scrapy 项目在将它们存储到 couchdb 时不是 JSON 可序列化的
Posted
技术标签:
【中文标题】scrapy 项目在将它们存储到 couchdb 时不是 JSON 可序列化的【英文标题】：scrapy items are not JSON serializable while storing them to couchdb 【发布时间】：2015-02-07 23:50:25 【问题描述】：items.py classes
import scrapy
from scrapy.item import Item, Field
import json
class Attributes(scrapy.Item):
description = Field()
pages=Field()
author=Field()
class Vendor(scrapy.Item):
title=Field()
order_url=Field()
class bookItem(scrapy.Item):
title = Field()
url = Field()
marketprice=Field()
images=Field()
price=Field()
attributes=Field()
vendor=Field()
time_scraped=Field()
我的刮刀
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import htmlXPathSelector
from scrapy.item import Item
from scrapy.spider import BaseSpider
from scrapy import log
from scrapper.items import bookItem,Attributes,Vendor
import couchdb
import logging
import json
import time
from couchdb import Server
class libertySpider(CrawlSpider):
couch = couchdb.Server()
db = couch['python-tests']
name = "libertybooks"
allowed_domains = ["libertybooks.com"]
unvisited_urls = []
visited_urls = []
start_urls = [
"http://www.libertybooks.com"
]
url=["http://www.kaymu.pk"]
rules = [Rule(SgmlLinkExtractor(), callback='parse_item', follow=True)]
total=0
productpages=0
exceptionnum=0
def parse_item(self,response):
if response.url.find("pid")!=-1:
with open("number.html","w") as w:
self.total=self.total+1
w.write(str(self.total)+","+str(self.productpages))
itm=bookItem()
attrib=Attributes()
ven=Vendor()
images=[]
try:
name=response.xpath('//span[@id="pagecontent_lblbookName"]/text()').extract()[0]
name=name.encode('utf-8')
except:
name="name not found"
try:
price=response.xpath('//span[@id="pagecontent_lblPrice"]/text()').extract()[0]
price=price.encode('utf-8')
except:
price=-1
try:
marketprice=response.xpath('//span[@id="pagecontent_lblmarketprice"]/text()').extract()[0]
marketprice=marketprice.encode('utf-8')
except:
marketprice=-1
try:
pages=response.xpath('//span[@id="pagecontent_spanpages"]/text()').extract()[0]
pages=pages.encode('utf-8')
except:
pages=-1
try:
author=response.xpath('//span[@id="pagecontent_lblAuthor"]/text()').extract()[0]
author=author.encode('utf-8')
except:
author="author not found"
try:
description=response.xpath('//span[@id="pagecontent_lblbookdetail"]/text()').extract()[0]
description=description.encode('utf-8')
except:
description="des: not found"
try:
image=response.xpath('//img[@id="pagecontent_imgProduct"]/@src').extract()[0]
image=image.encode('utf-8')
except:
image="#"
ven['title']='libertybooks'
ven['order_url']=response.url
itm['vendor']=ven
itm['time_scraped']=time.ctime()
itm['title']=name
itm['url']=response.url
itm['price']=price
itm['marketprice']=marketprice
itm['images']=images
attrib['pages']=pages
attrib['author']=author
attrib['description']=description
itm['attributes']=attrib
self.saveindb(itm)
return itm
def saveindb(self,obj):
logging.debug(obj)
self.db.save(obj)堆栈跟踪
2014-12-09 13:57:37-0800 [libertybooks] ERROR: Spider error processing <GET http://www.libertybooks.com/bookdetail.aspx?pid=16532>
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/local/lib/python2.7/dist-packages/scrapy/utils/defer.py", line 57, in <genexpr>
work = (callable(elem, *args, **named) for elem in iterable)
--- <exception caught here> ---
File "/usr/local/lib/python2.7/dist-packages/scrapy/utils/defer.py", line 96, in iter_errback
yield next(it)
File "/usr/local/lib/python2.7/dist-packages/scrapy/contrib/spidermiddleware/offsite.py", line 26, in process_spider_output
for x in result:
File "/usr/local/lib/python2.7/dist-packages/scrapy/contrib/spidermiddleware/referer.py", line 22, in <genexpr>
return (_set_referer(r) for r in result or ())
File "/usr/local/lib/python2.7/dist-packages/scrapy/contrib/spidermiddleware/urllength.py", line 33, in <genexpr>
return (r for r in result or () if _filter(r))
File "/usr/local/lib/python2.7/dist-packages/scrapy/contrib/spidermiddleware/depth.py", line 50, in <genexpr>
return (r for r in result or () if _filter(r))
File "/usr/local/lib/python2.7/dist-packages/scrapy/contrib/spiders/crawl.py", line 67, in _parse_response
cb_res = callback(response, **cb_kwargs) or ()
File "/home/asad/Desktop/scraper/scraper/spiders/liberty_spider.py", line 107, in parse_item
