I wrote some stupid code for learning just, but it doesn't work for any sites.
here is the code:
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')
The most strange thing is it works for site:
http://habrahabr.ru
http://5pd.ru
But doesn't work for most others that I've checked.
解决方案
You're making it far more complicated than it needs to be. Here's a simple way to do it:
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())