Ошибка при помощи SCRAPY

Question

У меня есть этот код в Python:

import scrapy 
from scrapy.contrib.spiders import CrawlSpider, Rule 
from scrapy.contrib.linkextractors import LinkExtractor 
from site_auto_1.items import AutoItem 


class AutoSpider(CrawlSpider): 
    name = "auto" 

    allowed_host = ["autowereld.nl"] 

    url = "http://www.autowereld.nl/" 

    start_urls = [ 
      "http://www.autowereld.nl/zoeken.html?mrk=187&mdl%5B%5D=463&prvan=500&prtot=3000&brstf%5B%5D=2&bjvan=2000&bjtot=2004&geoloc=&strl=&trns%5B%5D=&kmvan=&kmtot=&klr%5B%5D=&q=", 
      ] 

    path = '//*[@id="content-inhoud"]/div/div/table/tbody/tr/td/h3/a/@href' 

    rules = (
      Rule(
       LinkExtractor(restrict_xpaths='//*[@id="content-inhoud"]/div/div/table/tbody/tr/td/h3/a/@href'), 
       callback='parse_item', 
      ), 
     ) 

    def parse_item(self, response): 
     print "found item :', response.url 

, и это дает мне эту ошибку:

Traceback (most recent call last): 
     File "/usr/lib/python2.7/dist-packages/twisted/internet/base.py", line 824, in runUntilCurrent 
     call.func(*call.args, **call.kw) 
     File "/usr/lib/python2.7/dist-packages/twisted/internet/task.py", line 638, in _tick 
     taskObj._oneWorkUnit() 
     File "/usr/lib/python2.7/dist-packages/twisted/internet/task.py", line 484, in _oneWorkUnit 
     result = next(self._iterator) 
     File "/usr/lib/pymodules/python2.7/scrapy/utils/defer.py", line 57, in <genexpr> 
     work = (callable(elem, *args, **named) for elem in iterable) 
    --- <exception caught here> --- 
     File "/usr/lib/pymodules/python2.7/scrapy/utils/defer.py", line 96, in iter_errback 
     yield next(it) 
     File "/usr/lib/pymodules/python2.7/scrapy/contrib/spidermiddleware/offsite.py", line 26, in process_spider_output 
     for x in result: 
     File "/usr/lib/pymodules/python2.7/scrapy/contrib/spidermiddleware/referer.py", line 22, in <genexpr> 
     return (_set_referer(r) for r in result or()) 
     File "/usr/lib/pymodules/python2.7/scrapy/contrib/spidermiddleware/urllength.py", line 33, in <genexpr> 
     return (r for r in result or() if _filter(r)) 
     File "/usr/lib/pymodules/python2.7/scrapy/contrib/spidermiddleware/depth.py", line 50, in <genexpr> 
     return (r for r in result or() if _filter(r)) 
     File "/usr/lib/pymodules/python2.7/scrapy/contrib/spiders/crawl.py", line 73, in _parse_response 
     for request_or_item in self._requests_to_follow(response): 
     File "/usr/lib/pymodules/python2.7/scrapy/contrib/spiders/crawl.py", line 52, in _requests_to_follow 
     links = [l for l in rule.link_extractor.extract_links(response) if l not in seen] 
     File "/usr/lib/pymodules/python2.7/scrapy/contrib/linkextractors/lxmlhtml.py", line 107, in extract_links 
     links = self._extract_links(doc, response.url, response.encoding, base_url) 
     File "/usr/lib/pymodules/python2.7/scrapy/linkextractor.py", line 94, in _extract_links 
     return self.link_extractor._extract_links(*args, **kwargs) 
     File "/usr/lib/pymodules/python2.7/scrapy/contrib/linkextractors/lxmlhtml.py", line 50, in _extract_links 
     for el, attr, attr_val in self._iter_links(selector._root): 
     File "/usr/lib/pymodules/python2.7/scrapy/contrib/linkextractors/lxmlhtml.py", line 38, in _iter_links 
     for el in document.iter(etree.Element): 
    exceptions.AttributeError: 'str' object has no attribute 'iter' 

Я не знаю, что я делаю неправильно, поэтому я начал комментировать код и увидеть ведьму один буксирует ошибку и я понять это, что эта часть:

rules = (
     Rule(
      LinkExtractor(restrict_xpaths='//*[@id="content-inhoud"]/div/div/table/tbody/tr/td/h3/a/@href'), 
      callback='parse_item', 
     ), 
    ) 

Но я не знаю, что я делаю неправильно, я пытался сделать restrict_xpaths список, кортеж ... я новичок в scrapy, и я не могу понять это ...

Answer 1

XPath, сконфигурированный внутри restict_xpaths, должен указывать на элемент, а не на атрибут.

Заменить:

//*[@id="content-inhoud"]/div/div/table/tbody/tr/td/h3/a/@href 

с:

//*[@id="content-inhoud"]/div/div/table/tbody/tr/td/h3/a