Python Scrapy意外缩进错误

Question

We're trying to crawl items such as 'product', 'price', etc. but we keep getting a indentation error.

The code we're using (crawlproduct.py):

from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from productcrawl.items import ProductCrawlItem

class MySpider(BaseSpider):
name = "crawlproduct"
allowed_domains = ["yorcom.nl"]
f = open("items.txt")
start_urls = [url.strip() for url in f.readlines()]
f.close()


def parse(self, response):
hxs = HtmlXPathSelector(response)
events = hxs.select("//div[@class='productOverview']")
items = []
for event in events:
item = ProductCrawlItem()
item ["product"] = events.select("table/tbody/tr/td[@class='productTitle']/a/text()").extract()
item ["price"] = events.select("table/tbody/tr/td[@class='productPrice']/a/text()").extract()
item ["stock"] = events.select("table/tbody/tr/td[@class='productStock   voorraad']/a/text()").extract()
item ["link"] = events.select("table/tbody/tr/td[@class='productTitle']/a").extract()
yield item

and items.py:

from scrapy.item import Item, Field

    class ProductCrawlItem(Item):
        product = Field()
        price = Field()
        stock = Field()
        link = Field()

When we only use 1 field, it does work... Does anyone know the problem?

Thanks in advance,

Dean

Answer 1

With the following indentation, this is probably what you intended:

from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from productcrawl.items import ProductCrawlItem

class MySpider(BaseSpider):
    name = "crawlproduct"
    allowed_domains = ["yorcom.nl"]
    f = open("items.txt")
    start_urls = [url.strip() for url in f.readlines()] 
    f.close()


def parse(self, response):
    hxs = HtmlXPathSelector(response)
    events = hxs.select("//div[@class='productOverview']")
    items = []
    for event in events:
        item = ProductCrawlItem()
        item ["product"] = events.select("table/tbody/tr/td[@class='productTitle']/a/text()").extract()
        item ["price"] = events.select("table/tbody/tr/td[@class='productPrice']/a/text()").extract()
        item ["stock"] = events.select("table/tbody/tr/td[@class='productStock   voorraad']/a/text()").extract()
        item ["link"] = events.select("table/tbody/tr/td[@class='productTitle']/a").extract()
        yield item