【轉】擷取新聞和連結

一 存入隊列

import urllib.requestimport queueimport req = queue.Queue()headers = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}url = "http://news.163.com/rank/"url = urllib.request.Request(url , headers = headers)data = urllib.request.urlopen(url).read()data = data.decode('GBK')newlist=[]newlist = re.compile(r'</span><a href="(.*?)">(.*?)</a>',re.DOTALL).findall(data)Length = len(newlist)for i in range(0, Length):    q.put(newlist[i])while not q.empty():    print(q.get())

二 儲存本地

import urllib.request  import reheaders = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}url = "http://news.163.com/rank/"url = urllib.request.Request(url , headers = headers)data = urllib.request.urlopen(url).read()  data = data.decode('GBK')newlist=[]  newlist = re.compile(r'</span><a href="(.*?)">(.*?)</a>',re.DOTALL).findall(data)Length = len(newlist)  for i in range(0, Length):      print("NEW%d:%s\n"%(i+1, newlist[i]))    file_object = open("news.txt","a")    file_object.write("%s\n"% newlist)    file_object.close()