datetime.date) -> int:
         """The UNIX time of midnight at ``date`` in the comic's time zone"""
@@ -311,9 +315,9 @@ class NettserierCrawlerBase(CrawlerBase):
     # In order to get older releases we need to
     # loop through the pages and check the published date
     time_zone = "Europe/Oslo"
-    page_cache: Dict[str, Tuple[LxmlParser, datetime.date]] = {}
+    page_cache: dict[str, tuple[LxmlParser, datetime.date]] = {}
 
-    def get_page(self, url: str) -> Tuple[LxmlParser, datetime.date]:
+    def get_page(self, url: str) -> tuple[LxmlParser, datetime.date]:
         if url not in self.page_cache:
             page = self.parse_page(url)
             page_date = page.text('p[class="comic-pubtime"]')
@@ -339,10 +343,7 @@ def crawl_helper(self, short_name: str, pub_date: datetime.date) -> CrawlerResul
         title = page.text("div.comic-text h4")
         text = page.text("div.comic-text p", allow_multiple=True)
 
-        if text[0].find("Published") > -1:
-            text = None
-        else:
-            text = text[0]
+        text = None if text[0].find("Published") > -1 else text[0]
 
         # Get comic image
         url = page.src('img[src*="/_ns/files"]')

comics/aggregator/downloader.py

@@ -88,20 +88,21 @@ def _download_image(self, url, request_headers):
             temp_file = tempfile.NamedTemporaryFile(suffix="comics")
             temp_file.write(response.content)
             temp_file.seek(0)
-            return temp_file
         except (httpx.HTTPError, httpx.InvalidURL, OSError) as error:
-            raise DownloaderHTTPError(self.identifier, error)
+            raise DownloaderHTTPError(self.identifier, error) from error
+        else:
+            return temp_file
 
     def _get_sha256sum(self, file_handle):
         original_position = file_handle.tell()
-        hash = hashlib.sha256()
+        h = hashlib.sha256()
         while True:
             data = file_handle.read(8096)
             if not data:
                 break
-            hash.update(data)
+            h.update(data)
         file_handle.seek(original_position)
-        return hash.hexdigest()
+        return h.hexdigest()
 
     def _check_if_blacklisted(self, checksum):
         if checksum in settings.COMICS_IMAGE_BLACKLIST:
@@ -110,21 +111,23 @@ def _check_if_blacklisted(self, checksum):
     def _get_existing_image(self, comic, has_rerun_releases, checksum):
         try:
             image = Image.objects.get(comic=comic, checksum=checksum)
+        except Image.DoesNotExist:
+            return None
+        else:
             if image is not None and not has_rerun_releases:
                 raise ImageAlreadyExists(self.identifier)
             return image
-        except Image.DoesNotExist:
-            return None
 
     def _validate_image(self, image_file):
         try:
             image = PILImage.open(image_file)
             image.load()
-            return image
-        except IndexError:
-            raise ImageIsCorrupt(self.identifier)
+        except IndexError as error:
+            raise ImageIsCorrupt(self.identifier) from error
         except OSError as error:
-            raise ImageIsCorrupt(self.identifier, error)
+            raise ImageIsCorrupt(self.identifier, error) from error
+        else:
+            return image
 
     def _get_file_extension(self, image):
         if image.format not in IMAGE_FORMATS:

comics/api/tests/test_releases.py

@@ -44,7 +44,7 @@ def test_list_releases(self):
         self.assertEqual(
             image["text"],
             "People into masturbatory "
-            + "navel-gazing have a lot to learn about masturbation.",
+            "navel-gazing have a lot to learn about masturbation.",
         )
         self.assertEqual(image["height"], 235)
         self.assertEqual(image["width"], 740)

comics/browser/views.py

@@ -1,6 +1,5 @@
 import datetime
 import json
-from typing import Optional
 
 from django.conf import settings
 from django.contrib.auth.decorators import login_required
@@ -143,7 +142,7 @@ def get_view_type(self):
 class ReleaseDateMixin(ReleaseMixin):
     """Things common for all *date based* views"""
 
