技術標籤：爬蟲python

獲取網頁的標題：

from urllib.request import urlopen
from urllib.error import URLError
from bs4 import BeautifulSoup


def get_title(url):
    try:
        html = urlopen(url)
    except URLError as e:
        return None
    try:
        bs = BeautifulSoup(html.read(), 'html.parser')
        title =
 
 bs.body.h1
    except AttributeError as e:
        return None
    return title


my_title = get_title('https://www.alibabacloud.com/zh/'
                     'knowledge/what-is-cloud-computing?spm=a3c0i.243649.2033761600.2.a974d9130g0iYV')
if my_title is None:
    print('Title could not be found.')
else:
    print
 
(my_title)