1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
|
def (link):
po = urlparse(link)
file_url = '{scheme}://{netloc}/favicon.ico'.format(scheme=po.scheme, netloc=po.netloc)
favicon_name = 'favicon/{url}_favicon.ico'.format(url=po.netloc.replace('.', '_'))
file_path = '{root}/{name}'.format(root=settings.MEDIA_ROOT, name=favicon_name)
print(file_url, file_path)
r = requests.get(file_url, stream=True)
if r.status_code == 200:
with open(file_path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
return favicon_name
elif r.status_code == 404:
page = requests.get(link)
print(page.text)
soup = BeautifulSoup(page.text)
icon_link = soup.find("link", rel="shortcut icon")
if not icon_link:
icon_link = soup.find("link", rel="icon")
if icon_link:
print(icon_link['href'])
icon_src = icon_link['href']
if not icon_link['href'].startswith('http'):
icon_src = urljoin(link, icon_src)
r2 = requests.get(icon_src, stream=True)
if r2.status_code == 200:
with open(file_path, 'wb') as f:
r2.raw.decode_content = True
shutil.copyfileobj(r2.raw, f)
return favicon_name
|
近期评论