0

我正在使用 django 和 scrapy 在在线业务目录上制作一个项目。我只是使用scrapy来抓取数据并将其存储到数据库中。django 部分没有直接连接到scrapy。我需要从业务目录http://directory.thesun.co.uk/find/uk/computer-repair中删除业务详细信息 。问题是它只是从一个页面而不是从其他页面影响细节。 .请帮忙解决这个问题..

请查看我的代码并帮助我解决它

蜘蛛代码::

from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from project2.items import Project2Item

class ProjectSpider(BaseSpider):
    name = "project2spider"
    allowed_domains = ["http://directory.thesun.co.uk/"]
    start_urls = [
        'http://directory.thesun.co.uk/find/uk/computer-repair',
        'http://directory.thesun.co.uk/find/uk/computer-repair/page/2',
        'http://directory.thesun.co.uk/find/uk/computer-repair/page/3',
        'http://directory.thesun.co.uk/find/uk/computer-repair/page/4',
        'http://directory.thesun.co.uk/find/uk/computer-repair/page/5',
        'http://directory.thesun.co.uk/find/uk/computer-repair/page/6',
        'http://directory.thesun.co.uk/find/uk/computer-repair/page/7',
        'http://directory.thesun.co.uk/find/uk/computer-repair/page/8',
        'http://directory.thesun.co.uk/find/uk/computer-repair/page/9',
        'http://directory.thesun.co.uk/find/uk/computer-repair/page/10'
        ]

    def parse(self, response):
        hxs = HtmlXPathSelector(response)
        sites = hxs.select('//div[@class="abTbl "]')
        items = []
        for site in sites:
            item = Project2Item()
            item['Catogory'] = site.select('span[@class="icListBusType"]/text()').extract()
            item['Bussiness_name'] = site.select('a/@title').extract()
            item['Description'] = site.select('span[last()]/text()').extract()
            item['Number'] = site.select('span[@class="searchInfoLabel"]/span/@id').extract()
            item['Web_url'] = site.select('span[@class="searchInfoLabel"]/a/@href').extract()
            item['adress_name'] = site.select('span[@class="searchInfoLabel"]/span/text()').extract()
            item['Photo_name'] = site.select('img/@alt').extract()
            item['Photo_path'] = site.select('img/@src').extract()
            items.append(item)
        return items

我的 items.py 代码如下::

from scrapy.item import Item, Field

class Project2Item(Item):
    Catogory = Field()
    Bussiness_name = Field()
    Description = Field()
    Number = Field()
    Web_url = Field()
    adress_name = Field()
    Photo_name = Field()
    Photo_path = Field()

我的 settings.py 是:::

BOT_NAME = 'project2'

SPIDER_MODULES = ['project2.spiders']
NEWSPIDER_MODULE = 'project2.spiders'
ITEM_PIPELINES = (
    'project2.pipelines.MySQLStorePipeline',
)

我的管道代码是::

from scrapy import log
#from scrapy.core.exceptions import DropItem
from twisted.enterprise import adbapi

import MySQLdb.cursors


class MySQLStorePipeline(object):

    def __init__(self):
        #  hardcoded db settings

        self.dbpool = adbapi.ConnectionPool('MySQLdb',
                db='project',
                user='root',
                passwd='',
                host='127.0.0.1',
                port='3306',                            
                cursorclass=MySQLdb.cursors.DictCursor,
                charset='utf8',
                use_unicode=True
            )

def process_item(self, item, spider):
    # run db query in thread pool
    query = self.dbpool.runInteraction(self._conditional_insert, item)
    query.addErrback(self.handle_error)

    return item


def _conditional_insert(self, tx, item):
    insert_id = tx.execute(\
        "insert into crawlerapp_directory (Catogory, Bussiness_name, Description, Number, Web_url) "
        "values (%s, %s, %s, %s, %s)",
        (item['Catogory'][0],
         item['Bussiness_name'][0],
         item['Description'][0],
         item['Number'][0],
         item['Web_url'][0],
         )
        )

    tx.execute(\
        "insert into crawlerapp_adress (directory_id, adress_name) "
        "values (%s, %s)",
        (insert_id,
         item['adress_name'][0]
         )
        )

    tx.execute(\
        "insert into crawlerapp_photos (directory_id, Photo_path, Photo_name) "
        "values (%s, %s, %s)",
        (insert_id,
         item['Photo_path'][0],
         item['Photo_name'][0]
         )
        )
    log.msg("Item stored in db: %s" % item, level=log.DEBUG)
def handle_error(self, e):
    log.err(e)

请帮助我也从其他页面中删除数据..

4

0 回答 0