python使用pycurl模块详解

1. #!/usr/bin/env python2
   
2. #encoding=utf8
   
3. import pycurl
   
4. import StringIO
   
5. # 安装pycurl到http://pycurl.sourceforge.net/这里去找.
   
6. # 在windows安装的话http://pycurl.sourceforge.net/download/ , 看你使用的版本决定下载那个，我在 windows使用的是python2.4, 所以下载 pycurl-ssl-7.15.5.1.win32-py2.4.exe 。
   
7. def test(debug_type, debug_msg):
   
8. print "debug(%d): %s" % (debug_type, debug_msg)
   
9. def postFile(url,post_file):
   
10. #print pycurl.version_info()
    
11. #这个函数创建一个同 libcurl中的CURL处理器相对应的Curl对象.Curl对象自动的设置CURLOPT_VERBOSE为0, CURLOPT_NOPROGRESS为1,提供一个默认的CURLOPT_USERAGENT和设置CURLOPT_ERRORBUFFER指向一个私有的错误缓冲区.
    
12. c = pycurl.Curl() #创建一个同libcurl中的CURL处理器相对应的Curl对象
    
13. b = StringIO.StringIO()
    
14. #c.setopt(c.POST, 1)
    
15. c.setopt(pycurl.URL, url) #设置要访问的网址 url = "http://www.cnn.com"
    
16. #写的回调
    
17. c.setopt(pycurl.WRITEFUNCTION, b.write)
    
18. c.setopt(pycurl.FOLLOWLOCATION, 1) #参数有1、2
    
19. #最大重定向次数,可以预防重定向陷阱
    
20. c.setopt(pycurl.MAXREDIRS, 5)
    
21. #连接超时设置
    
22. c.setopt(pycurl.CONNECTTIMEOUT, 60) #链接超时
    
23. # c.setopt(pycurl.TIMEOUT, 300) #下载超时
    
24. # c.setopt(pycurl.HEADER, True)
    
25. # c.setopt(c.HTTPHEADER, ["Content-Type: application/x-www-form-urlencoded","X-Requested-With:XMLHttpRequest","Cookie:"+set_cookie[0]])
    
26. #模拟浏览器
    
27. c.setopt(pycurl.USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)")
    
28. # c.setopt(pycurl.AUTOREFERER,1)
    
29. # c.setopt(c.REFERER, url)
    
30. # cookie设置
    
31. # Option -b/--cookie <name=string/file> Cookie string or file to read cookies from
    
32. # Note: must be a string, not a file object.
    
33. # c.setopt(pycurl.COOKIEFILE, "cookie_file_name")
    
34. # Option -c/--cookie-jar Write cookies to this file after operation
    
35. # Note: must be a string, not a file object.
    
36. # c.setopt(pycurl.COOKIEJAR, "cookie_file_name")
    
37. # Option -d/--data HTTP POST data
    
38. post_data_dic = {"name":"value"}
    
39. c.setopt(c.POSTFIELDS, urllib.urlencode(post_data_dic))
    
40. #设置代理
    
41. # c.setopt(pycurl.PROXY, ‘http://11.11.11.11:8080′)
    
42. # c.setopt(pycurl.PROXYUSERPWD, ‘aaa:aaa’)
    
43. #不明确作用
    
44. # c.setopt(pycurl.HTTPPROXYTUNNEL,1) #隧道代理
    
45. # c.setopt(pycurl.NOSIGNAL, 1)
    
46. #设置post请求， 上传文件的字段名 上传的文件
    
47. #post_file = "/home/ubuntu/avatar.jpg"
    
48. c.setopt(c.HTTPPOST, [("textname", (c.FORM_FILE, post_file))])
    
49. # 调试回调.调试信息类型是一个调试信 息的整数标示类型.在这个回调被调用时VERBOSE选项必须可用
    
50. # c.setopt(c.VERBOSE, 1) #verbose 详细
    
51. # c.setopt(c.DEBUGFUNCTION, test)
    
52. # f = open("body", "wb")
    
53. # c.setopt(c.WRITEDATA, f)
    
54. # h = open("header", "wb")
    
55. # c.setopt(c.WRITEHEADER, h)
    
56. # print "Header is in file 'header', body is in file 'body'"
    
57. # f.close()
    
58. # h.close()
    
59. # c.setopt(c.NOPROGRESS, 0)
    
60. # c.setopt(c.PROGRESSFUNCTION, progress)
    
61. # c.setopt(c.OPT_FILETIME, 1)
    
62. #访问,阻塞到访问结束
    
63. c.perform() #执行上述访问网址的操作
    
64. print "HTTP-code:", c.getinfo(c.HTTP_CODE) #打印出 200(HTTP状态码)
    
65. print "Total-time:", c.getinfo(c.TOTAL_TIME)
    
66. print "Download speed: %.2f bytes/second" % c.getinfo(c.SPEED_DOWNLOAD)
    
67. print "Document size: %d bytes" % c.getinfo(c.SIZE_DOWNLOAD)
    
68. print "Effective URL:", c.getinfo(c.EFFECTIVE_URL)
    
69. print "Content-type:", c.getinfo(c.CONTENT_TYPE)
    
70. print "Namelookup-time:", c.getinfo(c.NAMELOOKUP_TIME)
    
71. print "Redirect-time:", c.getinfo(c.REDIRECT_TIME)
    
72. print "Redirect-count:", c.getinfo(c.REDIRECT_COUNT)
    
73. # epoch = c.getinfo(c.INFO_FILETIME)
    
74. #print "Filetime: %d (%s)" % (epoch, time.ctime(epoch))
    
75. html = b.getvalue()
    
76. print(html)
    
77. b.close()
    
78. c.close()