我的代码有问题，这不是从websi中删除数据

Question

我想在https://www.johnlewis.com/中搜集一些类别。我可以获取的类别的网址，但我不能从网站上刮数据

# -*- coding: utf-8 -*-
import scrapy
from ..items import ExperimentItem


class ExperimenSpider(scrapy.Spider):
    name = 'experimen'
    allowed_domains = ['www.johnlewis.com']
    start_urls = [
        # firsttest
        'https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/android/_/N-5nlvZ1z0ww04',
        'https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/windows-10/_/N-5nlvZ1z0i0qv',
        'https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/fire-os/_/N-5nlvZ1z0w8jv'
    ]

    def parse(self, response):
        global productCategory
        global productSubCategory
        products = response.css('.product-list-heading::text').extract_first()
        currentUrl = response.request.url
        items = ExperimentItem()

        androidTablets = 'https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/android/_/N-5nlvZ1z0ww04',
        windowTablets = 'https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/windows-10/_/N-5nlvZ1z0i0qv',
        fireOs = 'https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/fire-os/_/N-5nlvZ1z0w8jv'

        for product in products:
            if androidTablets in currentUrl:
                productCategory = 'Electric'
                productCategory = 'tablets'
            elif windowTablets in currentUrl:
                productCategory = 'Electric'
                productCategory = 'tablets'
            elif fireOs in currentUrl:
                productCategory = 'Electric'
                productCategory = 'tablets'

            productCountry = 'uk'
            productSeller = 'John Lewis'
            productLink = 'https://www.johnlewis.com' + response.css('.product-card__wrap-link::attr(href)').extract_first()
            productTitle = response.css('.product-card__title-inner::text').extract_first()
            productImage = response.css('.product-card__image::attr(src)').extract_first()
            productStandardPrice = response.css('.product-card__price-span::text').extract_first()
            productSalePrice = response.css('.product-card__price-span--discounted::text').extract_first()

            items['productCategory'] = productCategory
            items['productSubCategory'] = productSubCategory
            items['productCountry'] = productCountry
            items['productSeller'] = productSeller
            items['productLink'] = productLink
            items['productTitle'] = productTitle
            items['productImage'] = productImage
            items['productStandardPrice'] = productStandardPrice
            items['productSalePrice'] = productSalePrice

            yield items    

我得到的错误是：

2019-10-11 14:50:37 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/fire-os/_/N-5nlvZ1z0w8jv> (referer: None)
2019-10-11 14:50:37 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/android/_/N-5nlvZ1z0ww04> (referer: None)
2019-10-11 14:50:37 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/windows-10/_/N-5nlvZ1z0i0qv> (referer: None)
2019-10-11 14:50:37 [scrapy.core.scraper] ERROR: Spider error processing <GET https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/fire-os/_/N-5nlvZ1z0w8jv> (referer: None)
Traceback (most recent call last):
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\utils\defer.py", line 102, in iter_errback
    yield next(it)
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\offsite.py", line 29, in process_spider_output
    for x in result:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\referer.py", line 339, in <genexpr>
    return (_set_referer(r) for r in result or ())
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\urllength.py", line 37, in <genexpr>
    return (r for r in result or () if _filter(r))
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\depth.py", line 58, in <genexpr>
    return (r for r in result or () if _filter(r))
  File "C:\Users\Tobi Fafowora\Desktop\scrapy\experiment\experiment\spiders\experimen.py", line 29, in parse
    if androidTablets in currentUrl:
TypeError: 'in <string>' requires string as left operand, not tuple
2019-10-11 14:50:37 [scrapy.core.scraper] ERROR: Spider error processing <GET https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/android/_/N-5nlvZ1z0ww04> (referer: None)
Traceback (most recent call last):
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\utils\defer.py", line 102, in iter_errback
    yield next(it)
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\offsite.py", line 29, in process_spider_output
    for x in result:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\referer.py", line 339, in <genexpr>
    return (_set_referer(r) for r in result or ())
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\urllength.py", line 37, in <genexpr>
    return (r for r in result or () if _filter(r))
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\depth.py", line 58, in <genexpr>
    return (r for r in result or () if _filter(r))
  File "C:\Users\Tobi Fafowora\Desktop\scrapy\experiment\experiment\spiders\experimen.py", line 29, in parse
    if androidTablets in currentUrl:
TypeError: 'in <string>' requires string as left operand, not tuple
2019-10-11 14:50:37 [scrapy.core.scraper] ERROR: Spider error processing <GET https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/windows-10/_/N-5nlvZ1z0i0qv> (referer: None)
Traceback (most recent call last):
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\utils\defer.py", line 102, in iter_errback
    yield next(it)
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\offsite.py", line 29, in process_spider_output
    for x in result:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\referer.py", line 339, in <genexpr>
    return (_set_referer(r) for r in result or ())
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\urllength.py", line 37, in <genexpr>
    return (r for r in result or () if _filter(r))
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\core\spidermw.py", line 84, in evaluate_iterable
    for r in iterable:
  File "c:\users\tobi fafowora\anaconda3\lib\site-packages\scrapy\spidermiddlewares\depth.py", line 58, in <genexpr>
    return (r for r in result or () if _filter(r))
  File "C:\Users\Tobi Fafowora\Desktop\scrapy\experiment\experiment\spiders\experimen.py", line 29, in parse
    if androidTablets in currentUrl:`
TypeError: 'in <string>' requires string as left operand, not tuple
2019-10-11 14:50:37 [scrapy.core.engine] INFO: Closing spider (finished)

Answer 1

这是一个简单的解决方案，在这些行的末尾有逗号：

androidTablets = 'https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/android/_/N-5nlvZ1z0ww04',
windowTablets = 'https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/windows-10/_/N-5nlvZ1z0i0qv',
fireOs = 'https://www.johnlewis.com/browse/electricals/ipad-tablets/view-all-tablets/fire-os/_/N-5nlvZ1z0w8jv'

这使它们变成tuples而不是字符串。您的错误告诉您您正在询问tuple中的string。去掉这两个逗号，问题就解决了。你知道吗