http错误：
import urllib.request
req = urllib.request.Request(‘http://www.python.org/fish.html’)
try:
urllib.request.urlopen(req)
except urllib.error.HTTPError as e:
print(e.code)
print(e.read().decode(“utf8”))
异常处理1：
from urllib.request import Request, urlopen
from urllib.error import URLError, HTTPError
req = Request(“http://twitter.com/”)
try:
response = urlopen(req)
except HTTPError as e:
print(‘The server couldn\’t fulfill the request.’)
print(‘Error code: ‘, e.code)
except URLError as e:
print(‘We failed to reach a server.’)
print(‘Reason: ‘, e.reason)
else:
print(“good!”)
print(response.read().decode(“utf8”))
异常处理2：
from urllib.request import Request, urlopen
from urllib.error import URLError
req = Request(“http://twitter.com/”)
try:
response = urlopen(req)
except URLError as e:
if hasattr(e, ‘reason’):
print(‘We failed to reach a server.’)
print(‘Reason: ‘, e.reason)
elif hasattr(e, ‘code’):
print(‘The server couldn\’t fulfill the request.’)
print(‘Error code: ‘, e.code)
else:
print(“good!”)
print(response.read().decode(“utf8”))
http认证：
import urllib.request
# create a password manager
password_mgr = urllib.request.HTTPPasswordMgrWithDefaultRealm()
# Add the username and password.
# If we knew the realm, we could use it instead of None.
top_level_url = “https://cms.tetx.com/”
password_mgr.add_password(None, top_level_url, ‘yzhang’, ‘cccddd’)
handler = urllib.request.HTTPBasicAuthHandler(password_mgr)
# create “opener” (OpenerDirector instance)
opener = urllib.request.build_opener(handler)
# use the opener to fetch a URL
a_url = “https://cms.tetx.com/”
x = opener.open(a_url)
print(x.read())
# Install the opener.
# Now all calls to urllib.request.urlopen use our opener.
urllib.request.install_opener(opener)
a = urllib.request.urlopen(a_url).read().decode(‘utf8’)
print(a)
代理设置：
import urllib.request
proxy_support = urllib.request.ProxyHandler({‘sock5’: ‘localhost:1080’})
opener = urllib.request.build_opener(proxy_support)
urllib.request.install_opener(opener)
a = urllib.request.urlopen(“http://g.cn”).read().decode(“utf8”)
print(a)
Timeout的设置
上一节已经说过urlopen方法了，第三个参数就是timeout的设置，可以设置等待多久超时，为了解决一些网站实在响应过慢而造成的影响。
例如下面的代码,如果第二个参数data为空那么要特别指定是timeout是多少，写明形参，如果data已经传入，则不必声明。
import urllib.request
data=urllib.request.urlopen(“url”,timeout=10)
data=urllib.request.urlopen(“url”,data,10)
