BeautifulSoup `limit` Argument Examples

Example 1: Limit the Number of Results

from bs4 import BeautifulSoup

html = """
<ul>
    <li>Item 1</li>
    <li>Item 2</li>
    <li>Item 3</li>
    <li>Item 4</li>
    <li>Item 5</li>
</ul>
"""

soup = BeautifulSoup(html, 'html.parser')

# Find the first 3 list items
items = soup.find_all('li', limit=3)

# Print the list items
for item in items:
    print(item.text)

Output:

Item 1
Item 2
Item 3

Example 2: Limit Parsing to the First Match

from bs4 import BeautifulSoup

html = """
<div>
    <p>First Paragraph</p>
    <p>Second Paragraph</p>
    <p>Third Paragraph</p>
</div>
"""

soup = BeautifulSoup(html, 'html.parser')

# Find the first <p> element only
paragraph = soup.find('p', limit=1)

# Print the paragraph
print(paragraph.text)

Output:

First Paragraph

Example 3: Limit Search in Nested Structures

from bs4 import BeautifulSoup

html = """
<div>
    <div>
        <p>Paragraph 1</p>
    </div>
    <div>
        <p>Paragraph 2</p>
    </div>
</div>
"""

soup = BeautifulSoup(html, 'html.parser')

# Find the first <p> element in the nested structures
paragraph = soup.find('p', limit=1)

# Print the paragraph
print(paragraph.text)

Output:

Paragraph 1

Example 4: Limit Search in Nested Structures with `find_all`

from bs4 import BeautifulSoup

html = """
<div>
    <div>
        <p>Paragraph 1</p>
    </div>
    <div>
        <p>Paragraph 2</p>
    </div>
</div>
"""

soup = BeautifulSoup(html, 'html.parser')

# Find the first 2 <p> elements in the nested structures
paragraphs = soup.find_all('p', limit=2)

# Print the paragraphs
for paragraph in paragraphs:
    print(paragraph.text)

Output:

Paragraph 1
Paragraph 2

Example 5: Limit Search in Tables

from bs4 import BeautifulSoup

html = """
<table>
    <tr>
        <td>Row 1, Cell 1</td>
        <td>Row 1, Cell 2</td>
    </tr>
    <tr>
        <td>Row 2, Cell 1</td>
        <td>Row 2, Cell 2</td>
    </tr>
    <tr>
        <td>Row 3, Cell 1</td>
        <td>Row 3, Cell 2</td>
    </tr>
</table>
"""

soup = BeautifulSoup(html, 'html.parser')

# Find the first 2 rows in the table
rows = soup.find_all('tr', limit=2)

# Print the rows
for row in rows:
    print([cell.text for cell in row.find_all('td')])

Output:

['Row 1, Cell 1', 'Row 1, Cell 2']
['Row 2, Cell 1', 'Row 2, Cell 2']

Example 6: Limit Search to Specific Sections

from bs4 import BeautifulSoup

html = """
<div class="section">
    <p>Section 1</p>
    <p>Section 1</p>
</div>
<div class="section">
    <p>Section 2</p>
    <p>Section 2</p>
</div>
"""

soup = BeautifulSoup(html, 'html.parser')

# Find the first 2 <div> elements with class "section"
sections = soup.find_all('div', class_='section', limit=2)

# Print the sections
for section in sections:
    print([p.text for p in section.find_all('p')])

Output:

['Section 1', 'Section 1']
['Section 2', 'Section 2']