From 5187a6b5b12ee0166e34f67e9ee8760df4a84269 Mon Sep 17 00:00:00 2001
From: g1879 <g1879@qq.com>
Date: Thu, 31 Dec 2020 00:33:59 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BC=98=E5=8C=96s=E6=A8=A1=E5=BC=8Fhtml?=
 =?UTF-8?q?=E5=92=8Ctext=EF=BC=8C=E5=8E=BB=E9=99=A4=E7=A9=BA=E6=A0=BC?=
 =?UTF-8?q?=E5=92=8C=E5=9B=9E=E8=BD=A6=EF=BC=8C=E6=9C=AA=E5=AE=8C=E6=88=90?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 DrissionPage/common.py          |  7 +++++--
 DrissionPage/session_element.py | 31 +++++++++++++++++++++++--------
 2 files changed, 28 insertions(+), 10 deletions(-)

diff --git a/DrissionPage/common.py b/DrissionPage/common.py
index c062606..da2d22c 100644
--- a/DrissionPage/common.py
+++ b/DrissionPage/common.py
@@ -201,9 +201,12 @@ def _make_search_str(search_str: str) -> str:
     return search_str
 
 
-def format_html(text: str) -> str:
+def format_html(text: str, replace_space: bool = True) -> str:
     """处理html编码字符"""
-    return unescape(text).replace('\xa0', ' ') if text else text
+    if text:
+        return unescape(text).replace('\xa0', ' ') if replace_space else unescape(text)
+    else:
+        return text
 
 
 def translate_loc(loc: tuple) -> tuple:
diff --git a/DrissionPage/session_element.py b/DrissionPage/session_element.py
index fe01d14..bfb3f95 100644
--- a/DrissionPage/session_element.py
+++ b/DrissionPage/session_element.py
@@ -37,8 +37,15 @@ class SessionElement(DrissionElement):
     def html(self) -> str:
         """返回元素outerHTML文本"""
         # tostring()会把跟紧元素的文本节点也带上，因此要去掉
+        # print(tostring(self._inner_ele, method="html").decode())
         html = format_html(tostring(self._inner_ele, method="html").decode())
+        # print(html)
         return html[:html.rfind('>') + 1]
+        # return format_html(html[:html.rfind('>') + 1],False)
+
+    # def _html(self) -> str:
+    #     html = tostring(self._inner_ele, method="html").decode()
+    #     return html[:html.rfind('>') + 1]
 
     @property
     def inner_html(self) -> str:
@@ -59,7 +66,19 @@ class SessionElement(DrissionElement):
     @property
     def text(self) -> str:
         """返回元素内所有文本"""
-        return str(self._inner_ele.text_content())
+        html = format_html(tostring(self._inner_ele, method="html").decode(), False)
+        html = html[:html.rfind('>') + 1]
+
+        txt = re.sub(r'<.*?>', '', html).replace('\n', ' ')
+        txt = re.sub(r' {2,}', ' ', txt).strip()
+        # return format_html(txt)
+        return txt
+
+        # return t
+        # return str(self._inner_ele.text_content())
+        # return self._inner_ele.text_content()
+
+        # txt = str(self._inner_ele.text_content()).replace('\n', ' ')
 
     @property
     def link(self) -> str:
@@ -284,12 +303,6 @@ class SessionElement(DrissionElement):
         ele = self
 
         while ele:
-            # ele_id = ele.attr('id')
-
-            # if ele_id:
-            #     return f'#{ele_id}{path_str}' if mode == 'css' else f'//{ele.tag}[@id="{ele_id}"]{path_str}'
-            # else:
-
             if mode == 'css':
                 brothers = len(ele.eles(f'xpath:./preceding-sibling::*'))
                 path_str = f'>:nth-child({brothers + 1}){path_str}'
@@ -357,7 +370,8 @@ def execute_session_find(page_or_ele,
         page_or_ele = page_or_ele.inner_ele
     else:  # 传入的是SessionPage对象
         page = page_or_ele
-        page_or_ele = fromstring(page_or_ele.html)
+        # page_or_ele = fromstring(page_or_ele.html)
+        page_or_ele = fromstring(page_or_ele.response.text, False)
 
     try:
         # 用lxml内置方法获取lxml的元素对象列表
@@ -368,6 +382,7 @@ def execute_session_find(page_or_ele,
         else:
             ele = page_or_ele.cssselect(loc[1])
 
+        # 结果不是列表，如数字
         if not isinstance(ele, list):
             return ele