Big News: Socket raises $60M Series C at a $1B valuation to secure software supply chains for AI-driven development.Announcement →
Sign In

html2object

Package Overview
Dependencies
Maintainers
1
Versions
7
Alerts
File Explorer

Advanced tools

License
Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

html2object - pypi Package Compare versions

Comparing version
0.1.2
 to
0.1.3
+35
tests/test_html2object.py
import unittest
from html2object.html2object import *
class TestHtml2Object(unittest.TestCase):
def test_get_element(self):
html = "<div class='container'><h1>Title</h1></div>"
element = get_element(html, name="h1")
self.assertEqual(element, "<h1>")
def test_remove_element(self):
html = "<div class='container'><h1>Title</h1></div>"
new_html = remove_element(html, name="h1")
self.assertEqual(new_html, "<div class='container'></div>")
def test_get_name(self):
html = "<div class='container'><h1>Title</h1></div>"
name = get_name(html)
self.assertEqual(name, "div")
def test_get_attributes(self):
html = "<div id='main' class='container'><h1>Title</h1></div>"
attributes = get_attributes(html)
expected_attributes = {"id": "'main'", "class": "'container'"}
self.assertEqual(attributes, expected_attributes)
def test_get_child(self):
html = "<div><span>Child</span></div>"
child = get_child(html, name="div")
self.assertEqual(child, "<span>Child</span>")
if __name__ == "__main__":
unittest.main()
+1
-1
html2object.egg-info/PKG-INFO
Metadata-Version: 2.1
Name: html2object
Version: 0.1.2
Version: 0.1.3
Summary: Tools to handle the CRUD of .html files as objects.

@@ -5,0 +5,0 @@ Home-page: https://github.com/boterop/html2object

+1
-0
html2object.egg-info/SOURCES.txt

@@ -12,2 +12,3 @@ LICENSE

tests/__init__.py
tests/test_html2object.py
tests/test_html_element.py
+7
-16
html2object/html_element.py

@@ -23,6 +23,3 @@ import uuid

self.name = name
if id:
self.attributes = {"id": id, **attributes}
else:
self.attributes = attributes
self.attributes = {"id": id, **attributes} if id else attributes
self.children = children

@@ -59,5 +56,3 @@

result = None
if self.parent:
result = self.parent.find_element_by_id(id, pile)
result = self.parent.find_element_by_id(id, pile) if self.parent else None
if self.children and not result:

@@ -74,8 +69,5 @@ for child in self.children:

children_html = ""
children = self.children if self.children else []
children = self.children or []
for child in children:
if type(child) is str:
children_html += child
else:
children_html += str(child)
children_html += child if type(child) is str else str(child)
children_html += "\n"

@@ -107,5 +99,4 @@ children_html = children_html.strip()

children_html = html_u.get_child(html, name=self.name)
if children_html == None:
self.children = None
else:
self.children = None
if children_html is not None:
self.children = []

@@ -115,3 +106,3 @@ self._add_children(children_html)

def _add_children(self, html: str):
if html == "":
if not html:
return

@@ -118,0 +109,0 @@ try:

+6
-13
html2object/html2object.py

@@ -26,11 +26,4 @@ import re

def get_id(html: str) -> str:
id = re.search(r'id=[\'"]([^\'"]+)[\'"]', html)
if not id:
return ""
return id.group()
def get_attributes(html: str) -> dict:
attribs = re.search(r"<([a-zA-Z][a-zA-Z0-9]*)\b([^>]*)>", html).group(2).strip()
attribs = re.search(r"<([a-zA-Z][a-zA-Z0-9]*)\b([^>]*)>", html)[2].strip()
attribs_list = attribs.split(" ")

@@ -41,3 +34,3 @@ attribs_list = _fix_attrs(attribs_list)

for attr in attribs_list:
if attr != "" and attr != "/":
if attr not in ["", "/"]:
attr_div = attr.strip().split("=", 1)

@@ -47,3 +40,3 @@ key = attr_div[0]

key = last_key
value = attributes[key] + " " + attr_div[0]
value = f"{attributes[key]} {attr_div[0]}"
else:

@@ -74,7 +67,7 @@ value = attr_div[1]

html = re.sub(rf"<\/{name}>", "<remove>", html, 1)
(_, start_index) = re.search(rf"<{name}\b[^>]*>", html).span()
(end_index, _) = re.search(rf"<\/{name}>", html).span()
html = re.sub("<remove>", f"</{name}>", html)
end_index = end_index - ((5 - len(name)) * count)
child = html[:end_index].replace(element, "").strip()
return child
return html[start_index:end_index].strip()

@@ -89,3 +82,3 @@

if mix:
attr = mix + " " + attr
attr = f"{mix} {attr}"
mix = None

@@ -92,0 +85,0 @@ if attr.strip()[-1] in no_splitable:

+1
-1
PKG-INFO
Metadata-Version: 2.1
Name: html2object
Version: 0.1.2
Version: 0.1.3
Summary: Tools to handle the CRUD of .html files as objects.

@@ -5,0 +5,0 @@ Home-page: https://github.com/boterop/html2object

+1
-1
setup.py

@@ -5,3 +5,3 @@ from setuptools import setup, find_packages

name="html2object",
version="0.1.2",
version="0.1.3",
author="boterop",

@@ -8,0 +8,0 @@ author_email="boterop22@gmail.com",