BeautifulSoup recursive Argument Examples

Example 1: Default Behavior (Recursively Parsing)

from bs4 import BeautifulSoup

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

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

# Find all paragraphs recursively
paragraphs = soup.find_all('p')

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

Output:

Paragraph 1
Paragraph 2

Example 2: Disable Recursive Parsing

from bs4 import BeautifulSoup

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

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

# Find all paragraphs without recursion
paragraphs = soup.find_all('p', recursive=False)

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

Output:

Paragraph 1

Example 3: Recursive Parsing for Specific Tags

from bs4 import BeautifulSoup

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

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

# Find all paragraphs with recursive parsing within <div> tags
paragraphs = soup.find_all('p', recursive=True)

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

Output:

Paragraph 1
Paragraph 2

Example 4: Recursive Parsing for Specific Tags (Alternative Method)

from bs4 import BeautifulSoup

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

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

# Find all paragraphs with recursive parsing within <div> tags
paragraphs = soup.find_all('p', recursive=True, limit=2)

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

Output:

Paragraph 1
Paragraph 2

Example 5: Recursive Parsing in Nested Structures

from bs4 import BeautifulSoup

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

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

# Find all paragraphs with recursive parsing within nested structures
paragraphs = soup.find_all('p', recursive=True)

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

Output:

Paragraph 1

Example 6: Non-Recursive Parsing in Nested Structures

from bs4 import BeautifulSoup

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

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

# Find all paragraphs without recursive parsing within nested structures
paragraphs = soup.find_all('p', recursive=False)

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

Output:

Paragraph 1