>>> import html2text
>>>
>>> print(html2text.html2text("<p><strong>Zed's</strong> dead baby, <em>Zed's</em> dead.</p>"))
**Zed's** dead baby, _Zed's_ dead.

>>> import html2text
>>>
>>> h = html2text.HTML2Text()
>>> # Ignore converting links from HTML
>>> h.ignore_links = True
>>> print h.handle("<p>Hello, <a href='http://earth.google.com/'>world</a>!")
Hello, world!

>>> print(h.handle("<p>Hello, <a href='http://earth.google.com/'>world</a>!"))

Hello, world!

>>> # Don't Ignore links anymore, I like links
>>> h.ignore_links = False
>>> print(h.handle("<p>Hello, <a href='http://earth.google.com/'>world</a>!"))
Hello, [world](http://earth.google.com/)!

import urllib
from bs4 import BeautifulSoup

url = "http://news.bbc.co.uk/2/hi/health/2284783.stm"
html = urllib.urlopen(url).read()
soup = BeautifulSoup(html)

# kill all script and style elements
for script in soup(["script", "style"]):
    script.extract()    # rip it out

# get text
text = soup.get_text()

# break into lines and remove leading and trailing space on each
lines = (line.strip() for line in text.splitlines())
# break multi-headlines into a line each
chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
# drop blank lines
text = '\n'.join(chunk for chunk in chunks if chunk)

print(text)