def parse(self, response):
index = 118
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
# print(response.xpath('/html/body/form/div[3]/table/tr/td/table/tr[3]/td/table/tr[3]/td/table/tr/td[3]/div/span[2]/div/table[1]/tr[1]'))
# '/html/body/div[2]/table/tbody/tr[4]/td/table/tbody/tr[1]/td[1]/a/span'
for i in range(1, 2):
if i == 8: continue
# print(response.xpath('/html/body/section/div[1]/div[5]/ul/li[1]'))
for line in response.xpath(
'/html/body/div[1]/div[3]/div/div[1]/div/div/div[2]/div[2]/div[2]/div[2]/div[2]/ul/li'
): # 教育信息爬取
print(1)
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
# '/html/body/div[3]/div/div/ul/li[17]/a'
# '/html/body/div[3]/div/div[3]/div[1]/ul/li[1]/div[3]/a[1]/h3'
# '/td/table/tbody/tr/td[1]/a'
# '/html/body/div[1]/div[8]/div/div/div[2]/div[2]/div[2]/table/tbody/tr/td[2]/div[1]/div[2]/div[3]/div[2]/div/div[1]/div[1]/table/tbody/tr/td/a'
# '/html/body/div[1]/div[8]/div/div/div[2]/div[2]/div[2]/table/tbody/tr/td[2]/div[1]/div[2]/div[3]/div[2]/div/div[1]/div[1]/table/tbody/tr/td/a/text()'
item['name'] = line.xpath('./a/text()').extract()[0].strip()
# '/html/body/div[6]/div[4]/div[1]/div[9]/div/table/tbody/tr[1]/td/table[9]/tbody/tr[1]/td[2]/a/b'
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
# '/html/body/div[2]/table/tbody/tr[4]/td/table/tbody/tr[1]/td[1]/a/span'
# '/html/body/div[4]/div[2]/div[2]/p[1]'
item['url'] = line.xpath('./a/@href').extract()[0]
print(item['url'])
# item['details'] = line.xpath('./span/text()').extract()[0].strip()
yield item
def parse(self, response):
index = 72
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
# print(response.xpath('/html/body/form/div[3]/table/tr/td/table/tr[3]/td/table/tr[3]/td/table/tr/td[3]/div/span[2]/div/table[1]/tr[1]'))
# '/html/body/div[2]/table/tbody/tr[4]/td/table/tbody/tr[1]/td[1]/a/span'
for i in range(1, 2):
for line in response.xpath(
'/html/body/div[2]/div[3]/div/div[1]/ul/li'): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
# '/html/body/div[3]/div/div/ul/li[17]/a'
# '/html/body/div[3]/div/div[3]/div[1]/ul/li[1]/div[3]/a[1]/h3'
# '/td/table/tbody/tr/td[1]/a'
# '/html/body/div[1]/div[8]/div/div/div[2]/div[2]/div[2]/table/tbody/tr/td[2]/div[1]/div[2]/div[3]/div[2]/div/div[1]/div[1]/table/tbody/tr/td/a'
# '/html/body/div[1]/div[8]/div/div/div[2]/div[2]/div[2]/table/tbody/tr/td[2]/div[1]/div[2]/div[3]/div[2]/div/div[1]/div[1]/table/tbody/tr/td/a/text()'
item['name'] = line.xpath('./a/text()').extract()[0].strip()
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
# '/html/body/div[2]/table/tbody/tr[4]/td/table/tbody/tr[1]/td[1]/a/span'
item['url'] = "http://www.ytmuseum.com" + line.xpath(
'./a/@href').extract()[0]
print(item['url'])
# item['details'] = line.xpath('./span/text()').extract()[0].strip()
yield item
def parse_details(self,response):
item = eduItem()
item['mid']= response.meta['mid']
item['name'] = response.meta['name']
item['url'] = response.meta['url']
item['details'] = response.xpath('/html/body/div[2]/div[2]/div[4]/div/div/p[1]/text()').extract()[0]
yield item
def parse(self, response):
index = 42
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
print(
response.xpath(
'/html/body/form/div[3]/table/tr/td/table/tr[3]/td/table/tr[3]/td/table/tr/td[3]/div/span[2]/div/table[1]/tr[1]'
))
for line in response.xpath(
