对空气质量历史数据的爬取

爬取https://www.aqistudy.cn/historydata 网站的空气质量报告，爬取的数据以csv文件生成

scrapy startproject air_quality 创建scrapy项目

scrapy genspider api_history_spider https://www.apistudy.cn/historydata/index.php 编写spider

文件目录如图所示

seetings.py

1 ITEM_PIPELINES = {
2     'air_quality.pipelines.AirQualityPipeline': 300,
3 }

items.py

 1 import scrapy
 2 
 3 
 4 class AirQualityItem(scrapy.Item):
 5     # define the fields for your item here like:
 6     # name = scrapy.Field()
 7     city_name = scrapy.Field()  # 城市名称
 8     record_date = scrapy.Field()  # 检测日期
 9     aqi_val = scrapy.Field()  # AQI
10     range_val = scrapy.Field()  # 范围
11     quality_level = scrapy.Field()  # 质量等级
12     pm2_5_val = scrapy.Field()  # PM2.5
13     pm10_val = scrapy.Field()  # PM10
14     so2_val = scrapy.Field()  # SO2
15     co_val = scrapy.Field()  # CO
16     no2_val = scrapy.Field()  # NO2
17     o3_val = scrapy.Field()  # O3
18     rank = scrapy.Field()  # 排名

pipelines.py

 1 from scrapy.exporters import CsvItemExporter
 2 
 3 class AirQualityPipeline(object):
 4 
 5     def open_spider(se