beautifulsoup 分析html文档

beatifulsoup_eg.py

#eg 1

from BeautifulSoup import BeautifulSoup
import re

html_text = """
<h2>this is cool #12345678901</h2>
<h2>this is nothing</h2>
<h2>this is interesting #126666678901</h2>
<h2>this is blah #124445678901</h2>
"""

soup = BeautifulSoup(html_text)

for elem in soup('h2', text=re.compile(r' #\S{11}')):
    print elem.parent

#result
<h2>this is cool #12345678901</h2>
<h2>this is interesting #126666678901</h2>
<h2>this is blah #124445678901</h2>





#eg2

html = urllib.urlopen('http://www.nytimes.com/2009/12/21/us/21storm.html').read()
soup = BeautifulSoup.BeautifulSoup(html)
texts = soup.findAll(text=True)

def visible(element):
    if element.parent.name in ['style', 'script', '[document]', 'head', 'title']:
        return False
    elif re.match('<!--.*-->', str(element)):
        return False
    return True

visible_texts = filter(visible, texts)