python-urlopen 0.0.5__tar.gz → 0.0.5.1__tar.gz

{python_urlopen-0.0.5 → python_urlopen-0.0.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: python-urlopen
-Version: 0.0.5
+Version: 0.0.5.1
 Summary: Python urlopen wrapper.
 Home-page: https://github.com/ChenyangGao/web-mount-packs/tree/main/python-module/python-urlopen
 License: MIT
@@ -21,9 +21,11 @@ Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Software Development
 Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Dist: brotli
 Requires-Dist: http_response
 Requires-Dist: python-argtools
 Requires-Dist: python-filewrap
+Requires-Dist: zstandard
 Project-URL: Repository, https://github.com/ChenyangGao/web-mount-packs/tree/main/python-module/python-urlopen
 Description-Content-Type: text/markdown
 

{python_urlopen-0.0.5 → python_urlopen-0.0.5.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-urlopen"
-version = "0.0.5"
+version = "0.0.5.1"
 description = "Python urlopen wrapper."
 authors = ["ChenyangGao <wosiwujm@gmail.com>"]
 license = "MIT"
@@ -27,9 +27,11 @@ include = [
 
 [tool.poetry.dependencies]
 python = "^3.10"
+brotli = "*"
 http_response = "*"
 python-argtools = "*"
 python-filewrap = "*"
+zstandard = "*"
 
 [tool.poetry.scripts]
 python-urlopen = "urlopen.__main__:main"

{python_urlopen-0.0.5 → python_urlopen-0.0.5.1}/urlopen/__init__.py

@@ -9,6 +9,7 @@ import errno
 
 from collections.abc import Callable, Generator, Iterable, Mapping, Sequence
 from copy import copy
+from gzip import decompress as decompress_gzip
 from http.client import HTTPResponse
 from http.cookiejar import CookieJar
 from inspect import isgenerator
@@ -22,10 +23,13 @@ from typing import cast, Any
 from urllib.error import HTTPError
 from urllib.parse import urlencode, urlsplit
 from urllib.request import build_opener, HTTPCookieProcessor, HTTPSHandler, OpenerDirector, Request
+from zlib import compressobj, DEF_MEM_LEVEL, DEFLATED, MAX_WBITS
 
 from argtools import argcount
+from brotli import decompress as decompress_br # type: ignore
 from filewrap import bio_skip_iter, SupportsRead, SupportsWrite
 from http_response import get_filename, get_length, is_chunked, is_range_request
+from zstandard import decompress as decompress_zstd
 
 
 if "__del__" not in HTTPResponse.__dict__:
@@ -34,6 +38,43 @@ if "__del__" not in HTTPResponse.__dict__:
 CRE_search_charset = re_compile(r"\bcharset=(?P<charset>[^ ;]+)").search
 
 
+def decompress_deflate(data, compresslevel=9):
+    # Fork from: https://stackoverflow.com/questions/1089662/python-inflate-and-deflate-implementations#answer-1089787
+    compress = compressobj(
+            compresslevel,  # level: 0-9
+            DEFLATED,       # method: must be DEFLATED
+            -MAX_WBITS,     # window size in bits:
+                            #   -15..-8: negate, suppress header
+                            #   8..15: normal
+                            #   16..30: subtract 16, gzip header
+            DEF_MEM_LEVEL,  # mem level: 1..8/9
+            0               # strategy:
+                            #   0 = Z_DEFAULT_STRATEGY
+                            #   1 = Z_FILTERED
+                            #   2 = Z_HUFFMAN_ONLY
+                            #   3 = Z_RLE
+                            #   4 = Z_FIXED
+    )
+    deflated = compress.compress(data)
+    deflated += compress.flush()
+    return deflated
+
+
+def decompress_response(resp: HTTPResponse) -> bytes:
+    data = resp.read()
+    content_encoding = resp.headers.get("Content-Encoding")
+    match content_encoding:
+        case "gzip":
+            data = decompress_gzip(data)
+        case "deflate":
+            data = decompress_deflate(data)
+        case "br":
+            data = decompress_br(data)
+        case "zstd":
+            data = decompress_zstd(data)
+    return data
+
+
 def urlopen(
     url: str | Request, 
     method: str = "GET", 
@@ -136,17 +177,16 @@ def request(
     if parse is None:
         return resp
     with resp:
-        if parse is False:
-            return resp.read()
-        elif parse is True:
-            data = resp.read()
-            content_type = resp.headers.get("Content-Type", "")
-            if content_type == "application/json":
-                return loads(data)
-            elif content_type.startswith("application/json;"):
-                return loads(data.decode(get_charset(content_type)))
-            elif content_type.startswith("text/"):
-                return data.decode(get_charset(content_type))
+        if isinstance(parse, bool):
+            data = decompress_response(resp)
+            if parse is True:
+                content_type = resp.headers.get("Content-Type", "")
+                if content_type == "application/json":
+                    return loads(data)
+                elif content_type.startswith("application/json;"):
+                    return loads(data.decode(get_charset(content_type)))
+                elif content_type.startswith("text/"):
+                    return data.decode(get_charset(content_type))
             return data
         else:
             ac = argcount(parse)
@@ -154,7 +194,7 @@ def request(
                 if ac == 1:
                     return parse(resp)
                 else:
-                    return parse(resp, resp.read())
+                    return parse(resp, decompress_response(resp))
 
 
 def download(