在 windows 10 下安装 scrapy ，首先安装好 anaconda , 直接运行 conda install scrapy , anaconda 会帮你解决安装过程所需要的库和文件， 安装成功

安装scrapy

爬取 http://quotes.toscrape.com/ 网址的内容，注意跳转下一页

# quotes.py
# -*- coding: utf-8 -*-
import scrapy

from quotetutorial.items import QuoteItem


class QuotesSpider(scrapy.Spider):
    name = 'quotes'
    allowed_domains = ['quotes.toscrape.com']
    start_urls = ['http://quotes.toscrape.com/']

    def parse(self, response):
        quotes = response.css(".quote")
        for quote in quotes:
            item = QuoteItem()
            text = quote.css('.text::text').extract_first()
            author = quote.css('.author::text').extract_first()
            tags = quote.css('.tags .tag::text').extract()
            item['text'] = text
            item['author'] = author
            item['tags'] = tags
            yield item
        #正则取出下一页的 url
        next = response.css(".pager .next a::attr(href)").extract_first()
        #取出的url是相对路径，用下面函数合成一个绝对 url
        url = response.urljoin(next)
        #设置回调函数，递归传递下一页的url，实现下一页爬取
        yield scrapy.Request(url=url, callback=self.parse)

定义 item 列表处理数据

#items.py
import scrapy


class QuoteItem(scrapy.Item):
    # define the fields for your item here like:
    text = scrapy.Field()
    author = scrapy.Field()
    tags = scrapy.Field()

定义 pipeline ，处理数据

#pipeline.py
import pymongo
from scrapy.exceptions import DropItem


class TextPipeline(object):
    def __init__(self):
        self.limit = 50

    def process_item(self, item, spider):
        if item['text']:
            if len(item['text']) > self.limit:
                item['text'] = item['text'][0:self.limit].rstrip() + '...'
            return item
        else:
            #丢弃Item
            return DropItem('Missing Text')
#定义函数内变量
class MongoPipeline(object):
    def __init__(self, mongo_url, mongo_db):
        self.mongo_url = mongo_url
        self.mongo_db = mongo_db
     #从 setting 中传入设定的 MONGO_URL 和 MONGO_DB，
    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            mongo_url = crawler.settings.get('MONGO_URL'),
            mongo_db = crawler.settings.get('MONGO_DB')
        )
    #当 spider 开始时运行
    def open_spider(self, spider):
        self.client = pymongo.MongoClient(self.mongo_url)
        self.db = self.client[self.mongo_db]
    #存入 mongodb
    def process_item(self, item, spider):
        name = item.__class__.__name__
        self.db[name].insert(dict(item))
        return item
    #当关闭 spider 时运行
    def close_spider(self, spider):
        self.client.close()

setting 文件定义的变量

#setting.py
MONGO_URL = 'localhost'
MONGO_DB = 'quotestutorial'