這篇文章主要介紹了Python urllib、urllib2、httplib抓取網頁代碼實例,本文直接給出demo代碼,代碼中包含詳細注釋,需要的朋友可以參考下
使用urllib2，太強大了
試了下用代理登陸拉取cookie，跳轉抓圖片......
文檔：http://docs.python.org/library/urllib2.html
直接上demo代碼了
包括：直接拉取，使用Reuqest(post/get),使用代理，cookie,跳轉處理
?
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 #!/usr/bin/python # -*- coding:utf-8 -*- # urllib2_test.py # author: wklken # 2012-03-17 [email protected] import urllib,urllib2,cookielib,socket url = "http://www.testurl....." #change yourself #最簡單方式 def use_urllib2(): try: f = urllib2.urlopen(url, timeout=5).read() except urllib2.URLError, e: print e.reason print len(f) #使用Request def get_request(): #可以設置超時 socket.setdefaulttimeout(5) #可以加入參數 [無參數，使用get，以下這種方式，使用post] params = {"wd":"a","b":"2"} #可以加入請求頭信息，以便識別 i_headers = {"User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1) Gecko/20090624 Firefox/3.5", "Accept": "text/plain"} #use post,have some params post to server,if not support ,will throw exception #req = urllib2.Request(url, data=urllib.urlencode(params), headers=i_headers) req = urllib2.Request(url, headers=i_headers) #創建request後，還可以進行其他添加,若是key重復，後者生效 #request.add_header('Accept','application/json') #可以指定提交方式 #request.get_method = lambda: 'PUT' try: page = urllib2.urlopen(req) print len(page.read()) #like get #url_params = urllib.urlencode({"a":"1", "b":"2"}) #final_url = url + "?" + url_params #print final_url #data = urllib2.urlopen(final_url).read() #print "Method:get ", len(data) except urllib2.HTTPError, e: print "Error Code:", e.code except urllib2.URLError, e: print "Error Reason:", e.reason def use_proxy(): enable_proxy = False proxy_handler = urllib2.ProxyHandler({"http":"http://proxyurlXXXX.com:8080"}) null_proxy_handler = urllib2.ProxyHandler({}) if enable_proxy: opener = urllib2.build_opener(proxy_handler, urllib2.HTTPHandler) else: opener = urllib2.build_opener(null_proxy_handler, urllib2.HTTPHandler) #此句設置urllib2的全局opener urllib2.install_opener(opener) content = urllib2.urlopen(url).read() print "proxy len:",len(content) class NoExceptionCookieProcesser(urllib2.HTTPCookieProcessor): def http_error_403(self, req, fp, code, msg, hdrs): return fp def http_error_400(self, req, fp, code, msg, hdrs): return fp def http_error_500(self, req, fp, code, msg, hdrs): return fp def hand_cookie(): cookie = cookielib.CookieJar() #cookie_handler = urllib2.HTTPCookieProcessor(cookie) #after add error exception handler cookie_handler = NoExceptionCookieProcesser(cookie) opener = urllib2.build_opener(cookie_handler, urllib2.HTTPHandler) url_login = "https://www.yourwebsite/?login" params = {"username":"user","password":"111111"} opener.open(url_login, urllib.urlencode(params)) for item in cookie: print item.name,item.value #urllib2.install_opener(opener) #content = urllib2.urlopen(url).read() #print len(content) #得到重定向 N 次以後最後頁面URL def get_request_direct(): import httplib httplib.HTTPConnection.debuglevel = 1 request = urllib2.Request("http://www.google.com") request.add_header("Accept", "text/html,*/*") request.add_header("Connection", "Keep-Alive") opener = urllib2.build_opener() f = opener.open(request) print f.url print f.headers.dict print len(f.read()) if __name__ == "__main__": use_urllib2() get_request() get_request_direct() use_proxy() hand_cookie()
