#coding=utf-8
import HTMLParser
import time
import urllib2
# 继承语法
class MyParser(HTMLParser.HTMLParser):
targetid = ''
def __init__(self,targetid):
HTMLParser.HTMLParser.__init__(self)
self.targetid = targetid
def handle_starttag(self, tag, attrs):
self.is_h4 = ""
# 这里重新定义了处理开始标签的函数
if tag == 'span':
# 判断标签<a>的属性
for name,value in attrs:
if name == 'id':
if value == self.targetid:
self.is_h4 = 1
def handle_endtag(self, tag):
self.is_h4 = -1
def handle_data(self, data):
if self.is_h4 == 1:
print "大盘指数:", data
st = time.time()
pageContent = urllib2.urlopen('https://www.google.com.hk/finance?client=ob&hl=zh-CN&q=SHA:000001').read()
my = MyParser('ref_7521596_l')
my.feed(pageContent)
end = time.time()
print '所花时间: %d 秒'%(end-st)
python读取大盘指数
最新推荐文章于 2025-02-06 16:10:22 发布