Not sure how to use scrapy's itemLoaders - scrapy

Question

I'm trying to learn how to use scrappy's itemLoaders, can anybody told me what am I doing wrong???I would like to thank you in advance.
import scrapy
from items.items import ItemsItem
from scrapy.loader import ItemLoader
class ItemspiderSpider(scrapy.Spider):
name = 'itemspider'
allowed_domains = ['yellowpages.com']
start_urls = ['https://www.yellowpages.com/search?search_terms=handyman&geo_location_terms=Miami%2C+FL']
def parse(self, response):
#create the loader using the response
l = ItemLoader(item=ItemsItem(), response=response)
#create a for loop
for listing in response.css('div.search-results.organic div.srp-listing'):
l.add_css('Name', listing.css('a.business-name span::text').extract())
l.add_css('Details', response.urljoin(listing.css('a.business-name::attr(href)')))
l.add_css('WebSite', listing.css('a.track-visit-website::attr(href)').extract_first())
l.add_css('Phones', listing.css('div.phones::text').extract())
yield l.load_item()
When I run the code I keep getting this error:
root#debian:~/Desktop/items/items/spiders# scrapy runspider itemspider.py -o item.csv
/usr/local/lib/python3.5/dist-packages/scrapy/spiderloader.py:37: UserWarning: There are several spiders with the same name:
ItemspiderSpider named 'itemspider' (in items.spiders.itemspider)
ItemspiderSpider named 'itemspider' (in items.spiders.itemspiderLog)
This can cause unexpected behavior.
warnings.warn(msg, UserWarning)
2017-07-04 16:33:20 [scrapy.utils.log] INFO: Scrapy 1.4.0 started (bot: items)
2017-07-04 16:33:20 [scrapy.utils.log] INFO: Overridden settings: {'BOT_NAME': 'items', 'FEED_FORMAT': 'csv', 'SPIDER_LOADER_WARN_ONLY': True, 'SPIDER_MODULES': ['items.spiders'], 'FEED_URI': 'item.csv', 'ROBOTSTXT_OBEY': True, 'NEWSPIDER_MODULE': 'items.spiders'}
2017-07-04 16:33:20 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
'scrapy.extensions.memusage.MemoryUsage',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.feedexport.FeedExporter',
'scrapy.extensions.logstats.LogStats']
2017-07-04 16:33:20 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware',
'scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
'scrapy.downloadermiddlewares.retry.RetryMiddleware',
'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware',
'scrapy.downloadermiddlewares.stats.DownloaderStats']
2017-07-04 16:33:20 [scrapy.middleware] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
'scrapy.spidermiddlewares.referer.RefererMiddleware',
'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
'scrapy.spidermiddlewares.depth.DepthMiddleware']
2017-07-04 16:33:20 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2017-07-04 16:33:20 [scrapy.core.engine] INFO: Spider opened
2017-07-04 16:33:20 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2017-07-04 16:33:20 [scrapy.extensions.telnet] DEBUG: Telnet console listening on 127.0.0.1:6023
2017-07-04 16:33:21 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://www.yellowpages.com/robots.txt> (referer: None)
2017-07-04 16:33:23 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://www.yellowpages.com/search?search_terms=handyman&geo_location_terms=Miami%2C+FL> (referer: None)
2017-07-04 16:33:24 [scrapy.core.scraper] ERROR: Spider error processing <GET https://www.yellowpages.com/search?search_terms=handyman&geo_location_terms=Miami%2C+FL> (referer: None)
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/scrapy/utils/defer.py", line 102, in iter_errback
yield next(it)
File "/usr/local/lib/python3.5/dist-packages/scrapy/spidermiddlewares/offsite.py", line 29, in process_spider_output
for x in result:
File "/usr/local/lib/python3.5/dist-packages/scrapy/spidermiddlewares/referer.py", line 339, in <genexpr>
return (_set_referer(r) for r in result or ())
File "/usr/local/lib/python3.5/dist-packages/scrapy/spidermiddlewares/urllength.py", line 37, in <genexpr>
return (r for r in result or () if _filter(r))
File "/usr/local/lib/python3.5/dist-packages/scrapy/spidermiddlewares/depth.py", line 58, in <genexpr>
return (r for r in result or () if _filter(r))
File "/root/Desktop/items/items/spiders/itemspider.py", line 17, in parse
l.add_css('Details', response.urljoin(listing.css('a.business-name::attr(href)')))
File "/usr/local/lib/python3.5/dist-packages/scrapy/http/response/text.py", line 82, in urljoin
return urljoin(get_base_url(self), url)
File "/usr/lib/python3.5/urllib/parse.py", line 416, in urljoin
base, url, _coerce_result = _coerce_args(base, url)
File "/usr/lib/python3.5/urllib/parse.py", line 112, in _coerce_args
raise TypeError("Cannot mix str and non-str arguments")
TypeError: Cannot mix str and non-str arguments
2017-07-04 16:33:24 [scrapy.core.engine] INFO: Closing spider (finished)
2017-07-04 16:33:24 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 503,
'downloader/request_count': 2,
'downloader/request_method_count/GET': 2,
'downloader/response_bytes': 52924,
'downloader/response_count': 2,
'downloader/response_status_count/200': 2,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2017, 7, 4, 21, 33, 24, 121098),
'log_count/DEBUG': 3,
'log_count/ERROR': 1,
'log_count/INFO': 7,
'memusage/max': 49471488,
'memusage/startup': 49471488,
'response_received_count': 2,
'scheduler/dequeued': 1,
'scheduler/dequeued/memory': 1,
'scheduler/enqueued': 1,
'scheduler/enqueued/memory': 1,
'spider_exceptions/TypeError': 1,
'start_time': datetime.datetime(2017, 7, 4, 21, 33, 20, 705391)}
2017-07-04 16:33:24 [scrapy.core.engine] INFO: Spider closed (finished)
Not sure what is going this is actually the first time I tried to use the ItemLoaders

