python-爬网页

Posted 2020-10-17 巅峰之斗

import gevent
from urllib.request import urlopen


# 爬虫
def f(url):
    print(‘GET: %s‘ % url)
    resp = urlopen(url)
    data = resp.read()

    with open(‘baidu.html‘, ‘wb‘) as f:
        f.write(data)

    print(‘%d bytes %s‘ % (len(data), url))


# f(‘http://www.xiaohuar.com/‘)
f(‘http://www.baidu.com/‘)


# gevent.joinall([
#
#     gevent.spawn(f, ‘https://www.python.org/‘),
#     gevent.spawn(f, ‘https://www.yahoo.com/‘),
#
# ])