CrawlSpider inherits BaseSpider. It just added rules to extract and follow links.
If these rules are not enough flexible for you - use BaseSpider:
class USpider(BaseSpider):
"""my spider. """
start_urls = ['http://www.amazon.com/s/?url=search-alias%3Dapparel&sort=relevance-fs-browse-rank']
allowed_domains = ['amazon.com']
def parse(self, response):
'''Parse main category search page and extract subcategory search link.'''
self.log('Downloaded category search page.', log.DEBUG)
if response.meta['depth'] > 5:
self.log('Categories depth limit reached (recursive links?). Stopping further following.', log.WARNING)
hxs = HtmlXPathSelector(response)
subcategories = hxs.select("//div[@id='refinements']/*[starts-with(.,'Department')]/following-sibling::ul[1]/li/a[span[@class='refinementLink']]/@href").extract()
for subcategory in subcategories:
subcategorySearchLink = urlparse.urljoin(response.url, subcategorySearchLink)
yield Request(subcategorySearchLink, callback = self.parseSubcategory)
def parseSubcategory(self, response):
'''Parse subcategory search page and extract item links.'''
hxs = HtmlXPathSelector(response)
for itemLink in hxs.select('//a[@class="title"]/@href').extract():
itemLink = urlparse.urljoin(response.url, itemLink)
self.log('Requesting item page: ' + itemLink, log.DEBUG)
yield Request(itemLink, callback = self.parseItem)
try:
nextPageLink = hxs.select("//a[@id='pagnNextLink']/@href").extract()[0]
nextPageLink = urlparse.urljoin(response.url, nextPageLink)
self.log('
Going to next search page: ' + nextPageLink + '
', log.DEBUG)
yield Request(nextPageLink, callback = self.parseSubcategory)
except:
self.log('Whole category parsed: ' + categoryPath, log.DEBUG)
def parseItem(self, response):
'''Parse item page and extract product info.'''
hxs = HtmlXPathSelector(response)
item = UItem()
item['brand'] = self.extractText("//div[@class='buying']/span[1]/a[1]", hxs)
item['title'] = self.extractText("//span[@id='btAsinTitle']", hxs)
...
Even if BaseSpider's start_urls are not enough flexible for you, override start_requests method.
与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…