Element Modification

def drop(self) -> None:
    """
    Drop matched nodes from the parent element.
    
    Removes the selected element from its parent in the DOM tree.
    Uses appropriate removal method based on document type:
    - HTML: Uses lxml's drop_tree() method
    - XML: Uses parent.remove() method
    
    Raises:
    - CannotRemoveElementWithoutRoot: Element has no root document
    - CannotDropElementWithoutParent: Element has no parent to remove from
    """

def remove(self) -> None:
    """
    Remove matched nodes from the parent element.
    
    Deprecated: Use drop() method instead.
    
    Raises:
    - CannotRemoveElementWithoutRoot: Element has no root document  
    - CannotRemoveElementWithoutParent: Element has no parent to remove from
    - DeprecationWarning: Method is deprecated
    """

from parsel import Selector

html = """
<article>
    <h1>Article Title</h1>
    <div class="ads">Advertisement content</div>
    <p>First paragraph of content.</p>
    <div class="ads">Another advertisement</div>
    <p>Second paragraph of content.</p>
    <div class="sidebar">Sidebar content</div>
</article>
"""

selector = Selector(text=html)

# Remove all advertisement elements
ads = selector.css('.ads')
ads.drop()

# Verify ads are removed
remaining_content = selector.css('article').get()
print("Ads removed:", "ads" not in remaining_content)

# Remove sidebar
sidebar = selector.css('.sidebar')
sidebar.drop()

# Check final structure - only h1 and p elements remain
final_structure = selector.css('article > *')
elements = [elem.root.tag for elem in final_structure]
# Returns: ['h1', 'p', 'p']

html_with_cleanup = """
<div class="content">
    <h2>Important Heading</h2>
    <script>tracking_code();</script>
    <p>Valuable content paragraph.</p>
    <div class="popup">Popup modal</div>
    <p>Another valuable paragraph.</p>
    <noscript>No JavaScript message</noscript>
    <footer>Footer content</footer>
</div>
"""

selector = Selector(text=html_with_cleanup)

# Remove multiple unwanted element types at once
unwanted = selector.css('script, .popup, noscript')
unwanted.drop()

# Verify cleanup
cleaned_content = selector.css('.content').get()
print("Scripts removed:", "script" not in cleaned_content)
print("Popups removed:", "popup" not in cleaned_content)
print("Noscript removed:", "noscript" not in cleaned_content)

# Extract clean content
clean_paragraphs = selector.css('p::text').getall()
# Returns: ['Valuable content paragraph.', 'Another valuable paragraph.']

html_with_conditions = """
<div class="comments">
    <div class="comment" data-score="5">Great article!</div>
    <div class="comment" data-score="1">Spam content here</div>
    <div class="comment" data-score="4">Very helpful, thanks.</div>
    <div class="comment" data-score="2">Not very useful</div>
    <div class="comment" data-score="5">Excellent explanation!</div>
</div>
"""

selector = Selector(text=html_with_conditions)

# Remove low-quality comments (score <= 2)
low_quality = selector.xpath('//div[@class="comment"][@data-score<=2]')
low_quality.drop()

# Verify only high-quality comments remain
remaining_scores = selector.css('.comment').xpath('./@data-score').getall()
# Returns: ['5', '4', '5'] - only scores > 2

# Remove comments containing specific text
spam_comments = selector.xpath('//div[@class="comment"][contains(text(), "spam")]')
spam_comments.drop()

html_with_mixed_content = """
<article>
    <h1>Product Review</h1>
    <div class="meta">
        <span class="author">John Doe</span>
        <span class="date">2024-01-15</span>
        <span class="tracking" data-track="view">TRACK123</span>
    </div>
    <div class="content">
        <p>This product is amazing!</p>
        <div class="affiliate-link">
            <a href="/affiliate?id=123">Buy Now - Special Offer!</a>
        </div>
        <p>I highly recommend it to everyone.</p>
    </div>
</article>
"""

selector = Selector(text=html_with_mixed_content)

# Remove tracking and affiliate elements
tracking_elements = selector.css('[data-track], .affiliate-link')
tracking_elements.drop()

# Extract clean content
article_text = selector.css('.content p::text').getall()
# Returns: ['This product is amazing!', 'I highly recommend it to everyone.']

# Verify meta information is preserved (author, date kept)
meta_info = selector.css('.meta span:not(.tracking)::text').getall()
# Returns: ['John Doe', '2024-01-15']

class CannotRemoveElementWithoutRoot(Exception):
    """
    Raised when attempting to remove an element that has no root document.
    
    Common causes:
    - Trying to remove text nodes or pseudo-elements
    - Working with detached elements
    """

class CannotRemoveElementWithoutParent(Exception):
    """
    Raised when attempting to remove an element that has no parent.
    
    Common causes:
    - Trying to remove the root element
    - Working with already-removed elements
    """

class CannotDropElementWithoutParent(CannotRemoveElementWithoutParent):
    """
    Specific exception for drop() operations.
    Inherits from CannotRemoveElementWithoutParent.
    """

from parsel import Selector
from parsel.selector import (
    CannotRemoveElementWithoutRoot,
    CannotDropElementWithoutParent
)

html = """
<div>
    <p>Paragraph with <em>emphasis</em> text.</p>
    <ul>
        <li>Item 1</li>
        <li>Item 2</li>
    </ul>
</div>
"""

selector = Selector(text=html)

# Safe element removal with exception handling
def safe_remove_elements(selector, css_query):
    try:
        elements = selector.css(css_query)
        elements.drop()
        return True
    except CannotRemoveElementWithoutRoot:
        print(f"Cannot remove {css_query}: elements have no root")
        return False
    except CannotDropElementWithoutParent:
        print(f"Cannot remove {css_query}: elements have no parent")
        return False

# Remove list items safely
success = safe_remove_elements(selector, 'li')
print(f"List items removed: {success}")

# Try to remove text nodes (will fail gracefully)
text_nodes = selector.xpath('//text()')
try:
    text_nodes.drop()
except CannotRemoveElementWithoutRoot as e:
    print(f"Expected error: {e}")

# Try to remove root element (will fail)
try:
    root_div = selector.css('div')
    if root_div:
        root_div[0].drop()  # Try to remove root
except CannotDropElementWithoutParent as e:
    print(f"Cannot remove root: {e}")

html = """
<nav>
    <ul>
        <li><a href="/home">Home</a></li>
        <li class="active"><a href="/products">Products</a></li>
        <li><a href="/contact">Contact</a></li>
    </ul>
</nav>
"""

selector = Selector(text=html)

# Count elements before removal
initial_count = len(selector.css('li'))
print(f"Initial list items: {initial_count}")  # 3

# Remove active item
active_item = selector.css('li.active')
active_item.drop()

# Count elements after removal
final_count = len(selector.css('li'))
print(f"Remaining list items: {final_count}")  # 2

# Verify active item is gone
active_check = selector.css('li.active')
print(f"Active items found: {len(active_check)}")  # 0

# Get final HTML structure
final_html = selector.css('nav').get()
print("Active class removed:", "active" not in final_html)