Writing items to a MySQL database in Scrapy

Question

I am new to Scrapy, I had the spider code

class Example_spider(BaseSpider):
   name = "example"
   allowed_domains = ["www.example.com"]

   def start_requests(self):
       yield self.make_requests_from_url("http://www.example.com/bookstore/new")

   def parse(self, response):
       hxs = HtmlXPathSelector(response)
       urls = hxs.select('//div[@class="bookListingBookTitle"]/a/@href').extract()
       for i in urls:
           yield Request(urljoin("http://www.example.com/", i[1:]), callback=self.parse_url)

   def parse_url(self, response):
           hxs = HtmlXPathSelector(response)
           main =   hxs.select('//div[@id="bookshelf-bg"]')
           items = []
           for i in main:
           item = Exampleitem()
           item['book_name'] = i.select('div[@class="slickwrap full"]/div[@id="bookstore_detail"]/div[@class="book_listing clearfix"]/div[@class="bookstore_right"]/div[@class="title_and_byline"]/p[@class="book_title"]/text()')[0].extract()
           item['price'] = i.select('div[@id="book-sidebar-modules"]/div[@class="add_to_cart_wrapper slickshadow"]/div[@class="panes"]/div[@class="pane clearfix"]/div[@class="inner"]/div[@class="add_to_cart 0"]/form/div[@class="line-item"]/div[@class="line-item-price"]/text()').extract()
           items.append(item)
       return items

And pipeline code is:

class examplePipeline(object):

    def __init__(self):               
        self.dbpool = adbapi.ConnectionPool('MySQLdb',
                db='blurb',
                user='root',
                passwd='redhat',
                cursorclass=MySQLdb.cursors.DictCursor,
                charset='utf8',
                use_unicode=True
            )
def process_item(self, spider, item):
    # run db query in thread pool
    assert isinstance(item, Exampleitem)
    query = self.dbpool.runInteraction(self._conditional_insert, item)
    query.addErrback(self.handle_error)
    return item
def _conditional_insert(self, tx, item):
    print "db connected-=========>"
    # create record if doesn't exist. 
    tx.execute("select * from example_book_store where book_name = %s", (item['book_name']) )
    result = tx.fetchone()
    if result:
        log.msg("Item already stored in db: %s" % item, level=log.DEBUG)
    else:
        tx.execute("""INSERT INTO example_book_store (book_name,price)
                    VALUES (%s,%s)""",   
                            (item['book_name'],item['price'])
                    )
        log.msg("Item stored in db: %s" % item, level=log.DEBUG)            

def handle_error(self, e):
    log.err(e)          

After running this I am getting the following error

exceptions.NameError: global name 'Exampleitem' is not defined

I got the above error when I added the below code in process_item method

assert isinstance(item, Exampleitem)

and without adding this line I am getting

**exceptions.TypeError: 'Example_spider' object is not subscriptable

Can anyone make this code run and make sure that all the items saved into database?

Answer 1

Try the following code in your pipeline

import sys
import MySQLdb
import hashlib
from scrapy.exceptions import DropItem
from scrapy.http import Request

class MySQLStorePipeline(object):
    def __init__(self):
        self.conn = MySQLdb.connect('host', 'user', 'passwd', 
                                    'dbname', charset="utf8",
                                    use_unicode=True)
        self.cursor = self.conn.cursor()

    def process_item(self, item, spider):    
        try:
            self.cursor.execute("""INSERT INTO example_book_store (book_name, price)  
                        VALUES (%s, %s)""", 
                       (item['book_name'].encode('utf-8'), 
                        item['price'].encode('utf-8')))            
            self.conn.commit()            
        except MySQLdb.Error, e:
            print "Error %d: %s" % (e.args[0], e.args[1])
        return item

Answer 2

Your process_item method should be declared as: def process_item(self, item, spider): instead of def process_item(self, spider, item): -> you switched the arguments around.

This exception: exceptions.NameError: global name 'Exampleitem' is not defined indicates you didn't import the Exampleitem in your pipeline. Try adding: from myspiders.myitems import Exampleitem (with correct names/paths ofcourse).

Answer 3

I think this way is better and more concise:

#Item
class pictureItem(scrapy.Item):
    topic_id=scrapy.Field()
    url=scrapy.Field()

#SQL
self.save_picture="insert into picture(`url`,`id`) values(%(url)s,%(id)s);"

#usage
cur.execute(self.save_picture,dict(item))

It's just like

cur.execute("insert into picture(`url`,`id`) values(%(url)s,%(id)s)" % {"url":someurl,"id":1})

Cause (you can read more about Items in Scrapy)

The Field class is just an alias to the built-in dict class and doesn’t provide any extra functionality or attributes. In other words, Field objects are plain-old Python dicts.