使用urllib2,太強(qiáng)大了
試了下用代理登陸拉取cookie,跳轉(zhuǎn)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(zhuǎn)處理
#!/usr/bin/python # -*- coding:utf-8 -*- # urllib2_test.py # author: wklken # 2012-03-17 wklken@yeah.net import urllib,urllib2,cookielib,socket url = "http://www.testurl....." #change yourself #最簡(jiǎn)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(shè)置超時(shí) socket.setdefaulttimeout(5) #可以加入?yún)?shù) [無(wú)參數(shù),使用get,以下這種方式,使用post] params = {"wd":"a","b":"2"} #可以加入請(qǐng)求頭信息,以便識(shí)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(chuàng)建request后,還可以進(jìn)行其他添加,若是key重復(fù),后者生效 #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(shè)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 次以后最后頁(yè)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()
更多文章、技術(shù)交流、商務(wù)合作、聯(lián)系博主
微信掃碼或搜索:z360901061

微信掃一掃加我為好友
QQ號(hào)聯(lián)系: 360901061
您的支持是博主寫(xiě)作最大的動(dòng)力,如果您喜歡我的文章,感覺(jué)我的文章對(duì)您有幫助,請(qǐng)用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧,狠狠點(diǎn)擊下面給點(diǎn)支持吧,站長(zhǎng)非常感激您!手機(jī)微信長(zhǎng)按不能支付解決辦法:請(qǐng)將微信支付二維碼保存到相冊(cè),切換到微信,然后點(diǎn)擊微信右上角掃一掃功能,選擇支付二維碼完成支付。
【本文對(duì)您有幫助就好】元
