Question

我一直在线学习一些教程，使用Scrapy来废弃Craigslist的电子邮件。我有这个代码，但是当我运行命令并导出到json文件时，它会创建文件但是唯一的东西就是单个'['。

非常感谢任何帮助。以下是我的代码：

from scrapy.spider import BaseSpider 
from scrapy.selector import HtmlXPathSelector 
from scrapy_demo.items import ScrapyDemoItem
import urlparse 
from scrapy.http.request import Request

class ScrapyDemoSpider(BaseSpider): 
    name = "scrapy_demo"
    allowed_domains = ["buffalo.craigslist.org"]
    start_urls = ['http://buffalo.craigslist.org/search/cps/']

    def parse(self, response):
        hxs = HtmlXPathSelector(response) 
        listings = hxs.select('//....') 
        links = []

        #scrap listings page to get listing links
        for listing in listings:
            link = listing.select('..../@href').extract()[0]
            links.append(link)

        #parse listing url to get content of the listing page
        for link in links:
            item = ScrapyDemoItem()
            item['link'] = link
            yield Request(urlparse.urljoin(response.url, link), meta={'item': item}, callback=self.parse_listing_page)

            #get next button link
            next_page = hxs.select("//..../@href").extract()[0]
            if next_page:
                yield Request(urlparse.urljoin(response.url, next_page), self.parse)

    #scrap listing page to get content
    def parse_listing_page(self, response):
        hxs = HtmlXPathSelector(response)
        item = response.request.meta['item']
        item['title'] = hxs.select('//..../text()').extract()[0]
        item['content'] = hxs.select('//..../text()').extract()[0]
        yield item

Answer 1

这里有多个问题。

主要问题是select()调用中的无效表达式。

除此之外：

使用response.xpath()或response.css()不再需要HtmlXPathSelector
无需在Item回调中实例化parse()个实例并传入meta。在response.url回拨

parse_listing_page()

改进了工作代码：

import urlparse

from scrapy.spider import BaseSpider
from scrapy.http.request import Request

from scrapy_demo.items import ScrapyDemoItem


class ScrapyDemoSpider(BaseSpider): 
    name = "scrapy_demo"
    allowed_domains = ["buffalo.craigslist.org"]
    start_urls = ['http://buffalo.craigslist.org/search/cps/']

    def parse(self, response):
        # processing listings
        for listing in response.css('p.row > a[data-id]'):
            link = listing.xpath('@href').extract()[0]
            yield Request(urlparse.urljoin(response.url, link), callback=self.parse_listing_page)

        # following next page
        next_page = response.xpath('//a[contains(@class, "next")]/@href').extract()
        print next_page
        if next_page:
            yield Request(urlparse.urljoin(response.url, next_page[0]), callback=self.parse)

    def parse_listing_page(self, response):
        item = ScrapyDemoItem()
        item['link'] = response.url
        item['title'] = response.xpath('//title/text()').extract()[0].strip()
        item['content'] = response.xpath('//section[@id="postingbody"]/text()').extract()[0].strip()
        yield item

如果你运行蜘蛛，那么在输出JSON文件中，你会看到：

[
    {"content": "Using a web cam with your computer to video communicate with your loved ones has never been made easier and it's free (providing you have an Internet connection).  With the click of a few buttons, you are sharing your live video and audio with the person you are communicating with. It's that simple.  When you are seeing and hearing your grand kids live across the country or halfway around the world, web camming is the next best thing to being there!", "link": "http://buffalo.craigslist.org/cps/4784390462.html", "title": "Web Cam With Your Computer With Family And Friends"},
    {"content": "Looking to supplement or increase your earnings?", "link": "http://buffalo.craigslist.org/cps/4782757517.html", "title": "1k in 30 Day's"},
    {"content": "Like us on Facebook: https://www.facebook.com/pages/NFB-Systems/514380315268768", "link": "http://buffalo.craigslist.org/cps/4813039886.html", "title": "NFB SYSTEMS COMPUTER SERVICES + WEB DESIGNING"},
    {"content": "Like us on Facebook: https://www.facebook.com/pages/NFB-Systems/514380315268768", "link": "http://buffalo.craigslist.org/cps/4810219714.html", "title": "NFB Systems Computer Repair + Web Designing"},
    {"content": "I can work with you personally and we design your site together (no outsourcing or anything like that!) I'll even train you how to use your brand new site. (Wordpress is really easy to use once it is setup!)", "link": "http://buffalo.craigslist.org/cps/4792628034.html", "title": "I Make First-Class Wordpress Sites with Training"},
    ...
]

Scrapy JSON导出问题

1 个答案: