def parse(self, response):
selector = response.xpath("//div[@class='content']")
ITEM_NUMBER = len(selector)
title = selector.xpath("//a[@class='title']/text()").extract()
pts = selector.xpath("//div[@class='pts']/div/text()").extract()
# 数据装箱
for i in range(0, ITEM_NUMBER):
item = BilibiliranklistspiderItem()
item['title'] = title[i]
# item['play'] = play[i]
item['pts'] = pts[i]
yield item
def parse(self, response):
selector = response.xpath("//div[@class='content']")
ITEM_NUMBER = len(selector)
title = selector.xpath("//a[@class='title']/text()").extract()
barrage = selector.xpath(
"//span[@class='data-box']//i[@class='b-icon view']/parent::node()/text()"
).extract()
pts = selector.xpath("//div[@class='pts']/div/text()").extract()
play = selector.xpath(
"//span[@class='data-box']//i[@class='b-icon play']/parent::node()/text()"
).extract()
# 数据装箱
for i in range(0, ITEM_NUMBER):
item = BilibiliranklistspiderItem()
item['title'] = title[i]
item['barrage'] = barrage[i]
item['play'] = play[i]
item['pts'] = pts[i]
yield item
def parse(self, response):
# 文件名设为当日日期
filename = time.strftime("%Y-%m-%d")
with open('./temp/' + filename, 'wb') as f:
f.write(response.body)
selector = response.xpath("//div[@class='content']")
ITEM_NUMBER = len(selector)
title = selector.xpath("//a[@class='title']/text()").extract()
author = selector.xpath(
"//span[@class='data-box']//i[@class='b-icon author']/parent::node()/text()"
).extract()
barrage = selector.xpath(
"//span[@class='data-box']//i[@class='b-icon view']/parent::node()/text()"
).extract()
pts = selector.xpath("//div[@class='pts']/div/text()").extract()
href = selector.xpath("//a[@class='title']/@href").extract()
play = selector.xpath(
"//span[@class='data-box']//i[@class='b-icon play']/parent::node()/text()"
).extract()
# 数据装箱
for i in range(0, ITEM_NUMBER):
item = BilibiliranklistspiderItem()
item['title'] = title[i]
item['author'] = author[i]
item['barrage'] = barrage[i]
item['play'] = play[i]
item['pts'] = pts[i]
item['href'] = href[i]
# 为了爬取分区、粉丝数等数据，需要进入每一个视频的详情页面进行抓取
yield Request(
"https://" + href[i][2:],
meta={'item': item},
callback=self.detailParse)