Scrapy: 'str' object has no attribute 'iter'

Question

I added restrict_xpaths rules to my scrapy spider and now it immediately fails with:

2015-03-16 15:46:53+0000 [tsr] ERROR: Spider error processing <GET http://www.thestudentroom.co.uk/forumdisplay.php?f=143>
    Traceback (most recent call last):
      File "/System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python/twisted/internet/base.py", line 800, in runUntilCurrent
        call.func(*call.args, **call.kw)
      File "/System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python/twisted/internet/task.py", line 602, in _tick
        taskObj._oneWorkUnit()
      File "/System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python/twisted/internet/task.py", line 479, in _oneWorkUnit
        result = self._iterator.next()
      File "/Library/Python/2.7/site-packages/scrapy/utils/defer.py", line 57, in <genexpr>
        work = (callable(elem, *args, **named) for elem in iterable)
    --- <exception caught here> ---
      File "/Library/Python/2.7/site-packages/scrapy/utils/defer.py", line 96, in iter_errback
        yield next(it)
      File "/Library/Python/2.7/site-packages/scrapy/contrib/spidermiddleware/offsite.py", line 26, in process_spider_output
        for x in result:
      File "/Library/Python/2.7/site-packages/scrapy/contrib/spidermiddleware/referer.py", line 22, in <genexpr>
        return (_set_referer(r) for r in result or ())
      File "/Library/Python/2.7/site-packages/scrapy/contrib/spidermiddleware/urllength.py", line 33, in <genexpr>
        return (r for r in result or () if _filter(r))
      File "/Library/Python/2.7/site-packages/scrapy/contrib/spidermiddleware/depth.py", line 50, in <genexpr>
        return (r for r in result or () if _filter(r))
      File "/Library/Python/2.7/site-packages/scrapy/contrib/spiders/crawl.py", line 73, in _parse_response
        for request_or_item in self._requests_to_follow(response):
      File "/Library/Python/2.7/site-packages/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 "/Library/Python/2.7/site-packages/scrapy/contrib/linkextractors/lxmlhtml.py", line 107, in extract_links
        links = self._extract_links(doc, response.url, response.encoding, base_url)
      File "/Library/Python/2.7/site-packages/scrapy/linkextractor.py", line 94, in _extract_links
        return self.link_extractor._extract_links(*args, **kwargs)
      File "/Library/Python/2.7/site-packages/scrapy/contrib/linkextractors/lxmlhtml.py", line 50, in _extract_links
        for el, attr, attr_val in self._iter_links(selector._root):
      **File "/Library/Python/2.7/site-packages/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'**

I cannot understand why this error is happening.

Here is my short Spider:

import scrapy

from tutorial.items import DmozItem
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors import LinkExtractor

class TsrSpider(CrawlSpider):
    name = 'tsr'
    allowed_domains = ['thestudentroom.co.uk']
    start_urls = ['http://www.thestudentroom.co.uk/forumdisplay.php?f=143']

    download_delay = 4
    user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:35.0) Gecko/20100101 Firefox/35.0'

    rules = (
        Rule(
            LinkExtractor(
                allow=('forumdisplay\.php\?f=143\&page=\d',),
                restrict_xpaths=("//li[@class='pager-page_numbers']/a/@href",))),

        Rule(
            LinkExtractor(
                allow=('showthread\.php\?t=\d+\&page=\d+',),
                restrict_xpaths=("//li[@class='pager-page_numbers']/a/@href",)), 
            callback='parse_link'),

        Rule(
            LinkExtractor(
                allow=('showthread\.php\?t=\d+',),
                restrict_xpaths=("//tr[@class='thread  unread    ']",)),
            callback='parse_link'),
        )

    def parse_link(self, response):
#           Iterate over posts.     
        for sel in response.xpath("//li[@class='post threadpost old   ']"):
            rating = sel.xpath(
            "div[@class='post-footer']//span[@class='score']/text()").extract()
            if not rating:
                rating = 0
            else:
                rating = rating[0]
            item = DmozItem()
            item['post'] = sel.xpath(
    "div[@class='post-content']/blockquote[@class='postcontent restore']/text()").extract()
            item['link'] = response.url
            item['topic'] = response.xpath(
    "//div[@class='forum-header section-header']/h1/span/text()").extract()
            item['rating'] = rating
            yield item

source: http://pastebin.com/YXdWvPgX

Can someone help me out? Where is the mistake? I've been searching for days!?

Answer 1

The problem is that restrict_xpaths should point to elements - either the links directly or containers containing links, not attributes:

rules = [
    Rule(LinkExtractor(allow='forumdisplay\.php\?f=143\&page=\d',
                       restrict_xpaths="//li[@class='pager-page_numbers']/a")),

    Rule(LinkExtractor(allow='showthread\.php\?t=\d+\&page=\d+',
                       restrict_xpaths="//li[@class='pager-page_numbers']/a"),
         callback='parse_link'),

    Rule(LinkExtractor(allow='showthread\.php\?t=\d+',
                       restrict_xpaths="//tr[@class='thread  unread    ']"),
         callback='parse_link'),
]

Tested (worked for me).

FYI, Scrapy defines restrict_xpaths as "expressions pointing to regions":

restrict_xpaths (str or list) – is a XPath (or list of XPath’s) which defines regions inside the response where links should be extracted from. If given, only the text selected by those XPath will be scanned for links. See examples below.