Improved URL Handling, Added View to Post convertion

py34/post.py

@@ -1,4 +1,5 @@
 from .scraper import scraper
+from .url import ImageURL
 from io import BytesIO
 from PIL import Image
 from PIL.ImageFile import ImageFile
@@ -30,8 +31,9 @@ class Post:
             return self._image_data
         for ext in ["jpeg", "png", "gif", "mp4", "webm", "jpg"]:
             try:
-                self._image_data = scraper.get(f"https://wimg.rule34.xxx//images/{self.image_dir}/{self.image_id}.{ext}", retry=False)
+                self._image_data = scraper.get(ImageURL(self.image_dir, self.image_id, ext), retry=False)
                 self._image_format = ext
+                break
             except Exception as ex:
                 exception = ex
         if self._image_data is None:

py34/url.py

@@ -6,7 +6,10 @@ class ImageURL:
     def __init__(self, image_dir: int, image_id: str, image_format: str):
         self.dir:    int = image_dir
         self.id:     str = image_id
-        self.format: str = image_format
+        self.format: str = image_format.lstrip(".")
+
+    def __str__(self) -> str:
+        return f"https://wimg.rule34.xxx//images/{self.dir}/{self.id}.{self.format}"
 
 
 class ThumbnailURL:
@@ -14,6 +17,9 @@ class ThumbnailURL:
         self.dir: int = image_dir
         self.id:  str = image_id
 
+    def __str__(self) -> str:
+        return f"https://wimg.rule34.xxx//thumbnails/{self.dir}/thumbnail_{self.id}.jpg"
+
 
 def parse_image_url(url: str) -> ImageURL:
     url = urlparse(url)

py34/view.py

@@ -1,3 +1,5 @@
+from .post import Post
+from .url import ImageURL, ThumbnailURL, parse_image_url
 from .scraper import scraper
 from io import BytesIO
 from PIL import Image
@@ -33,9 +35,12 @@ class ViewTags:
 class View:
     def __init__(self, id: int):
         self.id = id
-        self._image_data: bytes     | None = None
-        self._image:      ImageFile | None = None
-        self._image_url:  str       | None = None
+        self._image_data: bytes        | None = None
+        self._image:      ImageFile    | None = None
+        self._image_url:  ImageURL     | None = None
+        self._thumb_data: bytes        | None = None
+        self._thumb:      ImageFile    | None = None
+        self._thumb_url:  ThumbnailURL | None = None
         document = scraper.get_html(f"https://rule34.xxx/index.php?page=post&s=view&id={id}")
 
         tag_bar = document.find_all("ul", attrs={"id": "tag-sidebar"})[0]
@@ -66,7 +71,9 @@ class View:
                 label = ent.text.lower().strip()
                 match label:
                     case "original image":
-                        self._image_url = ent.find_all("a")[0]["href"]
+                        self._image_url = parse_image_url(ent.find_all("a")[0]["href"])
+
+        self._thumb_url = ThumbnailURL(self._image_url.dir, self._image_url.id)
 
 
     def get_image(self) -> ImageFile:
@@ -83,6 +90,27 @@ class View:
         return self._image_data
 
 
+    def get_thumbnail(self) -> ImageFile:
+        if self._thumb is not None:
+            return self._thumb
+        self._thumb = Image.open(BytesIO(self.get_thumbnail_data()))
+        return self._thumb
+
+
+    def get_thumbnail_data(self) -> bytes:
+        if self._thumb_data is not None:
+            return self._thumb_data
+        self._thumb_data = scraper.get(self._thumb_url)
+
+
+    def to_post(self) -> Post:
+        return Post(
+            self.id,
+            self._image_url.dir,
+            self._image_url.id,
+            self.tags.to_list(),
+        )
+
     def __str__(self):
         return f"<View {self.id}>"