python - 如何使用漂亮的汤和python获取favicon

Question

我写了一些愚蠢的代码只是为了学习，但它对任何网站都不起作用。这是代码:

import urllib2, re
from BeautifulSoup import BeautifulSoup as Soup

class Founder:
    def Find_all_links(self, url):
        page_source = urllib2.urlopen(url)
        a = page_source.read()
        soup = Soup(a)

        a = soup.findAll(href=re.compile(r'/.a\w+'))
        return a
    def Find_shortcut_icon (self, url):
        a = self.Find_all_links(url)
        b = ''
        for i in a:
            strre=re.compile('shortcut icon', re.IGNORECASE)
            m=strre.search(str(i))
            if m:
                b = i["href"]
        return b
    def Save_icon(self, url):
        url = self.Find_shortcut_icon(url)
        print url
        host = re.search(r'[0-9a-zA-Z]{1,20}\.[a-zA-Z]{2,4}', url).group()
        opener = urllib2.build_opener()
        icon = opener.open(url).read()
        file = open(host+'.ico', "wb")
        file.write(icon)
        file.close()
        print '%s icon successfully saved' % host
c = Founder()
print c.Save_icon('http://lala.ru')

最奇怪的是它适用于网站: http://habrahabr.ru http://5pd.ru

但不适用于我检查过的大多数其他人。

Answer 1

你让它变得比需要的复杂得多。这是一个简单的方法:

import urllib
page = urllib.urlopen("http://5pd.ru/")
soup = BeautifulSoup(page)
icon_link = soup.find("link", rel="shortcut icon")
icon = urllib.urlopen(icon_link['href'])
with open("test.ico", "wb") as f:
    f.write(icon.read())