一个可从HTML页面中提取标题、内容、图像的可读解析器
jparser的Python项目详细描述
import urllib2 from jparser import PageModel html = urllib2.urlopen("http://news.sohu.com/20170512/n492734045.shtml").read().decode('gb18030') pm = PageModel(html) result = pm.extract() print "==title==" print result['title'] print "==content==" for x in result['content']: if x['type'] == 'text': print x['data'] if x['type'] == 'image': print "[IMAGE]", x['data']['src']