<p>这个站点是UTF-8。为什么你需要href.encode编码(“iso-8859-2”)?我从<a href="http://programming-review.com/beautifulsoasome-interesting-python-functions/" rel="nofollow">http://programming-review.com/beautifulsoasome-interesting-python-functions/</a>获取了下一个代码</p>
<pre><code> import urllib2
import cgitb
cgitb.enable()
from BeautifulSoup import BeautifulSoup
from urlparse import urlparse
# print all links
def PrintLinks(localurl):
data = urllib2.urlopen(localurl).read()
print 'Encoding of fetched HTML : %s', type(data)
soup = BeautifulSoup(data)
parse = urlparse(localurl)
localurl = parse[0] + "://" + parse[1]
print "<h3>Page links statistics</h3>"
l = soup.findAll("a", attrs={"href":True})
print "<h4>Total links count = " + str(len(l)) + '</h4>'
externallinks = [] # external links list
for link in l:
# if it's external link
if link['href'].find("http://") == 0 and link['href'].find(localurl) == -1:
externallinks = externallinks + [link]
print "<h4>External links count = " + str(len(externallinks)) + '</h4>'
if len(externallinks) > 0:
print "<h3>External links list:</h3>"
for link in externallinks:
if link.text != '':
print '<h5>' + link.text.encode('utf-8')
print ' => [' + '<a href="' + link['href'] + '" >' + link['href'] + '</a>' + ']' + '</h5>'
else:
print '<h5>' + '[image]',
print ' => [' + '<a href="' + link['href'] + '" >' + link['href'] + '</a>' + ']' + '</h5>'
PrintLinks( "http://www.zlatestranky.cz/pro-mobily/")
</code></pre>