def parse_item(self, response):
#i['domain_id'] = response.xpath('//input[@id="sid"]/@value').extract()
#i['name'] = response.xpath('//div[@id="name"]').extract()
#i['description'] = response.xpath('//div[@id="description"]').extract()
print response.url
for each in response.xpath('//div[@class="pagecenter p3"]'):
item = DongguanItem()
item["title"] = each.xpath(
".//strong[@class='tgray14']/text()").extract()[0]
item["num"] = item["title"].split(" ")[-1].split(":")[-1]
item["content"] = each.xpath(
".//div[@class='c1 text14_2']/text()").extract()[0]
print "666666"
yield item
def parse_item(self, response):
item = DongguanItem()
url = response.url
title_num = response.xpath(
'//div[@class="pagecenter p3"]//strong/text()').extract()[0]
title = title_num.split(' ')[0]
title = title.split('：')[1]
num = title_num.split(' ')[1]
num = num.split(':')[1]
content = response.xpath(
'//div[@class="content text14_2"]/div[@class="c1 text14_2"]/text() | //div[@class="contentext"]/text()'
).extract()
content = ''.join(content).strip()
item['url'] = url
item['title'] = title
item['num'] = num
item['content'] = content
yield item
def process_item(self, response):
item = DongguanItem()
url = response.url
title_num = response.xpath(
'//div[@class="pagecenter p3"]//strong/text()').extract()
title = title_num[0].split('\xa0\xa0')[0]
title = title.split('：')[1]
# print(title)
number = title_num[0].split('\xa0\xa0')[1]
number = number.split(':')[1]
# print(number)
content = response.xpath(
'//div[@class="c1 text14_2"]/text() | //div[@class="contentext"]/text()'
).extract()
content = ''.join(content).strip()
# print(content)
item['url'] = url
item['title'] = title
item['number'] = number
item['content'] = content
yield item