def test2() :
xpath = '//*[@id="baseInfoWrapDom"]/div[2]/div[1]'
content = read_resource("jiang.html")
doc = parser.fromstring(content)
title_list = doc.xpath('//*[@class="biTitle"]/text()')
content_list = doc.xpath('//*[@class="biContent"]/text()')
data = {}
for index in range(len(title_list)) :
btitle = extract_content(title_list[index].encode("utf8"))
bcontent = extract_content(content_list[index].encode("utf8"))
data[btitle] = bcontent
print btitle, bcontent
print data
json_str = json.dumps(data)
print "--------------"
print json_str
print data.get("中文名")
def xpath_test():
content = read_resource("jiang.html")
doc = parser.fromstring(content)
root = doc.text_content()
print root
