学习scrapy使用

运行scrapy 中的spider 

新建run.py

from scrapy import cmdline
cmdline.execute("scrapy crawl tq".split(" "))

判断获取元素的类型

print(type(sevenday(对象)))

获取对象中所有数据 对象.getall(); 对象.get()中的第一元素

组装数组：

在items中组装字段

import scrapy
from ..items import TqybItem
class TqSpider(scrapy.Spider):
    name = 'tq'
    allowed_domains = ['weather.com.cn']
    start_urls = ['http://www.weather.com.cn/weather/101010100.shtml']

    def parse(self, response):
        #print(response.text)
        sevendays = response.xpath('//div[@class="con today clearfix"]//div[@id="7d"]//h1/text()').getall()
        #print(type(sevendays))
        for sevenday in sevendays:
            day = sevenday
            print(type(sevenday))
            item = TqybItem(day=day)
            yield item #发给pipelines

yield item 发给管道