'/html/body/form/div[3]/table/tr/td/table/tr[3]/td/table/tr[3]/td/table/tr/td[3]/div/span[2]/div/table[1]/tr[1]'
): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
# '/html/body/div[3]/div/div/ul/li[17]/a'
item['name'] = line.xpath(
'./td/table/tr/td[2]/a/text()').extract()[0]
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
item['url'] = "http://www.cyjng.net" + line.xpath(
'./td/table/tr/td[2]/a/@href').extract()[0]
print(item['url'])
# item['details'] = line.xpath('./span/text()').extract()[0].strip()
yield item
def parse(self, response):
index = 44
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
# print(response.xpath('/html/body/form/div[3]/table/tr/td/table/tr[3]/td/table/tr[3]/td/table/tr/td[3]/div/span[2]/div/table[1]/tr[1]'))
for line in response.xpath(
'/html/body/div[8]/div/div/div/div/div[2]/div/div/div[2]/div/div/div'
): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
# '/html/body/div[3]/div/div/ul/li[17]/a'
# '/html/body/div[8]/div/div/div/div/div[2]/div/div/div[2]/div/div/div[2]/section/div[2]/header/h3/a'
item['name'] = line.xpath(
'./section/div[2]/header/h3/a/text()').extract()[0]
print(item['name'])
print(line.xpath('./section/div[2]/header/h3/a/@href').extract())
item[
'url'] = "http://www.19371213.com.cn/learn/programme" + line.xpath(
'./section/div[2]/header/h3/a/@href').extract()[0][1:]
print(item['url'])
# item['details'] = line.xpath('./span/text()').extract()[0].strip()
yield item
def parse(self, response):
index = 70
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
# print(response.xpath('/html/body/form/div[3]/table/tr/td/table/tr[3]/td/table/tr[3]/td/table/tr/td[3]/div/span[2]/div/table[1]/tr[1]'))
# '/html/body/div[2]/table/tbody/tr[4]/td/table/tbody/tr[1]/td[1]/a/span'
for i in range(1, 15, 3):
for line in response.xpath(
'/html/body/div[2]/table/tbody/tr[4]/td/table/tbody/tr[{}]'
.format(i)): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
# '/html/body/div[3]/div/div/ul/li[17]/a'
# '/html/body/div[3]/div/div[3]/div[1]/ul/li[1]/div[3]/a[1]/h3'
# '/td/table/tbody/tr/td[1]/a'
# '/html/body/div[1]/div[8]/div/div/div[2]/div[2]/div[2]/table/tbody/tr/td[2]/div[1]/div[2]/div[3]/div[2]/div/div[1]/div[1]/table/tbody/tr/td/a'
# '/html/body/div[1]/div[8]/div/div/div[2]/div[2]/div[2]/table/tbody/tr/td[2]/div[1]/div[2]/div[3]/div[2]/div/div[1]/div[1]/table/tbody/tr/td/a/text()'
item['name'] = line.xpath(
'./td[1]/a/span/text()').extract()[0].strip()
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
# '/html/body/div[2]/table/tbody/tr[4]/td/table/tbody/tr[1]/td[1]/a/span'
item[
'url'] = "http://bowuguan.qingzhou.gov.cn/jy/sjhd/tsjy" + line.xpath(
'./td[1]/a/@href').extract()[0]
print(item['url'])
# item['details'] = line.xpath('./span/text()').extract()[0].strip()
yield item
def parse(self, response):
index = 51
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
# print(response.xpath('/html/body/form/div[3]/table/tr/td/table/tr[3]/td/table/tr[3]/td/table/tr/td[3]/div/span[2]/div/table[1]/tr[1]'))
# for line in response.xpath('/html/body/div/div/div[2]/div/div[4]/div[5]/div[1]/ul/li'): # 教育信息爬取
# print(1)
# item = eduItem()
# item['mid'] = index
# # print(item['mid'])
# # '/html/body/div[3]/div/div/ul/li[17]/a'
# # '/html/body/div/div/div[2]/div/div[4]/div[5]/div[1]/ul/li[1]/div/div[2]/a/div[1]'
# item['name'] = line.xpath('./div/div[2]/a/div[1]/text()').extract()[0]
# print(item['name'])
# # print(line.xpath('./h2/a/@href').extract())
# item['url'] = "http://www.zmnh.com"+line.xpath('./div/div[2]/a/@href').extract()[0]
# print(item['url'])
# # item['details'] = line.xpath('./span/text()').extract()[0].strip()
# yield item
# print(response.text)
js = json.loads(response.xpath('/html/body/pre/text()').extract()[0])
