初学python，使用python抓取某网页的信息

# -*- coding: utf-8 -*-

#引入包

importsys

importchardet

importurllib2

frombs4importBeautifulSoup

#转换编码

reload(sys)

sys.setdefaultencoding('utf-8')

#获取页面代码

req = urllib2.Request("http://gs.amac.org.cn/amac-infodisc/res/pof/manager/138.html")

#r = requests.get('http://gs.amac.org.cn/amac-infodisc/res/pof/manager/138.html');

content = urllib2.urlopen(req).read()

#转码

typeEncode = sys.getfilesystemencoding()

infoencode = chardet.detect(content).get('encoding','utf-8')

html = content.decode(infoencode,'ignore').encode(typeEncode)

#data = content.text

#使用BeautifulSoup解析代码

soup = BeautifulSoup(html,'html.parser')

#创建一个文件

f =file('d:/pythonWorkSpace/Python27PygamePy2exe-master/Python27PygamePy2exe-master/test.html',"w")

#寻找此页面内的td，class为td-content的字符并保存

for i in soup.find_all('td',class_='td-content'):

    thisdata = i.text

    f.write(thisdata)

#关闭文件

f.close()