刮除蜘蛛，不包括所有请求的页面

Question

我为Yelp编写了一个Scrapy脚本，这在很大程度上是在工作。从本质上说，我可以提供一个Yelp页面列表，它应该返回所有页面的所有评论。到目前为止，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，除了第一页之外，这个特定的脚本会刮掉每个请求的评论的每一页。如果我注释掉最后一个" If“语句，它只会擦伤第一页。我想我只需要一个简单的“否则”命令，但我很困惑.我们非常感谢你的帮助！

编辑：，这是目前基于收到的援助的代码.

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

正如下面的注释中所提到的，运行这段代码是为了爬行每一个想要的页面，但是它只返回每个页面的一个评论，而不是所有的。

我尝试将yield item更改为yield items，但是对于每个爬行的URL，都会返回ERROR: Spider must return Request, BaseItem or None, got 'list' in <GET http://www.yelp.com/biz/[...]>的错误消息。

Answer 1

最后的答案确实在于一条yield行的缩进。这是代码，最终完成了我需要它做的事情。

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 YelpXSpider(Spider):
    name = "yelpx"
    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

感谢大家的帮助！

Answer 2

您需要稍微重新组织这些方法。首先在parse()方法中解析餐厅页面。然后，返回对评审的请求，并在另一种方法中处理响应，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

Answer 3

如果您在多个地方返回项/请求，则应该用return语句替换您的yield语句，这些语句会将您的函数转换为生成器，该生成器每次生成它时都会返回一个新元素(产生它)，而不会退出该函数，直到它们全部返回。否则，就像现在的代码一样，您的函数将在第一个return之后退出，不会发送以下页面的请求。

编辑:更正-您应该一次生成一个项目/请求，因此：

替换

for review in reviews:
    item = ...
return items

使用

for review in reviews:
    item = ...
    yield item

并替换

return requests

使用

for request in requests:
    yield request