From e439c1f679011b8c5d4cacd5c15c121f77ec52b2 Mon Sep 17 00:00:00 2001
From: g1879 <g1879@qq.com>
Date: Sat, 7 Nov 2020 15:46:35 +0800
Subject: [PATCH] =?UTF-8?q?SessionElement=E7=9A=84attr()=E5=88=A0=E9=99=A4?=
 =?UTF-8?q?=E5=AF=B9#=E5=92=8C=3F=E5=BC=80=E5=A4=B4=E7=9B=B8=E5=AF=B9?=
 =?UTF-8?q?=E8=B7=AF=E5=BE=84=E7=9A=84=E5=A4=84=E7=90=86?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 DrissionPage/session_element.py | 25 ++++++++-----------------
 1 file changed, 8 insertions(+), 17 deletions(-)

diff --git a/DrissionPage/session_element.py b/DrissionPage/session_element.py
index d3182e3..94f8084 100644
--- a/DrissionPage/session_element.py
+++ b/DrissionPage/session_element.py
@@ -231,23 +231,18 @@ class SessionElement(DrissionElement):
         :return: 属性值文本，没有该属性返回None
         """
         try:
+            # 获取href属性时返回绝对url
             if attr == 'href':
-                # 如直接获取attr只能获取相对地址
                 link = self.inner_ele.get('href')
+
+                # 若链接为js或邮件，直接返回
                 if link.lower().startswith(('javascript:', 'mailto:')):
                     return link
-                elif link.startswith('#'):
-                    if '#' in self.page.url:
-                        return re.sub(r'#.*', link, self.page.url)
-                    else:
-                        return f'{self.page.url}{link}'
-                elif link.startswith('?'):  # 避免当相对url以?开头时丢失参数的bug TODO:测试是否还存在
-                    if '?' in self.page.url:
-                        return re.sub(r'\?.*', link, self.page.url)
-                    else:
-                        return f'{self.page.url}{link}'
+
+                # 其它情况直接返回绝对url
                 else:
                     return self._make_absolute(link)
+
             elif attr == 'src':
                 return self._make_absolute(self.inner_ele.get('src'))
             elif attr == 'text':
@@ -293,12 +288,13 @@ def execute_session_find(page_or_ele,
     if mode not in ['single', 'all']:
         raise ValueError(f"Argument mode can only be 'single' or 'all', not '{mode}'.")
 
+    # 根据传入对象类型获取页面对象和lxml元素对象
     if isinstance(page_or_ele, SessionElement):
         page = page_or_ele.page
         page_or_ele = page_or_ele.inner_ele
     else:  # 传入的是SessionPage对象
         page = page_or_ele
-        page_or_ele = get_HtmlElement(page_or_ele.response.text)
+        page_or_ele = HTML(page_or_ele.response.text)
 
     try:
         # 用lxml内置方法获取lxml的元素对象列表
@@ -328,8 +324,3 @@ def execute_session_find(page_or_ele,
 
     except SelectorSyntaxError:
         raise SyntaxError('Invalid css selector syntax.', loc)
-
-
-def get_HtmlElement(html: str) -> _Element:
-    """从html文本生成lxml的元素对象"""
-    return HTML(html)