Day 88 - web scraping (1)

ksyke 2024. 12. 3. 17:52

116p~

https://www.crummy.com/software/BeautifulSoup/bs4/doc/#bs4.Tag

Beautiful Soup Documentation — Beautiful Soup 4.12.0 documentation

Beautiful Soup Documentation Beautiful Soup is a Python library for pulling data out of HTML and XML files. It works with your favorite parser to provide idiomatic ways of navigating, searching, and modifying the parse tree. It commonly saves programmers h

www.crummy.com

from urllib.request import Request
import urllib.request

msg='https://m.naver.com/'
with(
    urllib.request.urlopen(msg) as f,
    open('data2.csv','w') as fw
    ):
        print(bytes.decode(f.read(),'utf-8'))

import requests
requests.get('http://m.naver.com').text

import requests

requests.get('http://m.naver.com').text

html_doc = """
<html>
<head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>

<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>

<p class="story">...</p>
</body>
</html>
"""

from bs4 import BeautifulSoup

# soup=BeautifulSoup(html_doc,'html_parser')
soup=BeautifulSoup(html_doc)

soup.prettify()

soup.title

soup.a

soup.find_all('a')

soup.find(id='link2')

soup.p['class']

soup.find_all('p',{'class':'story'})

soup.a.get_text()

soup.p.get_text()

# soup.find_all('p',{'class':'story'})[0].get_text()
str(soup.find_all('p',{'class':'story'})[0].get_text())

soup.p.string.replace_with('edit')

soup.prettify()

soup.body.contents

soup.body.contents[3].contents[0]

list(soup.body.children)