我写了一个蜘蛛来抓取一些页面,有时候它可以工作,但有时却没有。
下面是问题所在:
Traceback (most recent call last):
File "/home/hadoop/scrapy/myapp/lib/python2.7/site-packages/twisted/internet/base.py", line 824, in runUntilCurrent
call.func(*call.args, **call.kw)
File "/home/hadoop/scrapy/myapp/lib/python2.7/site-packages/twisted/internet/task.py", line 638, in _tick
taskObj._oneWorkUnit()
File "/home/hadoop/scrapy/myapp/lib/python2.7/site-packages/twisted/internet/task.py", line 484, in _oneWorkUnit
result = next(self._iterator)
File "/home/hadoop/scrapy/myapp/lib/python2.7/site-packages/scrapy/utils/defer.py", line 57, in <genexpr>
work = (callable(elem, *args, **named) for elem in iterable)
--- <exception caught here> ---
File "/home/hadoop/scrapy/myapp/lib/python2.7/site-packages/scrapy/utils/defer.py", line 96, in iter_errback
yield next(it)
File "/home/hadoop/scrapy/myapp/lib/python2.7/site-packages/scrapy/contrib/spidermiddleware/offsite.py", line 26, in process_spider_output
for x in result:
File "/home/hadoop/scrapy/myapp/lib/python2.7/site-packages/scrapy/contrib/spidermiddleware/referer.py", line 22, in <genexpr>
return (_set_referer(r) for r in result or ())
File "/home/hadoop/scrapy/myapp/lib/python2.7/site-packages/scrapy/contrib/spidermiddleware/urllength.py", line 33, in <genexpr>
return (r for r in result or () if _filter(r))
File "/home/hadoop/scrapy/myapp/lib/python2.7/site-packages/scrapy/contrib/spidermiddleware/depth.py", line 50, in <genexpr>
return (r for r in result or () if _filter(r))
File "/home/hadoop/scrapy/myapp/scrapy-redis-master/soufang/soufang/spiders/soufang_spider.py", line 28, in parse_community
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/div[@class='ewmBoxTitle']/span[@class='floatl']/text()").extract()
exceptions.AttributeError: 'Response' object has no attribute 'xpath'
我有两个问题:
1。导致AttributeError的原因是什么?
2。我编写了一个下载中间件来记录所有异常,并将相关的URL记录在名为outurl_record.txt的txt文件中。为什么我没有抓住这个例外.AttributeError和网址?
下面是我的middleware.py和设置:
class CustomRecordMiddleware(object):
def process_exception(self,request,exception,spider):
url = request.url
proxy = request.meta['proxy']
myfile = open('outurl_record.txt','a')
myfile.write(url+'\n')
myfile.write(proxy+'\n')
myfile.close()
log.msg('Fail to request url %s with exception %s' % (url, str(exception)))
这是设置:
DOWNLOADER_MIDDLEWARES={'soufang.misc.middleware.CustomRecordMiddleware':860,}
这是spider.py
#-*- coding=utf8 -*-
import scrapy
from soufang.items import Community_info
import sys
from imp import reload
import re
from scrapy_redis.spiders import RedisSpider
reload(sys)
sys.setdefaultencoding( "utf-8" )
class soufangSpider(RedisSpider):
name = 'soufang_redis'
redis_key = 'soufangSpider:start_urls'
def parse_community(self,response):
item = response.meta['item']
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/div[@class='ewmBoxTitle']/span[@class='floatl']/text()").extract()
item['community'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='开 发 商:']/../text()").extract()
item['developer'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='所属区域:']/../text()").extract()
if temp :
item['district'] = temp[0]
else:
item['district'] = ''
myfile = open('outurl_item.txt', 'a')
myfile.write(response.url)
myfile.write('\n')
myfile.close()
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='小区地址:']/../text()").extract()
item['address'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='邮${nbsp}${nbsp}${nbsp}${nbsp}编:']/../text()").extract()
item['postcode'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='竣工时间:']/../text()").extract()
item['yearOfDev'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='firstpic']/dd[text()='本月均价:']/span[1]/text()").extract()
item['price'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='总 户 数:']/../text()").extract()
