파이썬 BeautifulSoup 선택과 탐색 SoupSieve CSS4 확장 정리

from bs4 import BeautifulSoup

html = '''
<div class="content">
  <p class="highlight">첫 번째 문단</p>
  <p>두 번째 문단</p>
</div>
'''

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

# CSS4 선택자 사용
first_para = soup.select_one("div.content > p:nth-of-type(1)")
print(first_para.text)  # 출력: 첫 번째 문단

from bs4 import BeautifulSoup

html = '''
<div>텍스트</div>
<p>문단</p>
<span>강조 텍스트</span>
'''

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

elements = soup.select(":is(p, span, div)")
for e in elements:
    print(e.text)

html = '''
<p class="highlight">첫 번째 문단</p>
<p>두 번째 문단</p>
<p>세 번째 문단</p>
'''

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

paras = soup.select("p:not(.highlight)")
for p in paras:
    print(p.text)

from bs4 import BeautifulSoup

html = '''
<div class="card">
  <h3>상품 A</h3>
  <p class="desc">설명</p>
</div>
<div class="card">
  <h3>상품 B</h3>
  <p class="price">19,900원</p>
</div>
<div class="card">
  <h3>상품 C</h3>
  <p class="price">29,900원</p>
  <a href="/buy/3">구매하기</a>
</div>
'''

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

# 가격 정보를 가진 카드만
priced_cards = soup.select('div.card:has(.price)')
print([c.h3.get_text(strip=True) for c in priced_cards])  # ['상품 B', '상품 C']

# '구매하기' 링크가 있는 카드만
buyable = soup.select('div.card:has(a[href^="/buy"])')
print([c.h3.get_text(strip=True) for c in buyable])       # ['상품 C']

html = '''
<div class="card">
  <img src="a1.jpg">
  <img src="a2.jpg">
  <img src="a3.jpg">
</div>

<table class="data">
  <tr><td>이름</td><td>가격</td></tr>
  <tr><td>A</td><td>19900</td></tr>
  <tr><td>B</td><td>29900</td></tr>
</table>
'''

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

# 카드 안의 두 번째 이미지
second_img = soup.select_one('div.card > img:nth-of-type(2)')
print(second_img["src"])  # a2.jpg

# 각 행의 두 번째 셀(td)
second_cells = [td.get_text(strip=True) for td in soup.select('table.data tr > td:nth-of-type(2)')]
print(second_cells)  # ['가격', '19900', '29900']

from bs4 import BeautifulSoup

html = '''
<ul>
  <li>Learn Python with BeautifulSoup</li>
  <li>Master JavaScript Today</li>
  <li>Python Tips and Tricks</li>
</ul>
'''

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

python_items = soup.select("li:contains('Python')")
for item in python_items:
    print(item.text)

html = '''
<div class="menu">
  <a href="/intro">Introduction</a>
  <a href="/python">Python Guide</a>
  <a href="/java">Java Guide</a>
</div>
'''

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

# 'Python' 포함 링크만
python_links = soup.select("a:contains('Python')")
print([a["href"] for a in python_links])  # ['/python']

from bs4 import BeautifulSoup

html = '''
<div class="links">
  <a href="https://example.com/guide.pdf">가이드 PDF</a>
  <a href="http://blog.example.com/post/123">블로그 글</a>
  <a href="/product/sku-1001?ref=home">상품 상세</a>
  <a href="/assets/manual_v2.PDF">매뉴얼 PDF</a>
</div>
'''

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

# 1) 외부 링크(프로토콜로 시작)
external = soup.select('a[href^="http"]')

# 2) PDF 파일(확장자로 끝)
pdfs = soup.select('a[href$=".pdf"], a[href$=".PDF"]')

# 3) 상품 URL을 포함
products = soup.select('a[href*="/product/"]')

print([a.get_text(strip=True) for a in external])   # ['가이드 PDF', '블로그 글']
print([a["href"] for a in pdfs])                    # ['https://example.com/guide.pdf', '/assets/manual_v2.PDF']
print([a["href"] for a in products])                # ['/product/sku-1001?ref=home']

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

# 1) 외부 링크면서 utm 파라미터가 없는 것만
clean_external = soup.select('a[href^="http"]:not([href*="utm_"])')

# 2) 특정 도메인 집합만 허용
safe_domains = soup.select('a:is([href*="example.com"], [href*="my.site"])')

# 3) 다운로드 버튼처럼 보이는 링크만
downloads = soup.select('a.button[href$=".zip"], a.btn[href$=".tar.gz"]')