python - Scrapy:自定义回调不起作用

Question

我不知道为什么我的蜘蛛不工作!我绝对不是一名程序员，所以请善待我!哈哈

背景: 我正在尝试使用“Scrapy”抓取与 Indigo 上找到的书籍相关的信息。

问题: 我的代码没有输入任何自定义回调...它似乎仅在我使用“解析”作为回调时才起作用。

如果我将代码的“规则”部分中的回调从“parse_books”更改为“parse”，那么我列出所有链接的列表的方法就可以正常工作并打印出所有链接我感兴趣的链接。但是，该方法中的回调(指向“parse_books”)永远不会被调用!奇怪的是，如果我将“parse”方法重命名为其他方法(即 ->“testmethod”)，然后将“parse_books”方法重命名为“parse”，我将在该方法中抓取信息放入元素中效果很好!

我想要实现的目标: 我想做的就是输入一个页面，比如说“畅销书”，导航到所有项目的相应项目级页面，并抓取所有与书籍相关的信息。我似乎这两件事都是独立工作的:/

代码!

import scrapy
import json
import urllib
from scrapy.http import Request
from urllib import urlencode
import re
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
import urlparse



from TEST20160709.items import IndigoItem
from TEST20160709.items import SecondaryItem



item = IndigoItem()
scrapedItem = SecondaryItem()

class IndigoSpider(CrawlSpider):

    protocol='https://'
    name = "site"
    allowed_domains = [
    "chapters.indigo.ca/en-ca/Books",
    "chapters.indigo.ca/en-ca/Store/Availability/"
    ]

    start_urls = [
         'https://www.chapters.indigo.ca/en-ca/books/bestsellers/',
    ]

    #extractor = SgmlLinkExtractor()s

    rules = (
    Rule(LinkExtractor(), follow = True),
    Rule(LinkExtractor(), callback = "parse_books", follow = True),
    )



    def getInventory (self, bookID):
        params ={
       'pid' : bookID,
       'catalog' : 'books'
        }
        yield Request(
            url="https://www.chapters.indigo.ca/en-ca/Store/Availability/?" + urlencode(params),
            dont_filter = True,
            callback = self.parseInventory
        )



    def parseInventory(self,response):
        dataInventory = json.loads(response.body)

        for entry in dataInventory ['Data']:
            scrapedItem['storeID'] = entry['ID']
            scrapedItem['storeType'] = entry['StoreType']
            scrapedItem['storeName'] = entry['Name']
            scrapedItem['storeAddress'] = entry['Address']
            scrapedItem['storeCity'] = entry['City']
            scrapedItem['storePostalCode'] = entry['PostalCode']
            scrapedItem['storeProvince'] = entry['Province']
            scrapedItem['storePhone'] = entry['Phone']
            scrapedItem['storeQuantity'] = entry['QTY']
            scrapedItem['storeQuantityMessage'] = entry['QTYMsg']
            scrapedItem['storeHours'] = entry['StoreHours']
            scrapedItem['storeStockAvailibility'] = entry['HasRetailStock']
            scrapedItem['storeExclusivity'] = entry['InStoreExlusive']

            yield scrapedItem



    def parse (self, response):
        #GET ALL PAGE LINKS
        all_page_links = response.xpath('//ul/li/a/@href').extract()
        for relative_link in all_page_links:
            absolute_link = urlparse.urljoin(self.protocol+"www.chapters.indigo.ca",relative_link.strip())
            absolute_link = absolute_link.split("?ref=",1)[0]
            request = scrapy.Request(absolute_link, callback=self.parse_books)
            print "FULL link: "+absolute_link

            yield Request(absolute_link, callback=self.parse_books)





    def parse_books (self, response):

        for sel in response.xpath('//form[@id="aspnetForm"]/main[@id="main"]'):
            #XML/HTTP/CSS ITEMS
            item['title']= map(unicode.strip, sel.xpath('div[@class="content-wrapper"]/div[@class="product-details"]/div[@class="col-2"]/section[@id="ProductDetails"][@class][@role][@aria-labelledby]/h1[@id="product-title"][@class][@data-auto-id]/text()').extract())
            item['authors']= map(unicode.strip, sel.xpath('div[@class="content-wrapper"]/div[@class="product-details"]/div[@class="col-2"]/section[@id="ProductDetails"][@class][@role][@aria-labelledby]/h2[@class="major-contributor"]/a[contains(@class, "byLink")][@href]/text()').extract())
            item['productSpecs']= map(unicode.strip, sel.xpath('div[@class="content-wrapper"]/div[@class="product-details"]/div[@class="col-2"]/section[@id="ProductDetails"][@class][@role][@aria-labelledby]/p[@class="product-specs"]/text()').extract())
            item['instoreAvailability']= map(unicode.strip, sel.xpath('//span[@class="stockAvailable-mesg negative"][@data-auto-id]/text()').extract())
            item['onlinePrice']= map(unicode.strip, sel.xpath('//span[@id][@class="nonmemberprice__specialprice"]/text()').extract())
            item['listPrice']= map(unicode.strip, sel.xpath('//del/text()').extract())

            aboutBookTemp = map(unicode.strip, sel.xpath('//div[@class="read-more"]/p/text()').extract())
            item['aboutBook']= [aboutBookTemp]

            #Retrieve ISBN Identifier and extract numeric data
            ISBN_parse = map(unicode.strip, sel.xpath('(//div[@class="isbn-info"]/p[2])[1]/text()').extract())
            item['ISBN13']= [elem[11:] for elem in ISBN_parse]
            bookIdentifier = str(item['ISBN13'])
            bookIdentifier = re.sub("[^0-9]", "", bookIdentifier)


            print "THIS IS THE IDENTIFIER:" + bookIdentifier

            if bookIdentifier:
                yield self.getInventory(str(bookIdentifier))

            yield item

Answer 1

我注意到的第一个问题是您的 allowed_domains 类属性已损坏。它应该包含域(因此得名)。

您的情况下的正确值是:

allowed_domains = [
    "chapters.indigo.ca",  # subdomain.domain.top_level_domain
]

如果您检查蜘蛛日志，您会看到:

DEBUG: Filtered offsite request to 'www.chapters.indigo.ca'

这不应该发生。