python-hard-way/Misc. learning/python-parse-html.py

48 lines
1.3 KiB
Python

# import SimpleHTTPServer
# import SocketServer
#
# PORT = 8000
#
# Handler = SimpleHTTPServer.SimpleHTTPRequestHandler
#
# httpd = SocketServer.TCPServer(("", PORT), Handler)
#
# print("serving at port", PORT)
# httpd.serve_forever()
from bs4 import BeautifulSoup
# import urllib.request
#
# url = "https://google.com/"
#
# yo = urllib.request.urlopen(url)
# soup = BeautifulSoup(url.read(), 'html.parser')
# print(soup)
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>
"""
soup = BeautifulSoup(html_doc, 'html.parser')
print(soup.prettify())
print("\n")
print(str(soup.title) + "\n")
print(str(soup.title.name) + "\n")
print(str(soup.title.string) + "\n")
print(str(soup.title.parent.name) + "\n")
print(str(soup.p) + "\n")
print(str(soup.p['class']) + "\n")
print(str(soup.a) + "\n")
print(str(soup.find_all('a')) + "\n")
print(str(soup.find(id="link3")) + "\n")