urlicon 0.1.0__py3-none-any.whl → 0.2.1__py3-none-any.whl

urlicon/urlicon.py

@@ -5,14 +5,14 @@ import urllib
 import requests
 from bs4 import BeautifulSoup
 from dotenv import load_dotenv
+from unforgettable import unforgettable
 
 from urlicon import urls
-from urlicon.string_cache import string_cache
 
 load_dotenv()
 
-STRING_CACHE_ROOT_DIR = os.getenv("STRING_CACHE_ROOT_DIR", None)
-cache = string_cache(cache_folder=STRING_CACHE_ROOT_DIR)
+SIMPLE_CACHE_ROOT_DIR = os.getenv("SIMPLE_CACHE_ROOT_DIR", None)
+cache = unforgettable(cache_folder=SIMPLE_CACHE_ROOT_DIR)
 
 
 def get_url_icon(url):
@@ -152,6 +152,15 @@ def requests_get(url):
     if req.status_code != 200:
         return None
 
-    code = req.text
-    cache.set(text=code, cache_id=cache_prefix + url)
+    code = req.content
+    cache.set(content=code, cache_id=cache_prefix + url)
     return code
+
+
+def is_file_binary(file_path: str) -> bool:
+    try:
+        with open(file_path, "r") as fp:
+            fp.read(16)
+            return False
+    except UnicodeDecodeError:
+        return True

{urlicon-0.1.0.dist-info → urlicon-0.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: urlicon
-Version: 0.1.0
+Version: 0.2.1
 Summary: `URLicon` helps you to discover an possible icon from a URL.
 Author-email: Cesar Cardoso <hello@cesarcardoso.cc>
 License-Expression: MIT
@@ -9,8 +9,9 @@ Description-Content-Type: text/markdown
 Requires-Dist: bs4>=0.0.2
 Requires-Dist: dotenv>=0.9.9
 Requires-Dist: requests>=2.32.5
+Requires-Dist: unforgettable
 
-# URLicon - v0.1.0
+# URLicon - v0.2.1
 
 `URLicon` helps you to discover an possible icon from a URL.
 
@@ -42,19 +43,19 @@ print("icon:", icon_url)
 
 ### Caching
 
-`URLicon` use a simple "cache" method to avoid unecessary URL requests.
+`URLicon` use the [unforgettable "cache"](https://github.com/bouli/unforgettable) to avoid unecessary URL requests.
 It uses a [temp dir](https://docs.python.org/3/library/tempfile.html) for each
 execution. But you can define a your own directory and use the cache as much as
-you want setting `STRING_CACHE_ROOT_DIR` env var.
+you want setting `SIMPLE_CACHE_ROOT_DIR` env var.
 
 ```python
-STRING_CACHE_ROOT_DIR = os.getenv("STRING_CACHE_ROOT_DIR", None)
-cache = string_cache(cache_folder=STRING_CACHE_ROOT_DIR)
+SIMPLE_CACHE_ROOT_DIR = os.getenv("SIMPLE_CACHE_ROOT_DIR", None)
+cache = unforgettable(cache_folder=SIMPLE_CACHE_ROOT_DIR)
 ```
 
 And you can clean the cache with:
 ```python
-urlicon.string_cache.clean()
+urlicon.unforgettable.clean()
 ```
 
 ## See Also

urlicon-0.2.1.dist-info/RECORD

@@ -0,0 +1,6 @@
+urlicon/urlicon.py,sha256=unEZeMvzLNxU4b4PIeQsLhuZEE_GRKruJbblvHZrd08,4263
+urlicon/urls.py,sha256=ErdlgRva3bxs6HuBX2iHng21PqpWGIF1etZFToJq4jc,2235
+urlicon-0.2.1.dist-info/METADATA,sha256=2ubWrjiZun1aJmfwGVMm_JekwEOWhw3dEYxafCEPSec,1788
+urlicon-0.2.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+urlicon-0.2.1.dist-info/top_level.txt,sha256=Jts8QbeWp-6xANJ9KVj3CHk6L-8D950AQ_ZKXmF4YGI,8
+urlicon-0.2.1.dist-info/RECORD,,