-    date_field: Optional[str] = "pub_date"
+    date_field: str | None = "pub_date"
     month_format = "%m"
 
 

comics/comics/20px.py

@@ -1,3 +1,5 @@
+# noqa: N999
+
 from comics.aggregator.crawler import CrawlerBase, CrawlerImage
 from comics.core.comic_data import ComicDataBase
 

comics/comics/8bittheater.py

@@ -1,3 +1,5 @@
+# noqa: N999
+
 from comics.aggregator.crawler import CrawlerBase
 from comics.core.comic_data import ComicDataBase
 

comics/comics/__init__.py

@@ -1,9 +1,8 @@
 import os
 from types import ModuleType
-from typing import List
 
 
-def get_comic_module_names() -> List[str]:
+def get_comic_module_names() -> list[str]:
     module_files = os.listdir(os.path.dirname(__file__))
     module_names = []
     for file in module_files:

comics/comics/adam4d.py

@@ -21,8 +21,7 @@ def crawl(self, pub_date):
             urls = entry.content0.src('img[src*="/wp-content/"]', allow_multiple=True)
 
             for url in urls:
-                url = url.replace("comics-rss", "comics")
-                results.append(CrawlerImage(url))
+                results.append(CrawlerImage(url.replace("comics-rss", "comics")))
 
             if not results:
                 continue

comics/comics/crookedgremlins.py

@@ -24,9 +24,6 @@ def crawl(self, pub_date):
 
         # Put together the text from multiple paragraphs
         text_paragraphs = page.text(".post-content p", allow_multiple=True)
-        if text_paragraphs is not None:
-            text = "\n\n".join(text_paragraphs)
-        else:
-            text = None
+        text = "\n\n".join(text_paragraphs) if text_paragraphs is not None else None
 
         return CrawlerImage(url, title, text)

comics/comics/ctrlaltdel.py

@@ -11,7 +11,6 @@ class ComicData(ComicDataBase):
 
 
 class Crawler(CrawlerBase):
-    # history_capable_date = "2002-10-23"
     history_capable_days = 20
     schedule = "Mo,We,Fr"
     time_zone = "US/Eastern"

comics/comics/jesusandmo.py

@@ -38,9 +38,6 @@ def crawl(self, pub_date):
             return
         url = url[0]
         text = release_page.root.xpath('//div[@class="entry"]/p')
-        if text:
-            text = text[0].text
-        else:
-            text = None
+        text = text[0].text if text else None
 
         return CrawlerImage(url, title, text)

comics/comics/nerfnow.py

@@ -29,9 +29,6 @@ def crawl(self, pub_date):
 
             # Put together text from multiple paragraphs
             text_paragraphs = entry.content0.text("p", allow_multiple=True)
-            if text_paragraphs is not None:
-                text = "\n\n".join(text_paragraphs)
-            else:
-                text = None
+            text = "\n\n".join(text_paragraphs) if text_paragraphs is not None else None
 
             return CrawlerImage(url, title, text)

comics/comics/savagechickens.py

@@ -18,8 +18,6 @@ class Crawler(CrawlerBase):
     def crawl(self, pub_date):
         feed = self.parse_feed("http://www.savagechickens.com/feed")
         for entry in feed.for_date(pub_date):
-            if "Cartoons" not in entry.tags:
-                print("skipping")
             url = entry.content0.src('img[src*="/wp-content/"]')
             title = entry.title
             return CrawlerImage(url, title)

comics/comics/vgcats.py

@@ -22,10 +22,7 @@ class Crawler(CrawlerBase):
 
     def crawl(self, pub_date):
         # FIXME: Seems like they are using gif images now and then
-        if pub_date < datetime.date(2003, 5, 1):
-            file_ext = "gif"
-        else:
-            file_ext = "jpg"
+        file_ext = "gif" if pub_date < datetime.date(2003, 5, 1) else "jpg"
         url = "http://www.vgcats.com/comics/images/{}.{}".format(
             pub_date.strftime("%y%m%d"),
             file_ext,