python - Scrapy 蜘蛛不包括所有请求的页面

Question

我有一个 Yelp 的 Scrapy 脚本，在大多数情况下，它是有效的。基本上我可以为它提供 Yelp 页面列表，它应该返回所有页面的所有评论。到目前为止的脚本如下:

from scrapy.spider import Spider
from scrapy.selector import Selector
from scrapy.http import Request
import re

from yelp2.items import YelpReviewItem

RESTAURANTS = ['sixteen-chicago']

def createRestaurantPageLinks(self, response):
    reviewsPerPage = 40
    sel = Selector(response)
    totalReviews = int(sel.xpath('//div[@class="rating-info clearfix"]//span[@itemprop="reviewCount"]/text()').extract()[0].strip().split(' ')[0])
    pages = [Request(url=response.url + '?start=' + str(reviewsPerPage*(n+1)), callback=self.parse) for n in range(totalReviews/reviewsPerPage)]
    return pages

class Yelp2aSpider(Spider):
    name = "yelp2a"
    allowed_domains = ["yelp.com"]
    start_urls = ['http://www.yelp.com/biz/%s' % s for s in RESTAURANTS]

    def parse(self, response):
        requests = []

        sel = Selector(response)
        reviews = sel.xpath('//div[@class="review review-with-no-actions"]')
        items = []

        for review in reviews:
            item = YelpReviewItem()
                item['venueName'] = sel.xpath('//meta[@property="og:title"]/@content').extract()
                item['reviewer'] = review.xpath('.//li[@class="user-name"]/a/text()').extract()
                item['reviewerLoc'] = review.xpath('.//li[@class="user-location"]/b/text()').extract()
                item['rating'] = review.xpath('.//meta[@itemprop="ratingValue"]/@content').extract()
                item['reviewDate'] = review.xpath('.//meta[@itemprop="datePublished"]/@content').extract()
                item['reviewText'] = review.xpath('.//p[@itemprop="description"]/text()').extract()
                item['url'] = response.url
                items.append(item)
        return items

        if response.url.find('?start=') == -1:
            requests += createRestaurantPageLinks(self, response)
            return requests

但是，我遇到的问题是这个特定的脚本会抓取每个请求的评论的每一页，除了第一页。如果我注释掉最后一个“if”语句，它只会抓取第一页。我怀疑我所需要的只是一个简单的“else”命令，但我很困惑……非常感谢帮助!

编辑:这是目前基于收到的帮助的代码...

from scrapy.spider import Spider
from scrapy.selector import Selector
from scrapy.http import Request
import re

from yelp2.items import YelpReviewItem

RESTAURANTS = ['sixteen-chicago']

def createRestaurantPageLinks(self, response):
    reviewsPerPage = 40
    sel = Selector(response)
    totalReviews = int(sel.xpath('//div[@class="rating-info clearfix"]//span[@itemprop="reviewCount"]/text()').extract()[0].strip().split(' ')[0])
    pages = [Request(url=response.url + '?start=' + str(reviewsPerPage*(n+1)), callback=self.parse) for n in range(totalReviews/reviewsPerPage)]
    return pages

class Yelp2aSpider(Spider):
    name = "yelp2a"
    allowed_domains = ["yelp.com"]
    start_urls = ['http://www.yelp.com/biz/%s' % s for s in RESTAURANTS]

    def parse(self, response):
        requests = []

        sel = Selector(response)
        reviews = sel.xpath('//div[@class="review review-with-no-actions"]')
        items = []

        for review in reviews:
            item = YelpReviewItem()
            item['venueName'] = sel.xpath('//meta[@property="og:title"]/@content').extract()
            item['reviewer'] = review.xpath('.//li[@class="user-name"]/a/text()').extract()
            item['reviewerLoc'] = review.xpath('.//li[@class="user-location"]/b/text()').extract()
            item['rating'] = review.xpath('.//meta[@itemprop="ratingValue"]/@content').extract()
            item['reviewDate'] = review.xpath('.//meta[@itemprop="datePublished"]/@content').extract()
            item['reviewText'] = review.xpath('.//p[@itemprop="description"]/text()').extract()
            item['url'] = response.url
        yield item

        if response.url.find('?start=') == -1:
            requests += createRestaurantPageLinks(self, response)
            for request in requests:
                    yield request

正如下面的评论中提到的，按原样运行此代码会抓取每个所需的页面，但它每个页面只返回一条评论，而不是所有评论。

我尝试更改 yield item至 yield items , 但错误消息 ERROR: Spider must return Request, BaseItem or None, got 'list' in <GET http://www.yelp.com/biz/[...]>为抓取的每个 URL 返回。

Answer 1

您需要重新组织一下方法。首先在 parse() 方法中解析餐厅页面。然后，返回评论请求并以另一种方法处理响应，例如parse_review():

import re

from scrapy.item import Item, Field
from scrapy.spider import Spider
from scrapy.selector import Selector
from scrapy.http import Request

from yelp2.items import YelpReviewItem


RESTAURANTS = ['sixteen-chicago']

class Yelp2aSpider(Spider):
    name = "yelp2a"
    allowed_domains = ["yelp.com"]
    start_urls = ['http://www.yelp.com/biz/%s' % s for s in RESTAURANTS]

    def parse(self, response):
        reviewsPerPage = 40
        sel = Selector(response)
        totalReviews = int(sel.xpath('//div[@class="rating-info clearfix"]//span[@itemprop="reviewCount"]/text()').extract()[0].strip().split(' ')[0])
        pages = [Request(url=response.url + '?start=' + str(reviewsPerPage*(n+1)), callback=self.parse_review) for n in range(totalReviews/reviewsPerPage)]
        return pages

    def parse_review(self, response):
        sel = Selector(response)
        reviews = sel.xpath('//div[@class="review review-with-no-actions"]')
        for review in reviews:
            item = YelpReviewItem()
            item['venueName'] = sel.xpath('//meta[@property="og:title"]/@content').extract()
            item['reviewer'] = review.xpath('.//li[@class="user-name"]/a/text()').extract()
            item['reviewerLoc'] = review.xpath('.//li[@class="user-location"]/b/text()').extract()
            item['rating'] = review.xpath('.//meta[@itemprop="ratingValue"]/@content').extract()
            item['reviewDate'] = review.xpath('.//meta[@itemprop="datePublished"]/@content').extract()
            item['reviewText'] = review.xpath('.//p[@itemprop="description"]/text()').extract()
            item['url'] = response.url
            yield item