Вы можете использовать BS
с re
.
Ex:
from bs4 import BeautifulSoup
import re
html = """<div class="inside">
<a href="http://www.linkar.com">
<b>A Show</b><br/>
<img alt="A Show" height="83" src="http://www.linkar.com/679.jpg"/>
</a>
<br/>Film : Gladiator
<br/>Location : example street, London, UK
<br/>Phone : +83817447184<br/>
</div>"""
soup = BeautifulSoup(html, "html.parser")
a_show = soup.find('div', class_="inside").text
film = re.search("Film :(.*)", a_show)
if film:
print(film.group())
location = re.search("Location :(.*)", a_show)
if location:
print(location.group())
phone = re.search("Phone :(.*)", a_show)
if phone:
print(phone.group())
Выход:
Film : Gladiator
Location : example street, London, UK
Phone : +83817447184
или
content = re.findall("(Film|Location|Phone) :(.*)", a_show)
if content:
print(content)
# --> [(u'Film', u' Gladiator'), (u'Location', u' example street, London, UK'), (u'Phone', u' +83817447184')]