self.saveindb(itm)
File "/home/asad/Desktop/scraper/scraper/spiders/liberty_spider.py", line 112, in saveindb
self.db.save(obj)
File "/usr/local/lib/python2.7/dist-packages/couchdb/client.py", line 431, in save
_, _, data = func(body=doc, **options)
File "/usr/local/lib/python2.7/dist-packages/couchdb/http.py", line 514, in post_json
**params)
File "/usr/local/lib/python2.7/dist-packages/couchdb/http.py", line 533, in _request_json
headers=headers, **params)
File "/usr/local/lib/python2.7/dist-packages/couchdb/http.py", line 529, in _request
credentials=self.credentials)
File "/usr/local/lib/python2.7/dist-packages/couchdb/http.py", line 244, in request
body = json.encode(body).encode('utf-8')
File "/usr/local/lib/python2.7/dist-packages/couchdb/json.py", line 69, in encode
return _encode(obj)
File "/usr/local/lib/python2.7/dist-packages/couchdb/json.py", line 135, in <lambda>
dumps(obj, allow_nan=False, ensure_ascii=False)
File "/usr/lib/python2.7/json/__init__.py", line 250, in dumps
sort_keys=sort_keys, **kw).encode(obj)
File "/usr/lib/python2.7/json/encoder.py", line 207, in encode
chunks = self.iterencode(o, _one_shot=True)
File "/usr/lib/python2.7/json/encoder.py", line 270, in iterencode
return _iterencode(o, 0)
File "/usr/lib/python2.7/json/encoder.py", line 184, in default
raise TypeError(repr(o) + " is not JSON serializable")
exceptions.TypeError: 'attributes': 'author': 'Tina Fey',
'description': "Once in a generation a woman comes along who changes everything. Tina Fey is not that woman, but she met that woman once and acted weird around her.\r\n\r\nBefore 30 Rock, Mean Girls and 'Sarah Palin', Tina Fey was just a young girl with a dream: a recurring stress dream that she was being chased through a local airport by her middle-school gym teacher.\r\n\r\nShe also had a dream that one day she would be a comedian on TV. She has seen both these dreams come true.\r\n\r\nAt last, Tina Fey's story can be told. From her youthful days as a vicious nerd to her tour of duty on Saturday Night Live; from her passionately halfhearted pursuit of physical beauty to her life as a mother eating things off the floor; from her one-sided college romance to her nearly fatal honeymoon - from the beginning of this paragraph to this final sentence.\r\n\r\nTina Fey reveals all, and proves what we've all suspected: you're no one until someone calls you bossy.",
'pages': '304 Pages',
'images': [],
'marketprice': '1,095',
'price': '986',
'time_scraped': 'Tue Dec 9 13:57:37 2014',
'title': 'Bossypants',
'url': 'http://www.libertybooks.com/bookdetail.aspx?pid=16532',
'vendor': 'order_url': 'http://www.libertybooks.com/bookdetail.aspx?pid=16532',
'title': 'libertybooks' is not JSON serializable
我是scrapy和couchdb的初学者，我也尝试使用“json.dumps(itm, default=lambda o: o.dict将item对象转换为json对象, sort_keys=True, indent=4)" 但得到了相同的响应，所以请告诉我有没有办法让我的类 json 可序列化，以便它们可以存储在 couchdb 中？
【问题讨论】：
【参考方案1】：嗯，简短的答案就是使用ScrapyJSONEncoder：
from scrapy.utils.serialize import ScrapyJSONEncoder
_encoder = ScrapyJSONEncoder()
...
def saveindb(self,obj):
logging.debug(obj)
self.db.save(_encoder.encode(obj))
更长的版本是：如果您打算让这个蜘蛛成长（如果它不应该是一次性的），您可能希望使用pipeline 将项目存储在 CouchDB 中并保持关注点分开（在蜘蛛代码中抓取/抓取，在管道代码中存储在数据库中）。
一开始这可能看起来像是过度设计，但当项目开始增长并使测试变得更容易时，它确实很有帮助。
【讨论】：
我已经在管道中分离了我的存储代码，并使用了 self.db.save(_encoder.encode(obj)) 但它仍然不起作用并说 (u'bad_content_type', u'Content-Type必须是 application/json') 它的堆栈跟踪是 File "/usr/local/lib/python2.7/dist-packages/couchdb/http.py", in post_json **params) File "/usr/local/lib /python2.7/dist-packages/couchdb/http.py", , in _request_json headers=headers, **params) 文件 "/usr/local/lib/python2.7/dist-packages/couchdb/http.py" ，第 529 行，在 _request credentials=self.credentials) 文件“/usr/local/lib/python2.7/dist-packages/couchdb/http.py”，第 383 行，在请求中引发 ServerError((status, error)) couchdb.http.ServerError: (415, (u'bad_content_type', u'Content-Type must be application/json')) @user3344528 看起来像是一个单独的问题，与如何使用 CouchDB API 保存 JSON 对象有关——抱歉，我对 CouchDB 不太熟悉。这可能是另一个问题的情况。您可以尝试使用 hack：self.db.save(json.loads(_encoder.encode(obj))) - 将编码的 JSON 转换为纯 Python dicts，但可能有更好的方法。以上是关于scrapy 项目在将它们存储到 couchdb 时不是 JSON 可序列化的的主要内容，如果未能解决你的问题，请参考以下文章
couchdb 气垫船限制，将任意 erlang 术语存储到 Couchdb