for i in js['data']:
item = eduItem()
item['mid'] = index
item['name'] = i['title']
print(item['name'])
item[
'url'] = "http://www.zmnh.com/news/news_info.html?category={}&infotype=8&id={}".format(
i['category'], i['id'])
print(item['url'])
yield item
def parse(self, response):
index = 1
rootUrl = 'https://www.dpm.org.cn'
for line in response.xpath('//table/tr/td[@width="660"]'): # 教育信息爬取
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./a/text()').extract()
# print(line.xpath('./a/@href').extract())
item['url'] = rootUrl + line.xpath('./a/@href').extract()[0]
yield item
def parse(self, response):
index = 4
rootUrl = 'http://www.jb.mil.cn/cyhd/jzhd/'
for line in response.xpath(
'/html/body/div[4]/div/div[3]/ul/li'): # 教育信息爬取
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./a/h3/text()').extract()
# print(line.xpath('./a/@href').extract())
item['url'] = rootUrl + line.xpath('./a/@href').extract()[0][1:]
yield item
def parse(self, response):
index = 8
rootUrl = 'http://www.bmnh.org.cn/'
for line in response.xpath('/html/body/div[3]/div[2]/div[2]/p'): # 教育信息爬取
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./a/span/text()').extract()
# print(line.xpath('./a/@href').extract())
item['url'] = rootUrl+line.xpath('./a/@href').extract()[0]
# print(line.xpath('./div[@class="jchg-info"]/a[@class="jchg-name"]/@href').extract()[0])
yield item
def parse(self, response):
index = 20
rootUrl = 'http://www.luxunmuseum.com.cn/'
for i in range(1,12,2):
for line in response.xpath('/html/body/table[4]/tr/td[3]/table/tr/td/table[2]/tr/td/table/tr/td/table/tr/td/table[1]/tr[1]/td{}'.format(i)): # 教育信息爬取
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./a/@title').extract()
# print(line.xpath('./a/@href').extract())
item['url'] = rootUrl + line.xpath('./div[2]/a/@href').extract()[0]
yield item
def parse(self, response):
index = 3
rootUrl = 'http://www.gmc.org.cn'
for line in response.xpath(
'/html/body/div[4]/div/div/div[3]/div[1]/div'): # 教育信息爬取
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./a/div[1]/div[1]/text()').extract()
# print(line.xpath('./a/div[1]/div[1]/text()').extract())
# print(line.xpath('./a/@href').extract())
item['url'] = rootUrl + line.xpath('./a/@href').extract()[0]
yield item
def parse(self, response):
index = 21
rootUrl = 'http://www.luxunmuseum.com.cn/'
print(1)
for line in response.xpath(
'/html/body/div[6]/div[2]/div/div[3]/div[1]/div'): # 教育信息爬取
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./div[2]/a/text()').extract()
# print(line.xpath('./a/@href').extract())
item['url'] = rootUrl + line.xpath('./div[2]/a/@href').extract()[0]
yield item
def parse(self, response):
index = 22
rootUrl = 'http://www.luxunmuseum.com.cn/'
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
for line in response.xpath('/html/body/div[5]/div/div[2]/div[2]/ul/li'): # 教育信息爬取
print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./h2/a/text()').extract()
# print(line.xpath('./h2/a/@href').extract())
item['url'] = line.xpath('./h2/a/@href').extract()[0]
