# !/usr/bin/python
#-*-coding:utf-8-*-
'''
功能：抽取指定url的页面内容中的title
'''
import re
import chardet
import urllib
from lxml import etree
def utf8_transfer(strs):
 '''
 utf8编码转换
 '''
 try:
  if isinstance(strs, unicode):
   strs = strs.encode('utf-8')
  elif chardet.detect(strs)['encoding'] == 'GB2312':
   strs = strs.decode("gb2312", 'ignore').encode('utf-8')
  elif chardet.detect(strs)['encoding'] == 'utf-8':
   strs = strs.decode('utf-8', 'ignore').encode('utf-8')
 except Exception, e:
  print 'utf8_transfer error', strs, e
 return strs
def get_title_xpath(Html):
 '''
 用xpath抽取网页Title
 '''
 Html = utf8_transfer(Html)
 Html_encoding = chardet.detect(Html)['encoding']
 page = etree.HTML(Html, parser=etree.HTMLParser(encoding=Html_encoding))
 title = page.xpath('/html/head/title/text()')
 try:
  title = title[0].strip()
 except IndexError:
  print 'Nothing'
 print title
def get_title(Html):
 '''
 用re抽取网页Title
 '''
 Html = utf8_transfer(Html)
 compile_rule = ur'<title>.*</title>'
 title_list = re.findall(compile_rule, Html)
 if title_list == []:
  title = ''
 else:
  title = title_list[0][7:-8]
 print title
if __name__ == '__main__':
	url = 'http://www.baidu.com'
	html = urllib.urlopen(url).read()
	new_html = utf8_transfer(html)
	try:
		get_title_xpath(new_html)
		get_title(new_html)
	except Exception, e:
		print e