Scrapy-笔记二 中文处理以及保存中文数据

scrapy shell http://blog.csdn.net/u012150179/article/details/34450547

sel.xpath('//h4/text()').extract()

In [1]: sel.xpath('//h4/text()').extract()
shell:1: ScrapyDeprecationWarning: "sel" shortcut is deprecated. Use "response.xpath()", "response.css()" or "response.selector" instead
Out[1]: 
[u'\u63d0\u53d6\u7f51\u9875\u4e2d\u4e2d\u6587\u5e76\u8f93\u51fa\u6216\u8005\u662f\u4fdd\u5b58\u65f6\u7ecf\u5e38\u4f1a\u51fa\u73b0\u4e00\u4e2a\u95ee\u9898\u662f\u663e\u793a\u7684\u662f\u4e2d\u6587\u5bf9\u5e94\u7684unicode\u7f16\u7801\u800c\u975e\u4e2d\u6587\u672c\u8eab\uff0c\u8fd9\u91cc\u8bb2\u8ff0\u89e3\u51b3\u8fd9\u79cd\u95ee\u9898\u7684\u65b9\u6cd5\u3002',
 u'\u6211\u7684\u540c\u7c7b\u6587\u7ae0',
 u'\u6b64\u535a\u5ba2\u5df2\u4e0d\u518d\u66f4\u65b0\uff0c\u65b0\u535a\u5ba2\u5730\u5740\uff1a\r\n',
 u'GitHub\u4e3b\u9875\uff1a\r\n']

temp = sel.xpath('//h4/text()').extract()

for i in temp[0]:
    print i.encode('utf-8'),

 11 class W3SchoolPipeline(object):
 12     def __init__(self):
 13         #初始化打开json记录文件数据
 14         #定义编码为utf-8
 15         self.file = codecs.open('w3school_data_utf8.json', 'wb', encoding='utf-8')

def process_item(self, item, spider):
 18         line = json.dumps(dict(item)) + '\n'
 19         # print line  
 20 
 21         self.file.write(line.decode("unicode_escape"))
 22         return item
 23         #返回类型必须要是item类型