urllib2 尝试并排除 404

Question

我正在尝试使用 urlib2 浏览一系列编号的数据页。我想做的是使用 try 语句，但我对它知之甚少，通过阅读一点来看，它似乎是基于异常的特定“名称”，例如 IOError 等。我不知道什么错误代码是我正在寻找的，这是问题的一部分。

我已经从“urllib2 缺失的手册”中编写/粘贴了我的 urllib2 页面获取例程：

def fetch_page(url,useragent)
    urlopen = urllib2.urlopen
    Request = urllib2.Request
    cj = cookielib.LWPCookieJar()

    txheaders =  {'User-agent' : useragent}

    if os.path.isfile(COOKIEFILE):
        cj.load(COOKIEFILE)
        print "previous cookie loaded..."
    else:
        print "no ospath to cookfile"

    opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
    urllib2.install_opener(opener)
    try:
        req = urllib2.Request(url, useragent)
        # create a request object

        handle = urlopen(req)
        # and open it to return a handle on the url

    except IOError, e:
        print 'Failed to open "%s".' % url
        if hasattr(e, 'code'):
            print 'We failed with error code - %s.' % e.code
        elif hasattr(e, 'reason'):
            print "The error object has the following 'reason' attribute :"
            print e.reason
            print "This usually means the server doesn't exist,",
            print "is down, or we don't have an internet connection."
            return False

    else:
        print
        if cj is None:
            print "We don't have a cookie library available - sorry."
            print "I can't show you any cookies."
        else:
            print 'These are the cookies we have received so far :'
            for index, cookie in enumerate(cj):
                print index, '  :  ', cookie
                cj.save(COOKIEFILE)           # save the cookies again

        page = handle.read()
        return (page)

def fetch_series():

  useragent="Firefox...etc."
  url="www.example.com/01.html"
  try:
    fetch_page(url,useragent)
  except [something]:
    print "failed to get page"
    sys.exit()

底部函数只是一个例子，看看我的意思，谁能告诉我应该放在那里什么？我让页面获取函数在收到 404 错误时返回 False，这是正确的吗？那么为什么 except False: 不起作用呢？感谢您提供的任何帮助。

好吧，按照我尝试过的建议：

except urlib2.URLError, e:

except URLError, e:

except URLError:

except urllib2.IOError, e:

except IOError, e:

except IOError:

except urllib2.HTTPError, e:

except urllib2.HTTPError:

except HTTPError:

它们都不起作用。

Answer 1

如果你想检测 404，你应该捕获 urllib2.HTTPError：

try:
    req = urllib2.Request(url, useragent)
    # create a request object

    handle = urllib2.urlopen(req)
    # and open it to return a handle on the url
except urllib2.HTTPError, e:
    print 'We failed with error code - %s.' % e.code

    if e.code == 404:
        # do stuff..  
    else:
        # other stuff...

    return False
else:
    # ...

---

要在 fetch_series() 中捕获它：

def fetch_page(url,useragent)
    urlopen = urllib2.urlopen
    Request = urllib2.Request
    cj = cookielib.LWPCookieJar()
    try:
        urlopen()
        #...
    except IOError, e:
        # ...   
    else:
        #...

def fetch_series(): 
    useragent=”Firefox...etc.”
    url=”www.example.com/01.html
    try:
        fetch_page(url,useragent)
    except urllib2.HTTPError, e:
        print “failed to get page”

http://docs.python.org/library/urllib2.html：

异常 urllib2.HTTPError
尽管是一个异常（URLError 的子类），HTTPError 可以
也可用作非异常的类似文件的返回值（相同
urlopen() 返回的东西）。这在处理异国情调时很有用
HTTP 错误，例如身份验证请求。

代码
RFC 2616 中定义的 HTTP 状态代码。该数值对应于在代码字典中找到的值
在BaseHTTPServer.BaseHTTPRequestHandler.responses中。

Answer 2

我建议您查看精彩的 requests 模块。

有了它，您可以实现您所要求的功能，如下所示：

import requests
from requests.exceptions import HTTPError

try:
    r = requests.get('http://httpbin.org/status/200')
    r.raise_for_status()
except HTTPError:
    print 'Could not download page'
else:
    print r.url, 'downloaded successfully'

try:
    r = requests.get('http://httpbin.org/status/404')
    r.raise_for_status()
except HTTPError:
    print 'Could not download', r.url
else:
    print r.url, 'downloaded successfully'

Answer 3

交互式戳：

要了解 python 中此类异常的性质和可能的内容，最好只需交互式地尝试关键调用：

>>> f = urllib2.urlopen('http://httpbin.org/status/404')
Traceback (most recent call last):
...
  File "C:\Python27\lib\urllib2.py", line 558, in http_error_default
    raise HTTPError(req.get_full_url(), code, msg, hdrs, fp)
HTTPError: HTTP Error 404: NOT FOUND

然后 sys.last_value 包含下降到交互式的异常值 - 并且可以是玩过：
（使用 TAB + 。交互式 shell 的自动扩展、dir()、vars() ...）

>>> ev = sys.last_value
>>> ev.__class__
<class 'urllib2.HTTPError'>
>>> dir(ev)
['_HTTPError__super_init', '__class__', '__delattr__', '__dict__', '__doc__', '__format__', '__getattribute__', '__getitem__', '__getslice__', '__hash__', '__init__', '__iter__', '__module__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__setstate__', '__sizeof__', '__str__', '__subclasshook__', '__unicode__', '__weakref__', 'args', 'close', 'code', 'errno', 'filename', 'fileno', 'fp', 'getcode', 'geturl', 'hdrs', 'headers', 'info', 'message', 'msg', 'next', 'read', 'readline', 'readlines', 'reason', 'strerror', 'url']
>>> vars(ev)
{'fp': <addinfourl at 140193880 whose fp = <socket._fileobject object at 0x01062370>>, 'fileno': <bound method _fileobject.fileno of <socket._fileobject object at 0x01062370>>, 'code': 404, 'hdrs': <httplib.HTTPMessage instance at 0x085ADF80>, 'read': <bound method _fileobject.read of <socket._fileobject object at 0x01062370>>, 'readlines': <bound method _fileobject.readlines of <socket._fileobject object at 0x01062370>>, 'next': <bound method _fileobject.next of <socket._fileobject object at 0x01062370>>, 'headers': <httplib.HTTPMessage instance at 0x085ADF80>, '__iter__': <bound method _fileobject.__iter__ of <socket._fileobject object at 0x01062370>>, 'url': 'http://httpbin.org/status/404', 'msg': 'NOT FOUND', 'readline': <bound method _fileobject.readline of <socket._fileobject object at 0x01062370>>}
>>> sys.last_value.code
404

尝试处理：

>>> try: f = urllib2.urlopen('http://httpbin.org/status/404')
... except urllib2.HTTPError, ev:
...     print ev, "'s error code is", ev.code
...     
HTTP Error 404: NOT FOUND 's error code is 404

---

构建一个不会引发 HTTP 错误的简单开启器：

>>> ho = urllib2.OpenerDirector()
>>> ho.add_handler(urllib2.HTTPHandler())
>>> f = ho.open('http://localhost:8080/cgi/somescript.py'); f
<addinfourl at 138851272 whose fp = <socket._fileobject object at 0x01062370>>
>>> f.code
500
>>> f.read()
'Execution error: <pre style="background-color:#faa">\nNameError: name \'e\' is not defined\n<pre>\n'

---

urllib2.build_opener< 的默认处理程序/代码>：

default_classes = [ProxyHandler、UnknownHandler、HTTPHandler、
HTTPDefaultErrorHandler、HTTPRedirectHandler、
FTPHandler、FileHandler、HTTPErrorProcessor]