Feat #437 urlencode 和 urldecode 支持指定编码

libs/utils.py

@@ -22,6 +22,7 @@
                       b2a_qp, b2a_uu, crc32, crc_hqx)
 from email.mime.text import MIMEText
 from hashlib import sha1
+from typing import Any, Iterable, Mapping, Tuple, Union
 from urllib import parse as urllib_parse
 
 import charset_normalizer
@@ -30,7 +31,7 @@
 from faker import Faker
 from jinja2.filters import do_float, do_int
 from jinja2.runtime import Undefined
-from jinja2.utils import generate_lorem_ipsum
+from jinja2.utils import generate_lorem_ipsum, url_quote
 from requests.utils import get_encoding_from_headers
 from tornado import gen, httpclient
 
@@ -338,6 +339,41 @@ def conver2unicode(value, html_unescape=False):
         tmp = html.unescape(tmp)
     return tmp
 
+def urlencode_with_encoding(
+    value: Union[str, Mapping[str, Any], Iterable[Tuple[str, Any]]],
+    encoding: str = "utf-8",
+    for_qs: bool = False,
+) -> str:
+    """Quote data for use in a URL path or query using UTF-8.
+
+    Basic wrapper around :func:`urllib.parse.quote` when given a
+    string, or :func:`urllib.parse.urlencode` for a dict or iterable.
+
+    :param value: Data to quote. A string will be quoted directly. A
+        dict or iterable of ``(key, value)`` pairs will be joined as a
+        query string.
+    :param encoding: The encoding to use for quoted strings.
+    :param for_qs: If ``True``, quote ``/`` as ``%2F``. If ``False``,
+        leave slashes unquoted. Defaults to ``False``.
+
+    When given a string, "/" is not quoted. HTTP servers treat "/" and
+    "%2F" equivalently in paths. If you need quoted slashes, use the
+    ``|replace("/", "%2F")`` filter.
+
+    .. versionadded:: 2.7
+    """
+    if isinstance(value, str) or not isinstance(value, Iterable):
+        return url_quote(value, charset=encoding, for_qs=for_qs)
+
+    if isinstance(value, dict):
+        items: Iterable[Tuple[str, Any]] = value.items()
+    else:
+        items = value  # type: ignore
+
+    return "&".join(
+        f"{url_quote(k, for_qs=True)}={url_quote(v, for_qs=True)}" for k, v in items
+    )
+
 def to_bool(value):
     ''' return a bool for the arg '''
     if value is None or isinstance(value, bool):
@@ -802,6 +838,7 @@ def _aes_decrypt(word:str, key:str, mode='CBC', iv:str=None, input_format='base6
     'bool': to_bool,
     'utf8': utf8,
     'unicode': conver2unicode,
+    'urlencode': urlencode_with_encoding,
     'quote_chinese': quote_chinese,
     # binascii
     'b2a_hex': b2a_hex,

web/handlers/util.py

@@ -273,7 +273,12 @@ async def post(self):
         Rtv = {}
         try:
             content = self.get_argument("content", "")
-            Rtv[u"转换后"] = urllib.parse.unquote(content)
+            encoding = self.get_argument("encoding", "utf-8")
+            unquote_plus = self.get_argument("unquote_plus", "false")
+            if strtobool(unquote_plus):
+                Rtv[u"转换后"] = urllib.parse.unquote_plus(content, encoding=encoding)
+            else:
+                Rtv[u"转换后"] = urllib.parse.unquote(content, encoding=encoding)
             Rtv[u"状态"] = "200"
         except Exception as e:
             Rtv[u"状态"] = str(e)

web/static/coffee/har/entry_editor.coffee

@@ -395,7 +395,7 @@ define (require, exports, module) ->
           headers: [],
           cookies: [],
           postData: {
-            text: "content="
+            text: "unquote_plus=false&encoding=utf-8&content="
           }
         },
         response: {},

web/tpl/about.html

@@ -79,9 +79,9 @@ <h2>
             <a href="/util/urldecode" target="_blank" rel="nofollow">api://util/urldecode</a>
           <button class="btn hljs-button" data-clipboard-target="#api_url3">复制</button>
         </td>
-        <td>content</td>
+        <td>unquote_plus,encoding,content</td>
         <td>是</td>
-        <td>要转码的内容</td>
+        <td>unquote_plus: 是否将加号(+)解码为空格( ), <br>默认为 False, 仅在 encoding 为 utf-8 时生效. <br>encoding: 指定编码, 默认为 utf-8<br>content:要转码的 urlencoded 内容, <br>如果 content 为非 utf-8 编码的 urlencoded 字符串, 请再次进行 urlencode 编码后再传入</td>
 
           <td id="api_exam3" class="showbut">
             <div class="autowrap">
@@ -341,6 +341,13 @@ <h2>
         <td class="autowrap">123%E4%B8%AD%E6%96%87QAQ&amp;amp;/:</td>
       </tr>
 
+      <tr>
+        <td>urlencode(value,encoding="utf-8", for_qs=False)</td>
+        <td>将 value 字符串进行url编码, <br>encoding: 编码, 默认为 utf-8, <br>for_qs: 是否将斜杠 / 编码为 %2F, 将 %20 替换为 +, 默认为 False</td>
+        <td>{{ urlencode("http://www.baidu.com?name=张三&age=18 ") }}</td>
+        <td class="autowrap">http%3A//www.baidu.com%3Fname%3D%E5%BC%A0%E4%B8%89%26age%3D18%20</td>
+      </tr>
+
       <tr>
         <td>b2a_hex(data[, sep[, bytes_per_sep=1]])</td>
         <td>将字节流 data 转为十六进制表示, <br>sep: 分隔符, 默认为空<br>bytes_per_sep: 每隔多少个字节添加一个分隔符, 默认为1</td>
@@ -746,13 +753,6 @@ <h2>
         <td class="autowrap">123 456</td>
       </tr>
 
-      <tr>
-        <td>urlencode</td>
-        <td>将字符串进行url编码</td>
-        <td>{{ "http://www.baidu.com?name=张三&age=18" | urlencode }}</td>
-        <td class="autowrap">http%3A//www.baidu.com%3Fname%3D%E5%BC%A0%E4%B8%89%26age%3D18</td>
-      </tr>
-
       <tr>
         <td>upper</td>
         <td>将字符串转为大写</td>