urlicon/string_cache.py

@@ -1,116 +0,0 @@
-import os
-
-
-class string_cache:
-    cache_folder: str | None = None
-    cache_files_extension: str = "html"
-
-    def __init__(self, cache_folder: str | None = None):
-        if cache_folder is not None:
-            self.cache_folder = cache_folder
-        else:
-            self.cache_folder = self.get_cache_folder()
-        pass
-
-    def safe_cache_id(func):
-        def filter_cache_id(cache_id):
-            cache_id = cache_id.replace('"', "").replace("\\", "")
-            cache_id = f'"{cache_id}"'
-            return cache_id
-
-        def _filter_cache_id_func(*args, **kwargs):
-            if "cache_id" in args:
-                args["cache_id"] = filter_cache_id(cache_id=args["cache_id"])
-
-            if "cache_id" in kwargs:
-                kwargs["cache_id"] = filter_cache_id(cache_id=kwargs["cache_id"])
-
-            return func(*args, **kwargs)
-
-        return _filter_cache_id_func
-
-    @safe_cache_id
-    def set(self, text: str, cache_id: str):
-        cache_folder = self.get_cache_folder()
-        cache_index_file_path = self.get_cache_index_path()
-
-        cache_folder_files = os.listdir(cache_folder)
-        cached_file_index = self.get_index_from_file_index(_safe_cache_id=cache_id)
-        if cached_file_index is not None:
-            new_file_index = cached_file_index
-        else:
-            new_file_index = len(cache_folder_files)
-            with open(cache_index_file_path, "a") as cache_index_file_writer:
-                cache_index_file_writer.write(f"\n{new_file_index}: {cache_id}")
-
-        new_file_name = f"{new_file_index}.{self.cache_files_extension}"
-        new_file_path = os.path.join(cache_folder, new_file_name)
-        with open(new_file_path, "w+") as new_file_writer:
-            new_file_writer.write(text)
-
-    @safe_cache_id
-    def get(self, cache_id: str) -> str:
-        cached_file_index = self.get_index_from_file_index(_safe_cache_id=cache_id)
-        code = self.get_cached_file_by_index(cached_file_index=cached_file_index)
-        return code
-
-    def get_index_from_file_index(self, _safe_cache_id):
-        cache_index_file = self.get_cache_index_file()
-        if cache_index_file.find(_safe_cache_id) < 1:
-            return None
-        cache_index_file = cache_index_file[: cache_index_file.find(_safe_cache_id) - 2]
-        cached_file_index = int(cache_index_file.split("\n")[-1].strip())
-        return cached_file_index
-
-    def get_cache_index_path(
-        self,
-    ) -> str:
-        cache_index_file_name = "cache_index.yaml"
-        cache_folder = self.get_cache_folder()
-        cache_index_file_path = os.path.join(cache_folder, cache_index_file_name)
-
-        if not os.path.exists(cache_index_file_path):
-            with open(cache_index_file_path, "w+") as cache_index_file_writer:
-                cache_index_file_writer.write(f"0: {cache_index_file_name}")
-
-        return cache_index_file_path
-
-    def get_cache_index_file(
-        self,
-    ) -> str:
-        with open(self.get_cache_index_path(), "r") as f:
-            cache_index_file_content = f.read()
-
-        return cache_index_file_content
-
-    def get_cached_file_by_index(self, cached_file_index: int) -> str:
-        code = None
-        cache_folder = self.get_cache_folder()
-        cached_file_name = f"{cached_file_index}.{self.cache_files_extension}"
-        cached_file_path = os.path.join(cache_folder, cached_file_name)
-        if not os.path.exists(cached_file_path):
-            return None
-        with open(cached_file_path, "r") as cached_file_reader:
-            code = cached_file_reader.read()
-        return code
-
-    def clean(
-        self,
-    ):
-        cache_folder = self.get_cache_folder()
-        cache_folder_files = os.listdir(cache_folder)
-        for file in cache_folder_files:
-            file_to_clean = os.path.join(cache_folder, file)
-            if os.path.exists(file_to_clean):
-                os.remove(file_to_clean)
-
-    def get_cache_folder(
-        self,
-    ):
-        import tempfile
-
-        if self.cache_folder is not None:
-            return self.cache_folder
-
-        tmpdirname = tempfile.mkdtemp()
-        return tmpdirname

urlicon-0.1.0.dist-info/RECORD

@@ -1,7 +0,0 @@
-urlicon/string_cache.py,sha256=fY4ZtAdZC3PDfdotuHZmuSAcQxQLA4WyJJ6pmOUZZMc,4130
-urlicon/urlicon.py,sha256=zcbevt29l2xbr14z9jFxz64TrvyS8O-fk29mCSQIoqI,4066
-urlicon/urls.py,sha256=ErdlgRva3bxs6HuBX2iHng21PqpWGIF1etZFToJq4jc,2235
-urlicon-0.1.0.dist-info/METADATA,sha256=1SEq8BOcKYjoGQhcFFrgQFscuJoe0Sv0wDcXyq3YBLw,1713
-urlicon-0.1.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-urlicon-0.1.0.dist-info/top_level.txt,sha256=Jts8QbeWp-6xANJ9KVj3CHk6L-8D950AQ_ZKXmF4YGI,8
-urlicon-0.1.0.dist-info/RECORD,,