Python BeautifulSoup库的高级特性详解

from bs4 import BeautifulSoup
html_doc = """
<div class="article">
    <h1 class="title">Article Title</h1>
    <p class="content">This is the content of the article.</p>
</div>
"""
soup = BeautifulSoup(html_doc, 'html.parser')
title = soup.select_one('.title').get_text()
content = soup.select_one('.content').get_text()
print('Title: ', title)
print('Content: ', content)

from bs4 import BeautifulSoup
html_doc = """
<div class="article"
    <h1 class="title">Article Title</h1>
    <p class="content">This is the content of the article.</p>
</div>
"""
soup = BeautifulSoup(html_doc, 'html.parser')
print(soup.prettify())

from bs4 import BeautifulSoup
xml_doc = """
<root>
    <![CDATA[
        <div>
            <p>This is a paragraph.</p>
        </div>
    ]]>
</root>
"""
soup = BeautifulSoup(xml_doc, 'lxml-xml')
cdata = soup.find_all(string=lambda text: isinstance(text, CData))
print(cdata)

from bs4 import BeautifulSoup
html_doc = """
<div class="article">
    <!-- This is a comment. -->
    <h1 class="title">Article Title</h1>
    <p class="content">This is the content of the article.</p>
</div>
"""
soup = BeautifulSoup(html_doc, 'html.parser')
comments = soup.find_all(string=lambda text: isinstance(text, Comment))
for comment in comments:
    print(comment)