yield item
def parse(self, response):
index = 11
rootUrl = 'http://www.chnmuseum.cn'
print(response.xpath('/html/body/div[4]/div/div/div/ul[2]/li[1]'))
for line in response.xpath(
'/html/body/div[4]/div/div/div/ul[2]/li'): # 教育信息爬取
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./a/text()').extract()
print(item['name'])
# print(line.xpath('./a/@href').extract())
item['url'] = rootUrl + line.xpath('./a/@href').extract()[0][1:]
print(item['url'])
# print(line.xpath('./div[@class="jchg-info"]/a[@class="jchg-name"]/@href').extract()[0])
yield item
def parse(self, response):
index = 9
rootUrl = 'http://www.1937china.com/'
print(response.xpath('/html/body/div[3]/div[2]/div'))
for line in response.xpath(
'/html/body/div[3]/div[2]/div/div[2]/div/ul/li'): # 教育信息爬取
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./a/p/text()').extract()
print(item['name'])
# print(line.xpath('./a/@href').extract())
item['url'] = line.xpath('./a/@href').extract()[0]
print(item['url'])
# print(line.xpath('./div[@class="jchg-info"]/a[@class="jchg-name"]/@href').extract()[0])
yield item
def parse(self, response):
index = 2
rootUrl = 'http://cstm.cdstm.cn/'
for line in response.xpath(
'/html/body/div[1]/div/div[@class="jchg-cont"]'): # 教育信息爬取
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath(
'./div[@class="jchg-info"]/a[@class="jchg-name"]/text()'
).extract()
# print(line.xpath('./a/@href').extract())
item['url'] = line.xpath(
'./div[@class="jchg-info"]/a[@class="jchg-name"]/@href'
).extract()[0]
# print(line.xpath('./div[@class="jchg-info"]/a[@class="jchg-name"]/@href').extract()[0])
yield item
def parse(self, response):
index = 31
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
for line in response.xpath('/html/body/div[2]/div[2]/div[3]/ul/li'): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
# '/html/body/div[3]/div/div/ul/li[17]/a'
item['name'] = line.xpath('./a/text()').extract()[0]
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
item['url'] = "http://www.jlmuseum.org" + line.xpath('./a/@href').extract()[0]
print(item['url'])
item['details'] = line.xpath('./span/text()').extract()[0].strip()
yield item
def parse(self, response):
index = 15
rootUrl = 'http://www.tjbwg.com/cn/'
# print(response.xpath('/html/body/div[4]/div/div/div/ul[2]/li[1]'))
for line in response.xpath(
'/html/body/div/div[3]/div/div/div[2]/div[2]/div/div/ul/li'
): # 教育信息爬取
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath(
'./a/div[@class="text"]/h3/text()').extract()[0].strip()
print(item['name'])
# print(line.xpath('./a/@href').extract())
item['url'] = rootUrl + line.xpath('./a/@href').extract()[0]
print(item['url'])
# print(line.xpath('./div[@class="jchg-info"]/a[@class="jchg-name"]/@href').extract()[0])
yield item
def parse(self, response):
index = 23
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
for i in (1, 5):
for line in response.xpath(
'/html/body/div/div/div[2]/div[2]/ul[{}]/li'.format(
i)): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./div/a/h3/strong/text()').extract()
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
item['url'] = "http://www.balujun.cn" + line.xpath(
'./div/a/@href').extract()[0]
print(item['url'])
yield item
def parse(self, response):
index = 25
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
for line in response.xpath(
