def parse(self, response):
for sel in response.xpath('//div[@class = "video-wrap"]//ul/li'):
num = self.webFunc.getNum(sel.xpath('div/span[@class="num"]//text() | span/span[@class="num"]//text()').extract()[0])
if num >= self.webFunc.limit:
item = ZhiboItem()
item['title'] = sel.xpath('div//a/text()').extract()[0]
item['link'] = sel.xpath('a/@href').extract()[0]
item['view'] = num
item['img_url'] = sel.xpath('a//img/@src').extract()[0]
item['zhubo'] = sel.xpath('a//img/@title').extract()[0]
item['web'] = "huya"
item['cate'] = self.webFunc.getCate(response.url)
# item['active'] = True
yield item
def parse(self, response):
jsonBody = json.loads(response.body)
for sel in jsonBody["data"]["channelList"]:
num = self.webFunc.getNum(sel["views"])
if num >= self.webFunc.limit:
item = ZhiboItem()
item['title'] = sel["channel"]
item['link'] = "http://www.huomao.com/" + sel["id"]
item['view'] = num
item['img_url'] = sel["image"]
item['zhubo'] = sel["nickname"]
item['web'] = "huomao"
item['cate'] = self.webFunc.getCate(response.url)
# item['active'] = True
yield item
def parse(self, response):
jsonBody = json.loads(response.body)
for sel in jsonBody["streams"]:
num = self.webFunc.getNum(str(sel["viewers"]))
if num >= self.webFunc.limit:
item = ZhiboItem()
item['title'] = sel["channel"]["status"]
item['link'] = sel["channel"]["url"]
item['view'] = num
item['img_url'] = sel["preview"]["medium"]
item['zhubo'] = sel["channel"]["display_name"]
item['web'] = "twitch"
item['cate'] = self.webFunc.getCate(response.url)
# item['active'] = True
yield item
def parse(self, response):
jsonBody = json.loads(response.body)
for sel in jsonBody["data"]:
num = self.webFunc.getNum(sel["view"])
if num >= self.webFunc.limit:
item = ZhiboItem()
item['title'] = sel["title"]
item['link'] = "http://www.quanmin.tv/v/" + sel["uid"]
item['view'] = num
item['img_url'] = sel["thumb"]
item['zhubo'] = sel["nick"]
item['web'] = "quanmin"
item['cate'] = self.webFunc.getCate(response.url)
# item['active'] = True
yield item
def parse(self, response):
jsonBody = json.loads(response.body)
for sel in jsonBody["data"]["list"]:
num = self.webFunc.getNum(sel["totalCount"])
if num >= self.webFunc.limit:
item = ZhiboItem()
# just slove the space character, need to be improved later
item['title'] = sel["introduction"].replace(" ", " ")
item['link'] = "http://www.huya.com/" + sel["privateHost"]
item['view'] = num
item['img_url'] = sel["screenshot"]
item['zhubo'] = sel["nick"]
item['web'] = "huya"
item['cate'] = "lol"
# item['active'] = True
yield item
def parse(self, response):
for sel in response.xpath('//div[@id = "list-con"]/a'):
item = ZhiboItem()
num = self.webFunc.getNum(
sel.xpath(
'ul/li[@class="livecard-meta-item livecard-meta-views"]/span[@class="livecard-meta-item-text"]/text()'
).extract()[0])
if num >= self.webFunc.limit:
item['title'] = sel.xpath('h3/@title').extract()[0]
item['link'] = sel.xpath('@href').extract()[0]
item['view'] = num
item['img_url'] = sel.xpath('img/@src').extract()[0]
item['zhubo'] = sel.xpath('span/strong/text()').extract()[0]
item['web'] = "longzhu"
item['cate'] = self.webFunc.getCate(response.url)
# item['active'] = True
yield item
def parse(self, response):
for sel in response.xpath('//div[@id = "live-list-content"]/ul/li'):
num = self.webFunc.getNum(
sel.xpath('a//span[@class="dy-num fr"]/text()').extract()[0])
if num >= self.webFunc.limit:
item = ZhiboItem()
item['title'] = sel.xpath('a/@title').extract()[0]
item['link'] = "http://www.douyutv.com" + sel.xpath(
'a/@href').extract()[0]
item['view'] = num
item['img_url'] = sel.xpath(
'a//span[@class = "imgbox"]/img/@data-original').extract(
)[0]
item['zhubo'] = sel.xpath(
'a//span[@class = "dy-name ellipsis fl"]/text()').extract(
)[0]
item['web'] = "douyu"
item['cate'] = self.webFunc.getCate(response.url)
# item['active'] = True
yield item
def parse(self, response):
for sel in response.xpath(
'//div[@class = "bb-variety-area bb-room-list"]/div[@class = "bd"]/ul/li'
):
item = ZhiboItem()
num = self.webFunc.getNum(
sel.xpath('a/div[@class="info-area"]/div/span/span/text()').
extract()[0])
if num >= self.webFunc.limit:
item['title'] = sel.xpath(
'a/div[@class="sub-mask"]/p/text()').extract()[0]
item['link'] = "http://www.zhanqi.tv" + sel.xpath(
'a/@href').extract()[0]
item['view'] = num
item['img_url'] = sel.xpath(
'a/div[@class="imgBox"]/img/@src').extract()[0]
item['zhubo'] = sel.xpath(
'a/div[@class="imgBox"]/img/@alt').extract()[0]
item['web'] = "zhanqi"
item['cate'] = "girl"
# item['active'] = True
yield item
def parse(self, response):
for sel in response.xpath(
'//div[@class = "live-list-tabc tabc js-room-list-tabc" and not(p[@class = "no-videoList-title"])]/ul/li | //div[@class = "bb-hot-area bb-funny-area bb-room-list" or @class ="bb-variety-area bb-room-list"]/div[@class = "bd"]/ul/li | //div[@class = "video-list-tabc" and not(p[@class = "no-videoList-title"])]/ul/li'
):
item = ZhiboItem()
num = self.webFunc.getNum(
sel.xpath(
'a/div[@class ="info-area"]/div[@class ="meat"]/span/span[@class = "dv"]/text()'
).extract()[0])
if num >= self.webFunc.limit:
item['title'] = sel.xpath(
'a/div[@class="imgBox"]/img/@alt').extract()[0]
item['link'] = "http://www.zhanqi.tv" + sel.xpath(
'a/@href').extract()[0]
item['view'] = num
item['img_url'] = sel.xpath(
'a/div[@class="imgBox"]/img/@src').extract()[0]
item['zhubo'] = sel.xpath(
'a/div[@class ="info-area"]/div[@class ="meat"]/span[@class = "anchor anchor-to-cut dv"]/text()'
).extract()[0]
item['web'] = "zhanqi"
item['cate'] = self.webFunc.getCate(response.url)
# item['active'] = True
yield item