def parse_day(self, response):
node_list = response.xpath("//div[@class='row']//tbody/tr")
city_name = response.xpath("//h2[@id='title']/text()").extract_first()
if not len(node_list):
return
node_list.pop(0)
for node in node_list:
item = AqiItem()
#item["city"] = response.meta["city"]
item["city"] = city_name
item["date"] = node.xpath("./td[1]//text()").extract_first()
item["aqi"] = node.xpath("./td[2]//text()").extract_first()
item["level"] = node.xpath("./td[3]//text()").extract_first()
item["pm2_5"] = node.xpath("./td[4]//text()").extract_first()
item["pm10"] = node.xpath("./td[5]//text()").extract_first()
item["so2"] = node.xpath("./td[6]//text()").extract_first()
item["co"] = node.xpath("./td[7]//text()").extract_first()
item["no2"] = node.xpath("./td[8]//text()").extract_first()
item["o3"] = node.xpath("./td[9]//text()").extract_first()
yield item
def parse_day(self, response):
item = AqiItem()
# 解析 标题 在提取城市名字
title = response.xpath('//*[@id="title"]/text()').extract_first()
item['city_name'] = title[8:-11]
# 1. 取出所有 tr_list
tr_list = response.xpath('//tr')
# 2.删除表头
tr_list.pop(0)
for tr in tr_list:
# 日期
item['date'] = tr.xpath('./td[1]/text()').extract_first()
# AQI
item['aqi'] = tr.xpath('./td[2]/text()').extract_first()
# 质量等级
item['level'] = tr.xpath('./td[3]//text()').extract_first()
# PM2.5
item['pm2_5'] = tr.xpath('./td[4]/text()').extract_first()
# PM10
item['pm10'] = tr.xpath('./td[5]/text()').extract_first()
# 二氧化硫
item['so_2'] = tr.xpath('./td[6]/text()').extract_first()
# 一氧化碳
item['co'] = tr.xpath('./td[7]/text()').extract_first()
# 二氧化氮
item['no_2'] = tr.xpath('./td[8]/text()').extract_first()
# 臭氧
item['o3'] = tr.xpath('./td[9]/text()').extract_first()
# 将数据 -->engine-->pipeline
yield item