def parse(self, response):
item=exhibition75Item()
item["museumID"]=121
li_list=response.xpath("/html//div/div[1]/div[2]/div[3]/ul/li")
for li in li_list:
item["exhibitionTheme"]=li.xpath("./span/a/text()").extract_first()
item["exhibition_picture"]='http://www.bjqtm.com/'+li.xpath("./a/img/@src").extract_first()
yield item
def parse(self, response):
item = exhibition75Item()
item["museumID"] = 115
li_list = response.xpath("/html//div[3]/div[2]/div[2]/a")
for li in li_list:
item["exhibitionTheme"] = li.xpath(
"./div[2]/div[2]/p[2]/text()").extract_first()
item["exhibitionIntroduction"] = li.xpath(
"./div[2]/div[2]/p[1]/text()").extract_first()
item["exhibition_picture"] = ''
yield item
def parse(self, response):
item = exhibition75Item()
item["museumID"] = 114
li_list = response.xpath("/html/body/div[3]/div[2]/div[2]/ul/li")
for li in li_list:
item["exhibitionTheme"] = li.xpath(
"./a/span/text()").extract_first()
item["exhibitionIntroduction"] = ' '
item["exhibition_picture"] = 'http://www.sxhm.com/' + li.xpath(
"./a/img/@src").extract_first()
yield item
def parse(self, response):
item = exhibition75Item()
item["museumID"] = 125
li_list = response.xpath("//tr")
for li in li_list:
item["exhibitionTheme"] = li.xpath(
".//div[2]/div[1]/a/text()").extract_first()
item["exhibitionIntroduction"] = li.xpath(
".//div//div[2]/text()").extract_first()
item["exhibition_picture"] = '(http://tour.dha.ac.cn)' + str(
li.xpath(".//a/img/@src").extract_first())
yield item
def parse(self, response):
item = exhibition75Item()
item["museumID"] = 105
li_list = response.xpath(
"/html/body/div[3]/div/div[2]/div[3]/div[2]/div[1]/div/div")
for li in li_list:
item["exhibitionIntroduction"] = ''
item["exhibitionTheme"] = li.xpath(
"./dl/dd/text()").extract_first()
item["exhibition_picture"] = li.xpath(
"./dl/a/dt/img/@src").extract_first()
yield item
def parse(self, response):
item = exhibition75Item()
item["museumID"] = 118
li_list = response.xpath(
"/html//table[4]//tr/td/table[2]//tr/td[3]/table[3]//tr[1]/td/div/ul/li"
)
for li in li_list:
item["exhibitionTheme"] = li.xpath("./a/text()").extract_first()
item["exhibitionIntroduction"] = li.xpath(
"./span/text()").extract_first()
item["exhibition_picture"] = ''
yield item
def parse(self, response):
item=exhibition75Item()
item["museumID"]=109
li_list=response.xpath("/html//div/div/div/div/div[2]/div/div[1]/div[2]/div/div/div[2]/div/div[1]/ul/li")
for li in li_list:
item["exhibitionTheme"] = li.xpath("normalize-space(./div[2]/ul/li/h1/strong/a/text())").extract_first()
item["exhibitionTheme"] = str(item["exhibitionTheme"]).replace(u'\\xa0', u' ')
item["exhibitionTheme"] = str(item["exhibitionTheme"]).replace(u'\xa0', u' ')
if len(item["exhibitionTheme"]) != 0:
item["exhibitionIntroduction"] = li.xpath("normalize-space(./div[2]/div/text())").extract_first()
item["exhibitionIntroduction"] = str(item["exhibitionIntroduction"]).replace(u'\\xa0', u' ')
item["exhibitionIntroduction"] = str(item["exhibitionIntroduction"]).replace(u'\xa0', u' ')
item["exhibition_picture"] = 'http://www.ynnmuseum.com' + str(li.xpath("./div[1]/div/a/img/@src").extract_first())
def parse(self, response):
item = exhibition75Item()
item["museumID"] = 126
li_list = response.xpath("/html//div[2]/div/div[2]/div[2]/div[2]/dl")
for li in li_list:
item['exhibitionTime'] = li.xpath(
"./dt/span/text()").extract_first()
item["exhibitionTheme"] = li.xpath("./dt/a/text()").extract_first()
item['exhibitionIntroduction'] = li.xpath(
"normalize-space(./dd[2]/text()[1])").extract_first()
item["exhibitionIntroduction"] = str(
item["exhibitionIntroduction"]).replace(u'\u3000', u'')
item["exhibition_picture"] = str(
li.xpath("./dd[1]/a/img/@src").extract_first())
yield item
def parse(self, response):
item = exhibition75Item()
item["museumID"] = 108
li_list = response.xpath(
"/html//div/div[3]/div[1]/div/div[3]/div[1]/div")
for li in li_list:
item["exhibitionTheme"] = li.xpath(
"normalize-space(./div[2]/div/div[1])").extract_first()
#item["exhibitionTheme"] = str(item["exhibitionTheme"]).replace(u'\\xa0', u' ')
#item["exhibitionTheme"] = str(item["exhibitionTheme"]).replace(u'\xa0', u' ')
item["exhibitionIntroduction"] = '' #li.xpath(
# "normalize-space(./div/div/div/div/div[1]/div[2]/div/text())").extract_first()
#item["exhibitionIntroduction"] = str(item["exhibitionIntroduction"]).replace(u'\\xa0', u' ')
# item["exhibitionIntroduction"] = str(item["exhibitionIntroduction"]).replace(u'\xa0', u' ')
item["exhibition_picture"] = 'http://www.ynmuseum.org' + li.xpath(
'./div[1]/a/img/@src').extract_first()
yield item
def parse(self, response):
item = exhibition75Item()
item["museumID"] = 107
li_list = response.xpath("/html//div[4]/div/div/div")
for li in li_list:
item["exhibitionTheme"] = li.xpath(
"normalize-space(./a/span/text())").extract_first()
item["exhibitionTheme"] = str(item["exhibitionTheme"]).replace(
u'\\xa0', u' ')
item["exhibitionTheme"] = str(item["exhibitionTheme"]).replace(
u'\xa0', u' ')
item["exhibitionIntroduction"] = li.xpath(
"normalize-space(./div/div/div/div/div[1]/div[2]/div/text())"
).extract_first()
item["exhibitionIntroduction"] = str(
item["exhibitionIntroduction"]).replace(u'\\xa0', u' ')
item["exhibitionIntroduction"] = str(
item["exhibitionIntroduction"]).replace(u'\xa0', u' ')
item["exhibition_picture"] = ''
yield item
