scrapy tutorial

1class SuperSpider(CrawlSpider):
2    name = 'spider'
3    allowed_domains = ['quotes.toscrape.com']
4    start_urls = ['http://quotes.toscrape.com/']
5    base_url = 'http://quotes.toscrape.com'
6    rules = [Rule(LinkExtractor(allow = 'page/', deny='tag/'),
7                  callback='parse_filter_book', follow=True)]
8 
9    def parse_filter_book(self, response):
10        for quote in response.css('div.quote'):
11            yield {
12                'Author': quote.xpath('.//span/a/@href').get(),
13                'Quote': quote.xpath('.//span[@class= "text"]/text()').get(),
14

1scrapy startproject projectname

1# -*- coding: utf-8 -*-
2import scrapy
3
4
5class AliexpressTabletsSpider(scrapy.Spider):
6    name = 'aliexpress_tablets'
7    allowed_domains = ['aliexpress.com']
8    start_urls = ['https://www.aliexpress.com/category/200216607/tablets.html',
9                 'https://www.aliexpress.com/category/200216607/tablets/2.html?site=glo&g=y&tag=']
10
11
12    def parse(self, response):
13
14        print("procesing:"+response.url)
15        #Extract data using css selectors
16        product_name=response.css('.product::text').extract()
17        price_range=response.css('.value::text').extract()
18        #Extract data using xpath
19        orders=response.xpath("//em[@title='Total Orders']/text()").extract()
20        company_name=response.xpath("//a[@class='store $p4pLog']/text()").extract()
21
22        row_data=zip(product_name,price_range,orders,company_name)
23
24        #Making extracted data row wise
25        for item in row_data:
26            #create a dictionary to store the scraped info
27            scraped_info = {
28                #key:value
29                'page':response.url,
30                'product_name' : item[0], #item[0] means product in the list and so on, index tells what value to assign
31                'price_range' : item[1],
32                'orders' : item[2],
33                'company_name' : item[3],
34            }
35
36            #yield or give the scraped info to scrapy
37            yield scraped_info
38