def parse(self, response):
subSelector = response.xpath('//div[@class ="top-min"]')
items = []
for sub in subSelector:
catgoryName = sub.xpath(
'.//div[@class="tt fn-clear"]/h5/text()').extract()[0]
storyNameTotal = sub.xpath(
'.//ul[@class ="top-list fn-clear"]/li/h5/a/text()').extract()
rankpoint = sub.xpath(
'.//ul[@class ="top-list fn-clear"]/li/div[@class="lasted-num fn-left"]/i/text()'
).extract()
point_int = sub.xpath(
'.//ul[@class ="top-list fn-clear"]/li/div[@class="lasted-time fn-right"]/strong/text()'
).extract()
point_float = sub.xpath(
'.//ul[@class ="top-list fn-clear"]/li/div[@class="lasted-time fn-right"]/span/text()'
).extract()
pointField = [
float(a) + float(b) for a in point_int for b in point_float
]
for i in range(len(storyNameTotal)):
item = Meiju100Item()
item['catgory'] = catgoryName
item["storyname"] = storyNameTotal[i]
item['rank'] = rankpoint[i]
item['point'] = pointField[i]
items.append(item)
return items
def parse(self, response):
li_list = response.xpath('//ul[@class="top-list fn-clear"]/li')
for sub in li_list:
item = Meiju100Item()
item['movname'] = sub.xpath('./h5/a/text()').extract_first()
item['movurl'] = response.urljoin(
sub.xpath('./h5/a/@href').extract_first())
item['movstatu'] = sub.xpath(
'./span[1]/font/text()').extract_first()
item['movstation'] = sub.xpath('./span[2]/text()').extract_first()
item['movupdate'] = sub.xpath('./div[2]/text()').extract_first()
if item['movstatu']:
pass
else:
item['movstatu'] = sub.xpath(
'./span[1]/text()').extract_first()
if item['movstation']:
pass
else:
item['movstation'] = [u'未知']
if item['movupdate']:
pass
else:
item['movupdate'] = sub.xpath(
'./div[2]/font/text()').extract_first()
yield item
def parse(self, response):
items = []
subSelector = response.xpath('//ul[@class="top-list fn-clear"]/li')
for sub in subSelector:
item = Meiju100Item()
item['storyName'] = sub.xpath('./h5/a/text()').extract()
item['storyState'] = sub.xpath('./span[1]/font/text()').extract()
item['tvStation'] = sub.xpath('./span[2]/text()').extract()
item['updateTime'] = sub.xpath('./div[2]/text()').extract()
items.append(item)
return items
def parse(self, response):
subSelector = response.xpath('//ul[@class="top-list fn-clear"]/li')
items = []
for sub in subSelector:
item = Meiju100Item()
item['storyName'] = sub.xpath('./h5/a/text()').extract()[0]
# item['storyState'] = sub.xpath('./span[@class="state1 new100state1"]/text()').extract()[0]
item['tvStation'] = sub.xpath(
'./span[@class="mjtv"]/text()').extract()[0]
# item['updateTime'] = sub.xpath('./div[@class="lasted-time new100time fn-right"]/font/text()').extract()[0]
item['storyLX'] = sub.xpath(
'./span[@class="mjjq"]/text()').extract()[0]
print("----------------------------------")
items.append(item)
return items
def parse(self, response):
subSelector = response.xpath('//li/div[@class="lasted-num fn-left"]')
items = []
for sub in subSelector:
item = Meiju100Item()
item['storyName'] = sub.xpath('../h5/a/text()').extract()[0]
item['storyState'] = sub.xpath(
'../span[@class="state1 new100state1"]/text()').extract()[0]
item['tvStation'] = sub.xpath(
'../span[@class="mjtv"]/a/text()').extract()
item['updateTime'] = sub.xpath(
'../div[@class="lasted-time new100time fn-right"]/text()'
).extract()[0]
items.append(item)
return items