pycoze 0.1.488__py3-none-any.whl → 0.1.489__py3-none-any.whl

pycoze/api/lib/web.py

@@ -6,62 +6,4 @@ socket = utils.socket
 
 
 class WebCls:
-    def get_simplified_webpage(self, url: str) -> str:
-        return socket.post_and_recv_result(
-            "getSimplifiedWebpage", {"url": url}
-        )
     
-    def get_simplified_html(self, html: str, selector=None) -> str:
-        soup = BeautifulSoup(html, 'html.parser')
-
-        # 如果指定了selector，则只提取该元素的内容
-        if selector:
-            element = soup.select_one(selector)
-            if element:
-                soup = BeautifulSoup(str(element), 'html.parser')
-            else:
-                return f"element not found: {selector}"
-
-        # 定义需要移除的标签
-        tags_to_remove = ['script', 'style', 'noscript', 'meta', 'link']
-        for tag in tags_to_remove:
-            for element in soup(tag):
-                element.decompose()
-
-        # 移除注释
-        for element in soup.find_all(string=lambda text: isinstance(text, Comment)):
-            element.extract()
-
-        # 定义需要保留的交互属性
-        INTERACTIVE_ATTRIBUTES = {
-            'a': ['href', 'onclick'],
-            'button': ['onclick'],
-            'img': ['src', 'onload'],
-            'form': ['action', 'onsubmit'],
-            'input': ['type', 'onclick', 'onchange'],
-            '*': ['onclick', 'onload', 'onchange', 'onsubmit', 'onmouseover']
-        }
-
-        # 遍历所有标签，保留交互属性并移除其他属性
-        for element in soup.find_all(True):
-            tag_name = element.name
-            allowed_attrs = INTERACTIVE_ATTRIBUTES.get(tag_name, []) + INTERACTIVE_ATTRIBUTES['*']
-            attrs = list(element.attrs.keys())
-            for attr in attrs:
-                if attr not in allowed_attrs:
-                    del element[attr]
-
-            # 如果是<img>标签，检查src是否为Base64
-            if tag_name == 'img' and 'src' in element.attrs and element['src'].startswith('data:'):
-                del element['src']
-
-            # 处理文本内容，超过1000字符则截取
-            if element.string and len(element.string) > 1000:
-                element.string = element.string[:1000] + '...'
-
-        # 移除标签之间的多余空白
-        for element in soup.find_all(True):
-            if not element.get_text(strip=True):
-                element.string = ''
-
-        return str(soup)

pycoze/utils/__init__.py

@@ -3,11 +3,13 @@ from .env import read_params_file, params, read_json_file
 from .socket import TcpSocket, socket, socket_subscribe
 from .text_or_file import to_text
 from .process import better_kill, execute_script, execute_script_and_block, execute_script_no_block
+from .web import get_simplified_html
 
 __all__ = [
     read_arg, 
     read_params_file, params, read_json_file, 
     TcpSocket, socket, socket_subscribe,
     to_text,
-    better_kill, execute_script, execute_script_and_block, execute_script_no_block
+    better_kill, execute_script, execute_script_and_block, execute_script_no_block,
+    get_simplified_html
 ]

pycoze/utils/web.py

@@ -0,0 +1,56 @@
+from bs4 import BeautifulSoup, Comment
+
+def get_simplified_html(html: str, selector=None) -> str:
+    soup = BeautifulSoup(html, 'html.parser')
+
+    # 如果指定了selector，则只提取该元素的内容
+    if selector:
+        element = soup.select_one(selector)
+        if element:
+            soup = BeautifulSoup(str(element), 'html.parser')
+        else:
+            return f"element not found: {selector}"
+
+    # 定义需要移除的标签
+    tags_to_remove = ['script', 'style', 'noscript', 'meta', 'link']
+    for tag in tags_to_remove:
+        for element in soup(tag):
+            element.decompose()
+
+    # 移除注释
+    for element in soup.find_all(string=lambda text: isinstance(text, Comment)):
+        element.extract()
+
+    # 定义需要保留的交互属性
+    INTERACTIVE_ATTRIBUTES = {
+        'a': ['href', 'onclick'],
+        'button': ['onclick'],
+        'img': ['src', 'onload'],
+        'form': ['action', 'onsubmit'],
+        'input': ['type', 'onclick', 'onchange'],
+        '*': ['onclick', 'onload', 'onchange', 'onsubmit', 'onmouseover']
+    }
+
+    # 遍历所有标签，保留交互属性并移除其他属性
+    for element in soup.find_all(True):
+        tag_name = element.name
+        allowed_attrs = INTERACTIVE_ATTRIBUTES.get(tag_name, []) + INTERACTIVE_ATTRIBUTES['*']
+        attrs = list(element.attrs.keys())
+        for attr in attrs:
+            if attr not in allowed_attrs:
+                del element[attr]
+
+        # 如果是<img>标签，检查src是否为Base64
+        if tag_name == 'img' and 'src' in element.attrs and element['src'].startswith('data:'):
+            del element['src']
+
+        # 处理文本内容，超过1000字符则截取
+        if element.string and len(element.string) > 1000:
+            element.string = element.string[:1000] + '...'
+
+    # 移除标签之间的多余空白
+    for element in soup.find_all(True):
+        if not element.get_text(strip=True):
+            element.string = ''
+
+    return str(soup)

