def parse_text(self, response):
selector = scrapy.Selector(response)
title = selector.xpath("//title/text()").extract()[0] #得到页面的标题
url = response.url #页面链接
#content=selector.xpath("string(//form[@name='form124904a'])").extract()[0].replace(u'\r\n','').replace(u'\xa0',u'')
content1 = selector.css(
"form[name='form124904a'] *:not(style)::text").extract() #得到页面的内容
content = "".join(content1).replace(u'\r\n', '').replace(
u'\xa0', u'').replace(' ', '').replace('\'', '').replace('\"', '')
item = JimeiItem()
item['url'] = url
item['title'] = title
item['content'] = content
yield item
def parse_text(self, response):
selector = scrapy.Selector(response)
title = selector.xpath("//title/text()").extract()[0] #得到页面的标题
url = response.url #页面链接
content = selector.css(
"div[id='vsb_content'] *:not(style)::text").extract() #得到页面的内容
content = "".join(content).replace(u'\r\n', '').replace(
u'\xa0', u'').replace(' ', '').replace('\'', '').replace('\"', '')
#filename="infos/ae.txt"
#with open(filename, 'a+',encoding='utf-8') as f:
#f.write(url+title+'\n')
item = JimeiItem()
item['url'] = url
item['title'] = title
item['content'] = content
yield item