#-*-coding:utf8-*-import reimport stringimport sysimport osimport urllibimport urllib2from bs4 import BeautifulSoupimport requestsfrom lxml import etreereload(sys) sys.setdefaultencoding('utf-8')if(len(sys.argv)>=2):  user_id = (int)(sys.argv[1])else:  user_id = (int)(raw_input(u"請輸入user_id: "))cookie = {"Cookie": "#your cookie"}url = 'http://weibo.cn/u/%d?filter=1&page=1'%user_idhtml = requests.get(url, cookies = cookie).contentselector = etree.HTML(html)pageNum = (int)(selector.xpath('//input[@name="mp"]')[0].attrib['value'])result = "" urllist_set = set()word_count = 1image_count = 1print u'爬蟲準備就緒...'for page in range(1,pageNum+1): #獲取lxml頁面 url = 'http://weibo.cn/u/%d?filter=1&page=%d'%(user_id,page)  lxml = requests.get(url, cookies = cookie).content #文字爬取 selector = etree.HTML(lxml) content = selector.xpath('//span[@class="ctt"]') for each in content:  text = each.xpath('string(.)')  if word_count>=4:   text = "%d :"%(word_count-3) +text+"/n/n"  else :   text = text+"/n/n"  result = result + text  word_count += 1 #圖片爬取 soup = BeautifulSoup(lxml, "lxml") urllist = soup.find_all('a',href=re.compile(r'^http://weibo.cn/mblog/oripic',re.I)) first = 0 for imgurl in urllist:  urllist_set.add(requests.get(imgurl['href'], cookies = cookie).url)  image_count +=1fo = open("/Users/Personals/%s"%user_id, "wb")fo.write(result)word_path=os.getcwd()+'/%d'%user_idprint u'文字微博爬取完畢'link = ""fo2 = open("/Users/Personals/%s_imageurls"%user_id, "wb")for eachlink in urllist_set: link = link + eachlink +"/n"fo2.write(link)print u'圖片鏈接爬取完畢'if not urllist_set: print u'該頁面中不存在圖片'else: #下載圖片,保存在當前目錄的pythonimg文件夾下 image_path=os.getcwd()+'/weibo_image' if os.path.exists(image_path) is False:  os.mkdir(image_path) x=1 for imgurl in urllist_set:  temp= image_path + '/%s.jpg' % x  print u'正在下載第%s張圖片' % x  try:   urllib.urlretrieve(urllib2.urlopen(imgurl).geturl(),temp)  except:   print u"該圖片下載失敗:%s"%imgurl  x+=1print u'原創微博爬取完畢，共%d條，保存路徑%s'%(word_count-4,word_path)print u'微博圖片爬取完畢，共%d張，保存路徑%s'%(image_count-1,image_path)