#coding=utf-8 import sys import requests reload(sys) sys.setdefaultencoding('utf-8') headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.87 Safari/537.36', 'Accept-Language':'zh-CN,zh;q=0.8', 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', 'Referer':'http://www.itaotm.com/search.php?seat=%E7%94%B3%E8%AF%B7%E4%BA%BA&searchKey=%E5%8C%97%E4%BA%AC', 'Upgrade-Insecure-Requests':'1'} session=requests.session() def get_detailpage(): url='http://www.itaotm.com/search!page.php?pageNo=1&l=20161019113636&gjfls=1%3B2%3B3%3B4%3B5%3B6%3B7%3B8%3B9%3B10%3B11%3B12%3B13%3B14%3B15%3B16%3B17%3B18%3B19%3B20%3B21%3B22%3B23%3B24%3B25%3B26%3B27%3B28%3B29%3B30%3B31%3B32%3B33%3B34&gjfl=0&seat=%E7%94%B3%E8%AF%B7%E4%BA%BA&searchKey=%E5%8C%97%E4%BA%AC' data={'pageNo':'1','l':'20161019113636','gjfls':'1%3B2%3B3%3B4%3B5%3B6%3B7%3B8%3B9%3B10%3B11%3B12%3B13%3B14%3B15%3B16%3B17%3B18%3B19%3B20%3B21%3B22%3B23%3B24%3B25%3B26%3B27%3B28%3B29%3B30%3B31%3B32%3B33%3B34', 'gjfl':'0','seat':'%E7%94%B3%E8%AF%B7%E4%BA%BA','searchKey':'%E5%8C%97%E4%BA%AC'} html=session.get(url=url,headers=headers,params=data) print html.text get_detailpage()
在填好搜索条件后,点击查询,页面上会显示要几秒后才能出结果,然后直接出现结果的页面。爬取的网址是最后出现结果的网址,但爬取到的内容会出现:
<div class="cls"></div> <div class="mainBox"> <div class="jump"> 数据量巨大,正在努力查询中.... 预计<span id="jumpTo">5</span>秒后出结果 </div> <div class="cls"></div> </div>
并不是想要的最终结果,怎么才能爬取到正确结果呢?不用selenium的话