004. using basic of BeautifulSoup
<![CDATA[
@
beauty.py
from bs4 import BeautifulSoup
# BeautifulSoup analyzes and parses html and xml
# Suppose we have following html code
html="""
<html>
<body>
<div id="meigen">
<h1>Wikibooks</h1>
<ul class="items art it book">
<li>Unity</li>
<li>Swift</li>
<li>Website</li>
</ul>
</div>
</body>
</html>
"""
# I create BeautifulSoup instance
# html : html code
# Kind of parser(this one parses html)
soup = BeautifulSoup(html, "html.parser")
# below 'ul.items', select all(descendant) 'li'
list_items = soup.select("ul.items > li")
# soup.select("ul.items li")
# soup.select("li")
# < <li>Unity</li>
# < <li>Swift</li>
# < <li>Website</li>
# Let's select <h1>Wikibooks</h1>
header = soup.select_one("body > div > h1")
# Let's use extracted data
print(header.string)
# < Wikibooks
# This one is dictionary type
# header.attrs['title']
print(soup.select_one("ul").attrs)
# < {'class': ['items', 'art', 'it', 'book']}
for li in list_items:
print(li.string)
# < Unity
# < Swift
# < Website
@
# Why should we extract parts from html by using BeautifulSoup?
# It's because all web pages are built by html
@
# The most used methods are "select()" and "select_one()"
# which are used along with CSS selectors
# I select specific tag with specific tag name
# If I want to select <ul></ul>, I need to input "ul"
# This is tag selector in BeautifulSoup : "ul", "div", "li", ...
@
<div id="meigen">
# Id selector : #meigen
# class selector : .items
# If element has multiple classes like <ul class = "items art it book">
# if you want to select element with multiple clases, you can use .item.it
@
<ul class="items art it book">
<li>Unity</li>
<li>Swift</li>
<li>Website</li>
</ul>
# "ul.book.items"
# < <li>Unity</li>
# < <li>Swift</li>
# < <li>Website</li>
# tag + class selection pattern like "ul.book" is most used
# If summany,
# 1. tag selector
# "h1"
# "html"
# 1. id selector
# "#meigen"
# 1. class selector
# ".book"
@
# Let's talk about structure selector
<html>
<body>
<div id="meigen">
<h1>Wikibooks</h1>
<ul class="items art it book">
<li>Unity</li>
<li>Swift</li>
<li>Website</li>
</ul>
</div>
</body>
</html>
# 1. descendant selector : all elements under every indent below a specific tag
# 1. child selector : all elements under one indent below a specific tag
# descendant of <html> is
<body>
<div id="meigen">
<h1>Wikibooks</h1>
<ul class="items">
<li>Unity</li>
<li>Swift</li>
<li>Website</li>
</ul>
</div>
</body>
# child of <html> : <body>
<body>
</body>
@
# descendant selector (all elements under every indent)
# "html li" means below html, select its descendant li
# <li>Unity</li>
# <li>Swift</li>
# <li>Website</li>
# "#meigen li" : below #meigen, select its descendant li
# <li>Unity</li>
# <li>Swift</li>
# <li>Website</li>
@
# child selector (all elements under one indent)
# "ul.items > li" : below ul.items, select its child li
# <li>Unity</li>
# <li>Swift</li>
# <li>Website</li>
]]>