item['household_no'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='物业类别:']/../text()").extract()
item['community_type'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='物 业 费:']/../text()").extract()
item['property_fee'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='建筑面积:']/../text()").extract()
item['total_area'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='占地面积:']/../text()").extract()
item['area'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='绿 化 率:']/../text()").extract()
item['greening_rate'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/dl[@class='lbox']/dd/strong[text()='容 积 率:']/../text()").extract()
item['volumn_rate'] = temp[0] if temp else ''
temp = response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/div[@class='yihang']/h3[text()='交通状况']/../following-sibling::dl[1]/dt[1]/text()").extract()
item['transportation'] = temp[0] if temp else ''
temp = "".join(response.xpath(u"//div[@class='maininfo']/div[@class='leftinfo']/div[@class='yihang']/h3[text()='周边信息']/../following-sibling::dl[1]//text()").extract())
item['periphery'] = temp if temp else ''
yield item
def parse(self,response):
flag = response.xpath(u"//div[@class='wid1000']/div[@class='listBox floatl']/div[@class='houseList']").extract()
city = response.xpath(u"//div[@class='wid1000']/div[@class='bread']/a[2]/text()").extract()
if flag and city :
item = Community_info()
item['city'] =city[0][:-3]
urls = response.xpath(u"//div[@class='info rel floatl ml15']/dl/dd[last()]/a[1]/@href").extract()
if len(urls)==0:
myfile = open('urls0.txt','a')
myfile.write(response.url+'\n')
myfile.close()
next_page = response.xpath(u"//div[@class='listBox floatl']/div[@class='fanye gray6']/a[text()='下一页']/@href").extract()
if next_page:
pageurl = next_page[0]
fullpage = re.match(r'http://.+com', response.url).group()+pageurl
yield scrapy.Request(fullpage,callback=self.parse)
for url in urls :
try:
request = scrapy.Request(url,callback=self.parse_community)
request.meta['item'] = item
yield request
except Exception,e:
myfile = open('badurl_item.txt','a')
myfile.write(response.url+'\n')
myfile.write(url+'\n')
myfile.close()
else:
myfile = open('outurl_break','a')
myfile.write(response.url + '\n')
myfile.close()
yield scrapy.Request(response.url,callback=self.parse)
答案 0 :(得分:1)
我将回答第一个问题: - 1.导致AttributeError的原因是什么?
这是因为页面是空的。
例如:scrapy shell
In [1]: fetch("http://diachiso.vn/Shop/CityPage_LoadShopBySubServiceIdAndFilterId?pageindex=6&pagesize=20&sid=256&fid=&cityid=3&parentSid=520")
2015-10-11 11:22:55 [scrapy] INFO: Spider opened
2015-10-11 11:22:55 [scrapy] DEBUG: Crawled (200) <GET http://diachiso.vn/Shop/CityPage_LoadShopBySubServiceIdAndFilterId?pageindex=6&pagesize=20&sid=256&fid=&cityid=3&parentSid=520> (referer: None)
[s] Available Scrapy objects:
[s] crawler <scrapy.crawler.Crawler object at 0x7fadf4f9cb50>
[s] item {}
[s] request <GET http://diachiso.vn/Shop/CityPage_LoadShopBySubServiceIdAndFilterId?pageindex=6&pagesize=20&sid=256&fid=&cityid=3&parentSid=520>
[s] response <200 http://diachiso.vn/Shop/CityPage_LoadShopBySubServiceIdAndFilterId?pageindex=6&pagesize=20&sid=256&fid=&cityid=3&parentSid=520>
[s] settings <scrapy.settings.Settings object at 0x7fadf4f9cad0>
[s] spider <DefaultSpider 'default' at 0x7fadf232a710>
[s] Useful shortcuts:
[s] shelp() Shell help (print this help)
[s] fetch(req_or_url) Fetch request (or URL) and update local objects
[s] view(response) View response in a browser
In [2]: response.
response.body response.flags response.meta response.request response.url
response.copy response.headers response.replace response.status response.urljoin
In [2]: response.status
Out[2]: 200
In [6]: response.body
Out[6]: ''