{pycoze-0.1.488.dist-info → pycoze-0.1.489.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pycoze
-Version: 0.1.488
+Version: 0.1.489
 Summary: Package for pycoze only!
 Author: Yuan Jie Xiong
 Author-email: aiqqqqqqq@qq.com

{pycoze-0.1.488.dist-info → pycoze-0.1.489.dist-info}/RECORD

@@ -7,7 +7,7 @@ pycoze/api/__init__.py,sha256=TLKvaZlRzTTt0KiXijLjj9b_iCr7fU1siwsXqyd74b8,375
 pycoze/api/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pycoze/api/lib/tab.py,sha256=UnvMGxawET0J2Gp0mMDqiBH-I21sUN88T7GtU4ZD2bE,3161
 pycoze/api/lib/view.py,sha256=_PIpTfeuTPPlMDKshMGsqFQYMq7ZiO4Hg5XwHwDoU60,7357
-pycoze/api/lib/web.py,sha256=4HaOV_zYHq6-SSQQIc_O7REnC1asIlXIELxee-pU6zc,2421
+pycoze/api/lib/web.py,sha256=g8pK_heoQOORb8UPAIpEJgr1IKNLlfFkIYeN0qUBvYI,109
 pycoze/api/lib/window.py,sha256=ZZacqnX0fvZUnLUhNVjbbjhBcKkYdi_6E0LswLp1MqM,2071
 pycoze/bot/__init__.py,sha256=rL3Q-ycczRpSFfKn84fg3QBl5k22WpyeIU5qOEjEby8,79
 pycoze/bot/chat.py,sha256=UjiQeK-7rGmBY1w5EhQCx_-Y9ccHXHY_2F5LQX5NIa8,6582
@@ -27,14 +27,15 @@ pycoze/ui/base.py,sha256=7drlRZ40zF1nwGIRwLTC3EuZOSENz2qhQEWUM5yd9cg,1081
 pycoze/ui/color.py,sha256=cT9Ib8uNzkOKxyW0IwVj46o4LwdB1xgNCj1_Rou9d_4,854
 pycoze/ui/typ.py,sha256=NpT0FrbHvByOszBZMFtroRp7I7pN-38tYz_zPOPejF4,1723
 pycoze/ui/ui_def.py,sha256=lGWZGpzRoegP34D562PvK0EJHrmVZrlHW1JjsIG9A9Q,4521
-pycoze/utils/__init__.py,sha256=yj1LLPIRL7EhYuMzO1-NghW_6OMQgef3ofOeyLMksiA,488
+pycoze/utils/__init__.py,sha256=qspSyKzJneb2-esPG_RB7jF40m-VxllHO_NUFV1AaSs,550
 pycoze/utils/arg.py,sha256=jop1tBfe5hYkHW1NSpCeaZBEznkgguBscj_7M2dWfrs,503
 pycoze/utils/env.py,sha256=5pWlXfM1F5ZU9hhv1rHlDEanjEW5wf0nbyez9bNRqqA,559
 pycoze/utils/process.py,sha256=U2MURGmxfyWBqdbKfy5UvyV17M40B6HHlNELgWfgrTE,3824
 pycoze/utils/socket.py,sha256=4Wm4LlwdWXC_kAV0NnZbUc0Y3Kc6KRMyFRqSw79u-9w,2468
 pycoze/utils/text_or_file.py,sha256=gpxZVWt2DW6YiEg_MnMuwg36VNf3TX383QD_1oZNB0Y,551
-pycoze-0.1.488.dist-info/LICENSE,sha256=QStd_Qsd0-kAam_-sOesCIp_uKrGWeoKwt9M49NVkNU,1090
-pycoze-0.1.488.dist-info/METADATA,sha256=DTz7Cgp0sYAt2i2yfM-JFZwIZo7oeblaA-BrMbQYtWA,854
-pycoze-0.1.488.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-pycoze-0.1.488.dist-info/top_level.txt,sha256=76dPeDhKvOCleL3ZC5gl1-y4vdS1tT_U1hxWVAn7sFo,7
-pycoze-0.1.488.dist-info/RECORD,,
+pycoze/utils/web.py,sha256=Fkre-ZtLCInbbylOMgXWF_WHkLwIY_THReflhnP3CM4,2007
+pycoze-0.1.489.dist-info/LICENSE,sha256=QStd_Qsd0-kAam_-sOesCIp_uKrGWeoKwt9M49NVkNU,1090
+pycoze-0.1.489.dist-info/METADATA,sha256=r5DB4_ltj9pNXK22rNik-ANKhMYl_qlvNQzrcVqYTkk,854
+pycoze-0.1.489.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+pycoze-0.1.489.dist-info/top_level.txt,sha256=76dPeDhKvOCleL3ZC5gl1-y4vdS1tT_U1hxWVAn7sFo,7
+pycoze-0.1.489.dist-info/RECORD,,