Data Extraction and Content Retrieval

def get(self) -> Any:
    """
    Serialize and return the matched node content.

    Returns:
    - For HTML/XML: String representation with percent-encoded content unquoted
    - For JSON/text: Raw data as-is
    - For boolean values: "1" for True, "0" for False
    - For other types: String conversion

    Note:
    - Uses appropriate serialization method based on document type
    - Preserves XML/HTML structure in output
    """

def getall(self) -> List[str]:
    """
    Serialize and return the matched node in a 1-element list.

    Returns:
    List[str]: Single-element list containing serialized content
    """

# Legacy alias
extract = get

from parsel import Selector

html = """
<div class="content">
    <p>First <strong>bold</strong> paragraph</p>
    <p>Second paragraph</p>
</div>
"""

selector = Selector(text=html)

# Extract full element with tags
full_content = selector.css('.content').get()
# Returns: '<div class="content">\\n    <p>First <strong>bold</strong> paragraph</p>\\n    <p>Second paragraph</p>\\n</div>'

# Extract text content only
text_only = selector.css('.content p::text').getall()
# Returns: ['First ', 'Second paragraph']

# Extract as single item
first_text = selector.css('.content p::text').get()
# Returns: 'First '

def re(
    self, regex: Union[str, Pattern[str]], replace_entities: bool = True
) -> List[str]:
    """
    Apply regex and return list of matching strings.

    Parameters:
    - regex (str or Pattern): Regular expression pattern
    - replace_entities (bool): Replace HTML entities except & and <

    Returns:
    List[str]: All regex matches from the content

    Extraction rules:
    - Named group "extract": Returns only the named group content
    - Multiple numbered groups: Returns all groups flattened
    - No groups: Returns entire regex matches
    """

def re_first(
    self,
    regex: Union[str, Pattern[str]],
    default: Optional[str] = None,
    replace_entities: bool = True,
) -> Optional[str]:
    """
    Apply regex and return first matching string.

    Parameters:
    - regex (str or Pattern): Regular expression pattern
    - default (str, optional): Value to return if no match found
    - replace_entities (bool): Replace HTML entities except & and <

    Returns:
    str or None: First match or default value
    """

html = """
<div>
    <p>Price: $25.99</p>
    <p>Discount: 15%</p>
    <p>Contact: user@example.com</p>
</div>
"""

selector = Selector(text=html)

# Extract all numbers
numbers = selector.css('div').re(r'\\d+\\.?\\d*')
# Returns: ['25.99', '15']

# Extract email addresses
emails = selector.css('div').re(r'[\\w.-]+@[\\w.-]+\\.\\w+')
# Returns: ['user@example.com']

# Extract with named groups
prices = selector.css('div').re(r'Price: \\$(?P<extract>\\d+\\.\\d+)')
# Returns: ['25.99']

# Get first match with default
first_number = selector.css('div').re_first(r'\\d+', default='0')
# Returns: '25'

# Extract from specific elements
contact_email = selector.css('p:contains("Contact")').re_first(r'[\\w.-]+@[\\w.-]+\\.\\w+')
# Returns: 'user@example.com'

@property
def attrib(self) -> Dict[str, str]:
    """
    Return the attributes dictionary for underlying element.

    Returns:
    Dict[str, str]: All attributes as key-value pairs

    Note:
    - Empty dict for non-element nodes
    - Converts lxml attrib to standard dict
    """

html = """
<div class="container" id="main" data-value="123">
    <a href="https://example.com" target="_blank" title="External Link">Link</a>
    <img src="image.jpg" alt="Description" width="300" height="200">
</div>
"""

selector = Selector(text=html)

# Get all attributes of div
div_attrs = selector.css('div').attrib
# Returns: {'class': 'container', 'id': 'main', 'data-value': '123'}

# Get all attributes of link
link_attrs = selector.css('a').attrib
# Returns: {'href': 'https://example.com', 'target': '_blank', 'title': 'External Link'}

# Access specific attribute values
href_value = selector.css('a').attrib.get('href')
# Returns: 'https://example.com'

# Check for attribute existence
has_target = 'target' in selector.css('a').attrib
# Returns: True

html = """
<p>Price: &lt; $100 &amp; shipping included &gt;</p>
<p>Copyright &copy; 2024</p>
"""

selector = Selector(text=html)

# With entity replacement (default)
text_with_entities = selector.css('p').re(r'.+', replace_entities=True)
# Returns: ['Price: < $100 & shipping included >', 'Copyright © 2024']

# Without entity replacement
text_raw = selector.css('p').re(r'.+', replace_entities=False)
# Returns: ['Price: &lt; $100 &amp; shipping included &gt;', 'Copyright &copy; 2024']

# Specific entities are preserved (&amp; and &lt;)
mixed_content = selector.css('p:first-child').re(r'.+', replace_entities=True)
# Returns: ['Price: < $100 & shipping included >']