Answer 1

There are a few issues with your code:
response.urljoin() expects a single string as parameter, not a list. You are passing the result of listing.css(), which is a SelectorList. You can use response.urljoin(listing.css('a.business-name::attr(href)').extract_first())
you need to instantiate one item loader per loop iteration, otherwise, you're accumulating values for each field of a single yielded item
you are using .add_css() with some values (result of .extract...() calls. .add_css() needs a CSS selector string, not the result of a selector extraction. The CSS extraction will then be done by the item loader. Or, you can use .add_value() if you want to pass the "final" field value directly.
Here are 2 versions that should get you going:
import scrapy
from items.items import ItemsItem
from scrapy.loader import ItemLoader
class ItemspiderSpider(scrapy.Spider):
name = 'itemspider'
allowed_domains = ['yellowpages.com']
start_urls = ['https://www.yellowpages.com/search?search_terms=handyman&geo_location_terms=Miami%2C+FL']
def parse(self, response):
for listing in response.css('div.search-results.organic div.srp-listing'):
# create the loader using the SELECTOR, inside the loop
l = ItemLoader(item=ItemsItem())
# use .add_value() since we pass the extraction result directly
l.add_value('Name', listing.css('a.business-name span::text').extract())
# pass a single value to response.urljoin()
l.add_value('Details',
response.urljoin(
listing.css('a.business-name::attr(href)').extract_first()
))
l.add_value('WebSite', listing.css('a.track-visit-website::attr(href)').extract_first())
l.add_value('Phones', listing.css('div.phones::text').extract())
yield l.load_item()
Or, using .add_css():
import scrapy
from items.items import ItemsItem
from scrapy.loader import ItemLoader
class ItemspiderSpider(scrapy.Spider):
name = 'itemspider'
allowed_domains = ['yellowpages.com']
start_urls = ['https://www.yellowpages.com/search?search_terms=handyman&geo_location_terms=Miami%2C+FL']
def parse(self, response):
for listing in response.css('div.search-results.organic div.srp-listing'):
# pass the 'listing' selector to the item loader
# so that CSS selection is relative to it
l = ItemLoader(ItemsItem(), selector=listing)
l.add_css('Name', 'a.business-name span::text')
l.add_css('Details', 'a.business-name::attr(href)')
l.add_css('WebSite', 'a.track-visit-website::attr(href)')
l.add_css('Phones', 'div.phones::text')
yield l.load_item()