Question

我以前已经成功使用了CrawlSpider。但是，当我更改代码以与Redis集成并添加我自己的中间件以设置UserAgent和cookie时，蜘蛛不再解析响应，因此蜘蛛不再生成新请求，因此蜘蛛在开始后不久就关闭了

即使我对此进行编码： def parse_start_url（自己，响应）：返回self.parse_item（response）它仅解析第一个网址的响应

这是我的代码：蜘蛛：

# -*- coding: utf-8 -*-
from scrapy.linkextractors import LinkExtractor
from yydzh.items import YydzhItem
from scrapy.spiders import Rule, CrawlSpider


class YydzhSpider(CrawlSpider):
    name = 'yydzhSpider'
    allowed_domains = ['yydzh.com']
    start_urls = ['http://www.yydzh.com/thread.php?fid=198']
    rules = (
         Rule(LinkExtractor(allow='thread\.php\?fid=198&page=([1-9]|1[0-9])#s', 
         restrict_xpaths=("//div[@class='pages']")), 
         callback='parse_item', follow=True,
         ),
    )

#def parse_start_url(self, response):
#   return self.parse_item(response)

def parse_item(self, response):
    item = YydzhItem()
    for each in response.xpath \
        ("//*[@id='ajaxtable']//tr[@class='tr2'][last()]/following-sibling::tr[@class!='tr2']"):
        item['title'] = each.xpath("./td[2]/h3[1]/a//text()").extract()[0]
        item['author'] = each.xpath('./td[3]/a//text()').extract()[0]
        item['category'] = each.xpath('./td[2]/span[1]//text()').extract()[0]
        item['url'] = each.xpath("./td[2]/h3[1]//a/@href").extract()[0]
        yield item

我认为至关重要的设置：

SCHEDULER = "scrapy_redis.scheduler.Scheduler"
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
DOWNLOADER_MIDDLEWARES = {
'yydzh.middlewares.UserAgentmiddleware': 500,
'yydzh.middlewares.CookieMiddleware': 600
}
COOKIES_ENABLED = True

中间件： UserAgentmiddleware随机更改用户代理，以避免被服务器注意到

CookieMiddleware添加cookie来请求要求登录进行扫描的页面

logger = logging.getLogger(__name__)


class UserAgentmiddleware(UserAgentMiddleware):

def process_request(self, request, spider):
    agent = random.choice(agents)
    request.headers["User-Agent"] = agent

class CookieMiddleware(RetryMiddleware):

def __init__(self, settings, crawler):
    RetryMiddleware.__init__(self, settings)
    self.rconn = redis.Redis(host=REDIS_HOST, port=REDIS_PORT,
                             password=REDIS_PASS, db=1, decode_responses=True)  
    init_cookie(self.rconn, crawler.spider.name)


@classmethod
def from_crawler(cls, crawler):
    return cls(crawler.settings, crawler)

def process_request(self, request, spider):
    redisKeys = self.rconn.keys()
    while len(redisKeys) > 0:
        elem = random.choice(redisKeys)
        if spider.name + ':Cookies' in elem:
            cookie = json.loads(self.rconn.get(elem))
            request.cookies = cookie
            request.meta["accountText"] = elem.split("Cookies:")[-1]
            break
        else:
            redisKeys.remove(elem)

def process_response(self, request, response, spider):
    if('您没有登录或者您没有权限访问此页面' in str(response.body)):
        accountText = request.meta["accountText"]
        remove_cookie(self.rconn, spider.name, accountText)
        update_cookie(self.rconn, spider.name, accountText)
        logger.warning("更新Cookie成功！（账号为:%s）" % accountText)
        return request

    return response

Answer 1

查找问题：Redis服务器在之前的请求之前已过滤所有URL，然后重新启动就可以解决问题。

Scrapy：CrawlSpider无法解析响应

1 个答案: