notes

Author: OpenNeptune

PythonStu/stu/HTML/getURL_urllib.py

@@ -4,6 +4,10 @@
 #   利用标准库urllib获取想要的HTML文件
 import urllib
 import sys
+import httplib
+
+#打开urllib的debug模式，清晰的查看http请求的过程
+httplib.HTTPConnection.debuglevel=1    
 
 #获取python.org的首页并打印
 def demo_urlopen():

PythonStu/stu/HTML/urllib2_cookie.py

@@ -0,0 +1,16 @@
+#! /usr/bin/python
+#encoding=UTF-8
+
+
+import urllib2
+import cookielib
+
+cookie = cookielib.CookieJar()
+opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
+response = opener.open('http://www.baidu.com')
+
+#debug
+print type(cookie)
+print cookie
+for item in cookie:
+    print item.name,"=>",item.value

PythonStu/stu/HTML/urllib2_debuglog.py

@@ -0,0 +1,21 @@
+#! /usr/bin/python
+#encoding=UTF-8
+
+
+import urllib2
+
+"""Open Debug Mode in urllib2"""
+
+def get_debugHandle():
+    """return debug mode handler for handler http"""
+    http_debug_handler = urllib2.HTTPHandler(debuglevel=1)
+    opener = urllib2.build_opener(http_debug_handler)
+    return opener
+
+if __name__ == "__main__":
+    opener = get_debugHandle()
+    if  opener:
+        opener.open('http://www.baidu.com')
+    else:
+        print 'init http Handler error'
+    

PythonStu/stu/HTML/urllib2_httpheader.py

@@ -0,0 +1,17 @@
+#! /usr/bin/python
+#encoding=UTF-8
+
+import urllib2
+
+url = "http://www.baidu.com"
+
+request = urllib2.Request(url)
+request.add_header('User-Agent','Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 Safari/537.36')
+http_debug_handler = urllib2.HTTPHandler(debuglevel=1)
+opener =urllib2.build_opener(http_debug_handler)
+urllib2.install_opener(opener)
+fp = urllib2.urlopen(request)
+
+
+
+

PythonStu/stu/HTML/urllib2_httpstatus.py

@@ -0,0 +1,19 @@
+#! /usr/bin/python
+#encoding=UTF-8
+
+
+import urllib2
+
+
+print "对于请求的请求可以通过response.getcode()就能获得"
+print "对于错误的请求，urllib2会抛出异常，这时可以检测异常对象的code属性"
+
+
+response = urllib2.urlopen('http://www.baidu.com')
+print response.getcode()
+
+
+try:
+    response = urllib2.urlopen('http://127.0.0.1/admin.php')
+except urllib2.HTTPError,e:
+    print e.code

PythonStu/stu/HTML/urllib2_isRedirect.py

@@ -0,0 +1,39 @@
+#! /usr/bin/python
+#encoding=UTF-8
+
+import urllib2
+def isRedirect(url):
+    """request url judge is redirect?"""
+    redirected = False
+    response = urllib2.urlopen(url)
+    redirected = response.geturl() == url
+    print 'response url',response.geturl()
+    print 'request url',url
+    return not redirected
+
+class RedirectHandler(urllib2.HTTPRedirectHandler):
+    def http_error_301(self,req,fp,code,msg,headers):
+        print req
+        print fp
+        print code
+        print msg
+        print headers
+
+    def http_error_302(self,req,fp,code,msg,headers):
+        print req
+        print fp
+        print code
+        print msg
+        print headers
+
+
+def myRedirect():
+    opener = urllib2.build_opener(RedirectHandler)
+
+    opener.open('http://www.g.cn')
+
+if __name__=="__main__":
+    print isRedirect('http://www.baidu.com')
+    print isRedirect('http://www.g.cn')
+   
+    myRedirect() 

PythonStu/stu/HTML/urllib2_proxy.py

@@ -0,0 +1,14 @@
+#! /usr/bin/python
+#encoding=UTF-8
+
+import urllib2
+    """setting http proxy"""
+
+enable_proxy = True
+proxy_handler = urllib2.ProxyHandler({'http':'http://www.proxy.org:8080'})
+if enable_proxy:
+    opener = urllib2.build_opener(proxy_handler)
+else:
+    opener = urllib2.build_opener(urllib2.ProxyHnadler({}))
+
+urllib2.install_opener(opener)