Scrapy实战：爬取http://quotes.toscrape.com网站数据

import scrapy


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

# -*- 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):
        # print(response.status) # 200
        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

        next = response.css(‘.pager .next a::attr(href)‘).extract_first()  # 获取下一页的相对链接
        url = response.urljoin(next)  # 生成完整的下一页链接
        yield scrapy.Request(url=url, callback=self.parse)  # 把下一页的链接回调给自身再次请求

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html

# 使用的话需要在settings文件中设置


import pymongo as pymongo
from scrapy.exceptions import DropItem


class TextPipeline(object):
    """对输出的item进行进一步的处理"""

    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:
            return DropItem(‘Missing Text!‘)


class MongoPipeline(object):
    """把输出的item保存到MongoDB数据库"""

    def __init__(self, mongo_url, mongo_db):
        self.mongo_uri = mongo_url
        self.mongo_db = mongo_db

    @classmethod
    def from_crawler(cls, crawler):
        """从settings文件获取配置信息"""
        return cls(
            mongo_url=crawler.settings.get(‘MONGO_URI‘),
            mongo_db=crawler.settings.get(‘MONGO_DB‘)
        )

    def open_spider(self, spider):
        """初始化mongodb"""
        self.client = pymongo.MongoClient(self.mongo_uri)
        self.db = self.client[self.mongo_db]  # 为啥用[],而不是()

    def process_item(self, item, spider):
        name = item.__class__.__name__  # 获取item的名称用作表名,也就是QuoteItem
        self.db[name].insert(dict(item))  # 为啥要用dict(item)
        return item

    def close_spider(self, spider):
        self.client.close()

ITEM_PIPELINES = {
   # ‘quotetutorial.pipelines.TextPipeline‘: 300,
   ‘quotetutorial.pipelines.MongoPipeline‘: 400,
}

MONGO_URI = ‘localhost‘
MONGO_DB = ‘quotestutorial‘