pycoze 0.1.487__tar.gz → 0.1.489__tar.gz

{pycoze-0.1.487 → pycoze-0.1.489}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pycoze
-Version: 0.1.487
+Version: 0.1.489
 Summary: Package for pycoze only!
 Author: Yuan Jie Xiong
 Author-email: aiqqqqqqq@qq.com

pycoze-0.1.489/pycoze/api/lib/web.py

@@ -0,0 +1,9 @@
+from pycoze import utils
+from bs4 import BeautifulSoup, Comment
+
+
+socket = utils.socket
+
+
+class WebCls:
+    

{pycoze-0.1.487 → pycoze-0.1.489}/pycoze/bot/tools.py

@@ -117,7 +117,7 @@ class WriteFileTool(Tool):
         # 创建目录并写入或覆盖文件
         os.makedirs(os.path.dirname(path), exist_ok=True)
         with open(path, "w", encoding="utf-8") as f:
-            f.write(self.params["content"].replace("@`@`@`@", "```")
+            f.write(self.params["content"].replace("@`@`@`@", "```"))
         return f"File [[{path}]] written successfully."
 
 

{pycoze-0.1.487 → pycoze-0.1.489}/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-0.1.489/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-0.1.487 → pycoze-0.1.489}/pycoze.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pycoze
-Version: 0.1.487
+Version: 0.1.489
 Summary: Package for pycoze only!
 Author: Yuan Jie Xiong
 Author-email: aiqqqqqqq@qq.com

{pycoze-0.1.487 → pycoze-0.1.489}/pycoze.egg-info/SOURCES.txt

@@ -39,4 +39,5 @@ pycoze/utils/arg.py
 pycoze/utils/env.py
 pycoze/utils/process.py
 pycoze/utils/socket.py
-pycoze/utils/text_or_file.py
+pycoze/utils/text_or_file.py
+pycoze/utils/web.py

{pycoze-0.1.487 → pycoze-0.1.489}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="pycoze",
-    version="0.1.487",
+    version="0.1.489",
     packages=find_packages(),
     install_requires=[],
     author="Yuan Jie Xiong",

pycoze-0.1.487/pycoze/api/lib/web.py

@@ -1,67 +0,0 @@
-from pycoze import utils
-from bs4 import BeautifulSoup, Comment
-
-
-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)