python使用Scrapy库进行数据提取和处理的方法详解

import scrapy
class QuotesSpider(scrapy.Spider):
    name = "quotes"
    start_urls = [
        'http://quotes.toscrape.com/page/1/',
    ]
    def parse(self, response):
        for quote in response.css('div.quote'):
            text = quote.css('span.text::text').get()
            author = quote.css('span small::text').get()
            print(f'Text: {text}, Author: {author}')

import scrapy
class QuoteItem(scrapy.Item):
    text = scrapy.Field()
    author = scrapy.Field()

class QuotesSpider(scrapy.Spider):
    name = "quotes"
    start_urls = [
        'http://quotes.toscrape.com/page/1/',
    ]
    def parse(self, response):
        for quote in response.css('div.quote'):
            item = QuoteItem()
            item['text'] = quote.css('span.text::text').get()
            item['author'] = quote.css('span small::text').get()
            yield item

import json
class JsonWriterPipeline(object):
    def open_spider(self, spider):
        self.file = open('quotes.jl', 'w')
    def close_spider(self, spider):
        self.file.close()
    def process_item(self, item, spider):
        line = json.dumps(dict(item)) + "\n"
        self.file.write(line)
        return item

ITEM_PIPELINES = {
   'tutorial.pipelines.JsonWriterPipeline': 1,
}