'/html/body/div[2]/div[2]/div[2]/ul/li'): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath('./span[1]/a/text()').extract()[0]
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
item[
'url'] = "http://ordosbwg.org.cn/shjy_121919/sjhd" + line.xpath(
'./span[1]/a/@href').extract()[0][1:]
print(item['url'])
item['details'] = line.xpath('./span[2]/text()').extract()[0]
yield item
def parse(self, response):
index = 59
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
# print(response.xpath('/html/body/form/div[3]/table/tr/td/table/tr[3]/td/table/tr[3]/td/table/tr/td[3]/div/span[2]/div/table[1]/tr[1]'))
for line in response.xpath(
'/html/body/div[4]/div/div[2]/div[2]/ul/li'): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
# '/html/body/div[3]/div/div/ul/li[17]/a'
# '/html/body/div[3]/div/div[3]/div[1]/ul/li[1]/div[3]/a[1]/h3'
item['name'] = line.xpath('./h1/text()').extract()[0].replace(
'\t', '').replace('\n', '')
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
item['url'] = line.xpath('./p/a/@href').extract()[0]
print(item['url'])
# item['details'] = line.xpath('./span/text()').extract()[0].strip()
yield item
def parse(self, response):
index = 37
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
for i in range(2, 28, 2):
for line in response.xpath(
'/html/body/table[3]/tr/td/table/tr/td[2]/table/tr[2]/td/div/table/tr[{}]'
.format(i)): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
# '/html/body/div[3]/div/div/ul/li[17]/a'
item['name'] = line.xpath('./td/a/font/text()').extract()[0]
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
item['url'] = "http://www.dqsbwg.com/" + line.xpath(
'./td/a/@href').extract()[0]
print(item['url'])
# item['details'] = line.xpath('./li/span/text()').extract()[0].strip()
yield item
def parse(self, response):
index = 38
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
for line in response.xpath(
'/html/body/div[6]/div[2]/div[1]/ul/li'): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
# '/html/body/div[3]/div/div/ul/li[17]/a'
item['name'] = line.xpath(
'./div[2]/div[1]/dl/dt/text()').extract()[0]
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
item[
'url'] = "https://www.shanghaimuseum.net/education/" + line.xpath(
'./div[1]/div[2]/a/@href').extract()[0]
print(item['url'])
item['details'] = line.xpath(
'./div[2]/div[1]/dl/dd[1]/p/text()').extract()[0].strip()
yield item
def parse(self, response):
index = 29
# / html / body / div[5] / div / div[2] / div[2] / ul / li[1]
# print(response.xpath('/html/body/div/div/div[2]/div[2]/ul[1]/li[2]/div/a/h3'))
# ' / html / body / div / div / div[2] / div[2] / ul[1] / li[2] / div / a / h3 / strong'
for line in response.xpath(
'/html/body/div[1]/div[4]/div[1]/div/div[2]/div/div[2]/div/div/div[2]/div/div/div[1]/ul/li[@class="content column-num1"]'
): # 教育信息爬取
# print(1)
item = eduItem()
item['mid'] = index
# print(item['mid'])
item['name'] = line.xpath(
'./div/ul/li[1]/h3/a/@title').extract()[0]
print(item['name'])
# print(line.xpath('./h2/a/@href').extract())
item['url'] = "http://www.sypm.org.cn/" + line.xpath(
'./div/ul/li[1]/h3/a/@href').extract()[0]
print(item['url'])
# '/ html / body / div[1] / div[4] / div[1] / div / div[2] / div / div[2] / div / div / div[2] / div / div / \
# div[1] / ul / li[1] / div / ul / li[2]'
item['details'] = line.xpath(
'./div/ul/li[2]/text()').extract()[0].strip()
yield item
