def parse_item(self, response):
item = NewdongguanItem()
#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()
return item
def parse_item(self, response):
item = NewdongguanItem()
# 标题
# item['title'] = response.xpath('//div[contains(@class, "pagecenter p3")]//strong/text()').extract()[0]
item['title'] = response.xpath(
'//div[@id = "news_main"]//div[@class = "news_content"]/h2[@class = "newsTitle"]/text()'
).extract()[0]
# 编号
item['number'] = response.xpath(
'//div[@id = "news_main"]//div[@class = "news_content"]//div[@class = "message"]/text()'
).extract()[0]
# 内容，先使用有图片情况下的匹配规则，如果有内容，返回所有内容的列表集合
contents = response.xpath(
'//div[@id = "news_main"]//div[@class = "news_content"]//p/text()'
).extract()
content = ""
for cont in contents:
content = content + cont
item['content'] = content
item['url'] = response.url
# 交给管道
yield item
def parse_item(self, response):
item = NewdongguanItem()
# 标题
item['title'] = response.xpath('//div[contains(@class, "pagecenter p3")]//strong/text()').extract()[0]
# 编号
item['number'] = item['title'].split(' ')[-1].split(":")[-1]
# 内容，先使用有图片情况下的匹配规则，如果有内容，返回所有内容的列表集合
content = response.xpath('//div[@class="contentext"]/text()').extract()
# 如果没有内容，则返回空列表，则使用无图片情况下的匹配规则
if len(content) == 0:
content = response.xpath('//div[@class="c1 text14_2"]/text()').extract()
item['content'] = "".join(content).strip()
else:
item['content'] = "".join(content).strip()
# 链接
item['url'] = response.url
yield item
# # -*- coding: utf-8 -*-
# import scrapy
# from newdongguan.items import NewdongguanItem
# class DongdongSpider(scrapy.Spider):
# # 处理每个帖子的response内容
# def parse_item(self, response):
# item = NewdongguanItem()
# # 标题
# item['title'] = response.xpath('//div[contains(@class, "pagecenter p3")]//strong/text()').extract()[0]
# # 编号
# item['number'] = item['title'].split(' ')[-1].split(":")[-1]
# # 内容，先使用有图片情况下的匹配规则，如果有内容，返回所有内容的列表集合
# content = response.xpath('//div[@class="contentext"]/text()').extract()
# # 如果没有内容，则返回空列表，则使用无图片情况下的匹配规则
# if len(content) == 0:
# content = response.xpath('//div[@class="c1 text14_2"]/text()').extract()
# item['content'] = "".join(content).strip()
# else:
# item['content'] = "".join(content).strip()
# # 链接
# item['url'] = response.url
# # 交给管道
# yield item
def parse_item(self, response):
item = NewdongguanItem()
item['title'] = response.xpath('//div[contains(@class, "pagecenter p3")]//strong/text()').extract()[0]
item['num'] = item['title'].split(' ')[-1].split(":")[-1]
content = response.xpath('//div[@class="contentext"]/text()').extract()
if len(content) == 0:
content = response.xpath(
'//div[@class="c1 text14_2"]/text()').extract()
item['content'] = ''.join(content).strip()
else:
item['content'] = ''.join(content).strip()
item['url'] = response.url
yield item
def parse_item(self, response):
item = NewdongguanItem()
#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()
item['title'] = response.xpath('//div[contains(@class, "pagecenter p3")]//strong/text()').extract()[0]
# 编号
item['number'] = item['title'].split(' ')[-1].split(":")[-1]
# 内容
item['content'] = response.xpath('//div[@class="c1 text14_2"]/text()').extract()[0]
# 链接
item['url'] = response.url
yield item
def parse_item(self, response):
print response.url
item = NewdongguanItem()
item['title'] = response.xpath('//div[contains(@class,"pagecenter p3")]//strong/text()').extract()[0]
# 编号
item['number'] = item['title'].split(' ')[-1].split(":")[-1]
# 内容,先取出有图片的情况下匹配规则，如果有内容，返回所有内容的列表集合，如果没有内容
content = response.xpath('//div[@class="contentext"]/text()').extract()
#如果没有内容，则返回空列表，则无图片情况下的匹配规则
if len(content)== 0:
content = response.xpath('//div[@class="c1 text14_2"]/text()').extract()
item['content'] = "".join(content).strip()
else:
item['content'] = "".join(content).strip()
# 链接
item['url'] = response.url
# 交给管道
yield item
def parse_item(self, response):
# try:
item = NewdongguanItem()
# 标题
# item['title'] = response.xpath('//div[contains(@class, "pagecenter p3")]//strong/text()').extract()[0]
item['title'] = response.xpath(
'//div[@class = "article_cent"]//h1/text()').extract()[0]
# 编号
item['time'] = response.xpath(
'//div[@class = "article_cent"]//span/text()').extract()[0]
# time2= response.xpath('//div[@class="content"]//div[@class="zx_all"]/text()').extract()[0]
# item['time'] = time1 =time2
# = str(time).replace(" ","")
# 内容，先使用有图片情况下的匹配规则，如果有内容，返回所有内容的列表集合
contents = response.xpath(
'//div[@class = "article_cent"]//p/text()').extract()
# contentsp = response.xpath('//div[@class="content"]//div[@class="font14"]//p/text()').extract()
# contentsdiv = response.xpath('//div[@class="content"]//div[@class="font14"]/text()').extract()
# contentsstrong= response.xpath('//div[@class="content"]//div[@class="font14"]//strong/text()').extract()
content = ""
# for condiv in contentsdiv:
# content = content + condiv
# for constp in contentsp:
# content = content + constp
# for constrong in contentsstrong:
# content = content + constrong
for cont in contents:
print cont
content = content + "/r/n" + cont
# item['content']= str(content).replace(" ", "")
item['content'] = content
# item['content']= str(content).replace(" ","")
item['url'] = response.url
# except Exception, e:
# print "parse_item failue"
# 交给管道
yield item