在Scrapy中将项目写入MySQL数据库

  • Z时代
  • 2024-01-10
  • 分类：问答

我是Scrapy的新手，我有spider代码

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

管道代码为：

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)

运行此后，我得到以下错误

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

当我在process_item方法中添加以下代码时，出现上述错误

assert isinstance(item, Exampleitem)

而没有添加这行我得到

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

任何人都可以运行此代码，并确保所有项目都保存到数据库中吗？

回答：

在管道中尝试以下代码

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

以上是 在Scrapy中将项目写入MySQL数据库 的全部内容， 来源链接： utcz.com/qa/427980.html

回到顶部