복잡한 HTML 구조 탐색

from bs4 import BeautifulSoup

html_doc = """
<div class="parent">
  <p>Child 1</p>
  <span>Child 2</span>
  Text node
</div>
"""
soup = BeautifulSoup(html_doc, 'html.parser')
parent_div = soup.find('div', class_='parent')

print("Using .contents:")
for child in parent_div.contents:
  print(f"- {child.name or 'Text'}: {repr(child)[:20]}...")

print("\nUsing .children:")
for child in parent_div.children:
  print(f"- {child.name or 'Text'}: {repr(child)[:20]}...")

from bs4 import BeautifulSoup

html_doc = """
<div class="grandparent">
  <div class="parent">
    <p class="child">Hello</p>
  </div>
</div>
"""
soup = BeautifulSoup(html_doc, 'html.parser')
child_p = soup.find('p', class_='child')

print(f"Child: {child_p.name}")
print(f"Direct Parent: {child_p.parent.name}")

print("All Ancestors:")
for p in child_p.parents:
  if p.name: # Filter out [document] and other non-tag elements
    print(f"- {p.name}")

from bs4 import BeautifulSoup

html_doc = """
<div class="items">
  <p>Item 1</p>
  <span>Item 2</span>
  <p>Item 3</p>
</div>
"""
soup = BeautifulSoup(html_doc, 'html.parser')
item_one = soup.find('p', string='Item 1')

# The next sibling after <p>Item 1</p> is usually a newline character (NavigableString)
# We need to find the *next tag* sibling
next_tag = item_one.next_sibling
while next_tag and not next_tag.name:
    next_tag = next_tag.next_sibling

print(f"Item 1: {item_one.text}")
if next_tag:
  print(f"Next tag sibling: {next_tag.text}")
else:
  print("No next tag sibling found.")

from bs4 import BeautifulSoup

html_doc = """
<div class="menu">
  <a href="#home">Home</a>
  <a href="#about">About</a>
  <a href="#contact">Contact</a>
</div>
"""
soup = BeautifulSoup(html_doc, 'html.parser')
home_link = soup.find('a', href='#home')

print("All next siblings after Home:")
for sibling in home_link.next_siblings:
  if sibling.name == 'a': # Only interested in <a> tags
    print(f"- {sibling.text}: {sibling['href']}")

from bs4 import BeautifulSoup

html_doc = """
<div class="header">
  <h2>Section Title</h2>
</div>
<p>Some introductory text.</p>
<div class="content">
  <p>First paragraph.</p>
  <span>Important data!</span>
  <p>Second paragraph.</p>
</div>
"""
soup = BeautifulSoup(html_doc, 'html.parser')
section_title = soup.find('h2')

# Find the next <span> tag anywhere after the h2
important_data_span = section_title.find_next('span')

print(f"Section Title: {section_title.text}")
if important_data_span:
  print(f"Data found after title: {important_data_span.text}")

# Find all <p> tags after the h2
all_next_paragraphs = section_title.find_all_next('p')
print("All paragraphs after title:")
for p in all_next_paragraphs:
    print(f"- {p.text}")

from bs4 import BeautifulSoup

html_doc = """
<div class="product-listing">
  <div class="product">
    <h3>Laptop X</h3>
    <p class="price">$1200</p>
  </div>
  <div class="product">
    <h3>Mouse Y</h3>
    <p class="price">$50</p>
  </div>
</div>
<div class="summary">
  <p>Total items: 2</p>
</div>
"""
soup = BeautifulSoup(html_doc, 'html.parser')

# Find "Laptop X" and then get its price
laptop_h3 = soup.find('h3', string='Laptop X')
if laptop_h3:
  # The price is a sibling of the h3
  price_tag = laptop_h3.find_next_sibling('p', class_='price')
  if price_tag:
    print(f"{laptop_h3.text} price: {price_tag.text}")

# Find the product listing, then get the text of the summary's paragraph
product_listing_div = soup.find('div', class_='product-listing')
if product_listing_div:
  summary_div = product_listing_div.find_next_sibling('div', class_='summary')
  if summary_div:
    summary_text = summary_div.find('p').text
    print(f"Summary: {summary_text}")

from bs4 import BeautifulSoup

html_doc = """
<div>
  Hello
  <p>World</p>
  !
</div>
"""
soup = BeautifulSoup(html_doc, 'html.parser')
div_tag = soup.find('div')

print("Children of the div:")
for child in div_tag.children:
  if child.name:
    print(f"- Tag: {child.name}, Text: {child.text}")
  else:
    print(f"- Text Node: {repr(child)}")

# Accessing a specific NavigableString
hello_text_node = list(div_tag.children)[0]
print(f"\nFirst child (text node): '{hello_text_node.strip()}'")