Scrapy 不收集数据

Question

我正在使用 scrapy 从 craiglist 收集一些电子邮件，当我运行它 returns .csv 文件中的空白行。我能够提取标题、标签和 link。只有电子邮件是问题所在。这是代码：

 # -*- coding: utf-8 -*-
import re
import scrapy
from scrapy.http import Request


# item class included here
class DmozItem(scrapy.Item):
    # define the fields for your item here like:
    link = scrapy.Field()
    attr = scrapy.Field()
    title = scrapy.Field()
    tag = scrapy.Field()

class DmozSpider(scrapy.Spider):
    name = "dmoz"
    allowed_domains = ["craigslist.org"]
    start_urls = [
    "http://raleigh.craigslist.org/bab/5038434567.html"
    ]

    BASE_URL = 'http://raleigh.craigslist.org/'

    def parse(self, response):
        links = response.xpath('//a[@class="hdrlnk"]/@href').extract()
        for link in links:
            absolute_url = self.BASE_URL + link
            yield scrapy.Request(absolute_url, callback=self.parse_attr)

    def parse_attr(self, response):
        match = re.search(r"(\w+)\.html", response.url)
        if match:
            item_id = match.group(1)
            url = self.BASE_URL + "reply/nos/vgm/" + item_id

            item = DmozItem()
            item["link"] = response.url
            item["title"] = "".join(response.xpath("//span[@class='postingtitletext']//text()").extract())
            item["tag"] = "".join(response.xpath("//p[@class='attrgroup']/span/b/text()").extract()[0])
            return scrapy.Request(url, meta={'item': item}, callback=self.parse_contact)

    def parse_contact(self, response):
        item = response.meta['item']
        item["attr"] = "".join(response.xpath("//div[@class='anonemail']//text()").extract())
        return item

Answer 1

首先，您想要 start_urls 在目录页面：http://raleigh.craigslist.org/search/bab。

此外，据我了解，接收电子邮件的额外请求应该发送至 reply/ral/bab/ 而不是 reply/nos/vgm/。

此外，如果没有 attr 组，您会在以下行收到错误消息：

item["tag"] = "".join(response.xpath("//p[@class='attrgroup']/span/b/text()").extract()[0])

替换为：

item["tag"] = "".join(response.xpath("//p[@class='attrgroup']/span/b/text()").extract())

对我有用的完整代码：

# -*- coding: utf-8 -*-
import re
import scrapy


class DmozItem(scrapy.Item):
    # define the fields for your item here like:
    link = scrapy.Field()
    attr = scrapy.Field()
    title = scrapy.Field()
    tag = scrapy.Field()


class DmozSpider(scrapy.Spider):
    name = "dmoz"
    allowed_domains = ["raleigh.craigslist.org"]
    start_urls = [
        "http://raleigh.craigslist.org/search/bab"
    ]

    BASE_URL = 'http://raleigh.craigslist.org/'

    def parse(self, response):
        links = response.xpath('//a[@class="hdrlnk"]/@href').extract()
        for link in links:
            absolute_url = self.BASE_URL + link
            yield scrapy.Request(absolute_url, callback=self.parse_attr)

    def parse_attr(self, response):
        match = re.search(r"(\w+)\.html", response.url)
        if match:
            item_id = match.group(1)
            url = self.BASE_URL + "reply/ral/bab/" + item_id

            item = DmozItem()
            item["link"] = response.url
            item["title"] = "".join(response.xpath("//span[@class='postingtitletext']//text()").extract())
            item["tag"] = "".join(response.xpath("//p[@class='attrgroup']/span/b/text()").extract())
            return scrapy.Request(url, meta={'item': item}, callback=self.parse_contact)

    def parse_contact(self, response):
        item = response.meta['item']
        item["attr"] = "".join(response.xpath("//div[@class='anonemail']//text()").extract())
        return item

Scrapy 不收集数据

Scrapy not collecting data

python

web-crawler

scrapy

web-scraping