Scrapy does not write data to a file

问题

He created a spider in Scrapy: items.py:

from scrapy.item import Item, Field

class dns_shopItem (Item):
     # Define the fields for your item here like:
     # Name = Field ()
     id = Field ()
     idd = Field ()

dns_shop_spider.py:

from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.loader.processor import TakeFirst
from scrapy.contrib.loader import XPathItemLoader
from scrapy.selector import HtmlXPathSelector
from dns_shop.items import dns_shopItem
 
class dns_shopLoader (XPathItemLoader):
     default_output_processor = TakeFirst ()
 
class dns_shopSpider (CrawlSpider):
    name = "dns_shop_spider"
    allowed_domains = ["www.playground.ru"]
    start_urls = ["http://www.playground.ru/files/stalker_clear_sky/"]
    rules = (
    Rule (SgmlLinkExtractor (allow = ('/ files / s_t_a_l_k_e_r_chistoe_nebo')), follow = True),
    Rule (SgmlLinkExtractor (allow = ('/ files / s_t_a_l_k_e_r_chistoe_nebo')), callback = 'parse_item'),
    )

    def parse_item (self, response):
        hxs = HtmlXPathSelector (response)
        l = dns_shopLoader (dns_shopItem (), hxs)
        l.add_xpath ('id', "/ html / body / table [2] / tbody / tr [5] / td [2] / table / tbody / tr / td / div [6] / h1/text ()" )
        l.add_xpath ('idd', "/ / html / body / table [2] / tbody / tr [5] / td [2] / table / tbody / tr / td / div [6] / h1/text () ")
        return l.load_item ()

Run the following command:

scrapy crawl dns_shop_spider-o scarped_data_utf8.csv-t csv

This log shows that Scrapy through all the necessary url, but why not write to the specified file when you start the spider. In what could be the problem?

回答1:

Assuming you want to follow all links on the page http://www.playground.ru/files/stalker_clear_sky/ and get titles, urls and links for downloading:

from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.loader.processor import TakeFirst
from scrapy.contrib.loader import XPathItemLoader
from scrapy.selector import HtmlXPathSelector

from scrapy.item import Item, Field


class PlayGroundItem(Item):
    title = Field()
    url = Field()
    download_url = Field()


class PlayGroundLoader(XPathItemLoader):
    default_output_processor = TakeFirst()


class PlayGroundSpider(CrawlSpider):
    name = "playground_spider"
    allowed_domains = ["www.playground.ru"]
    start_urls = ["http://www.playground.ru/files/stalker_clear_sky/"]
    rules = (
        Rule(SgmlLinkExtractor(allow=('/files/s_t_a_l_k_e_r_chistoe_nebo')), follow=True, callback='parse_item'),
    )


    def parse_item(self, response):
        hxs = HtmlXPathSelector(response)
        l = PlayGroundLoader(PlayGroundItem(), hxs)
        l.add_value('url', response.url)
        l.add_xpath('title', "//div[@class='downloads-container clearfix']/h1/text()")
        l.add_xpath('download_url', "//div[@class='files-download-holder']/div/a/@href")

        return l.load_item()

Save it to the spider.py and run via:

scrapy runspider test_scrapy.py -o output.json

Then check output.json.

Hope that helps.

来源：https://stackoverflow.com/questions/16751323/scrapy-does-not-write-data-to-a-file

标签

python

parsing

scrapy

sites