使用美丽汤按类名获取内容

试试这个，也许对于这个简单的事情来说太多了，但是它起作用了：

def match_class(target):    target = target.split()    def do_match(tag):        try: classes = dict(tag.attrs)["class"]        except KeyError: classes = ""        classes = classes.split()        return all(c in classes for c in target)    return do_matchhtml = """<div ><div ><div ><span>The actual data is some where here</span></div></div></div>"""from BeautifulSoup import BeautifulSoupsoup = BeautifulSoup(html)matches = soup.findAll(match_class("feeditemcontent cxfeeditemcontent"))for m in matches:    print m    print "-"*10matches = soup.findAll(match_class("feeditembody"))for m in matches:    print m    print "-"*10