クロールされたデータをmysqlに挿入するためにscrapyを取得しようとしていますが、コードは正常にクロールされ、バッファ内のデータを収集し、エラーは発生しませんが、データベースは更新されません. 「運がない」、「エラーがない」
パイプライン.py
from twisted.enterprise import adbapi
import datetime
import MySQLdb.cursors
class SQLStorePipeline(object):
def __init__(self):
self.dbpool = adbapi.ConnectionPool('MySQLdb', db='craigs',
user='bra', passwd='boobs', cursorclass=MySQLdb.cursors.DictCursor,
charset='utf8', use_unicode=True)
def process_item(self, items, spider):
# run db query in thread pool
query = self.dbpool.runInteraction(self._conditional_insert, items)
query.addErrback(self.handle_error)
return items
def _conditional_insert(self, tx, items):
# create record if doesn't exist.
# all this block run on it's own thread
tx.execute("select * from scraped where link = %s", (items['link'][0], ))
result = tx.fetchone()
if result:
log.msg("Item already stored in db: %s" % items, level=log.DEBUG)
else:
tx.execute(\
"insert into scraped (posting_id, email, location, text, title) "
"values (%s, %s, %s, %s, %s)",
(items['posting_id'][0],
items['email'][1],
items['location'][2],
items['text'][3],
items['title'][4],
)
)
log.msg("Item stored in db: %s" % items, level=log.DEBUG)
def handle_error(self, e):
log.err(e)
クロール コード
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import HtmlXPathSelector
from craigs.items import CraigsItem
class MySpider(CrawlSpider):
name = "craigs"
f = open("urls.txt")
start_urls = [url.strip() for url in f.readlines()]
f.close()
rules = [Rule(SgmlLinkExtractor(restrict_xpaths=('/html/body/blockquote[3]/p/a',)), follow=True, callback='parse_profile')]
def parse_profile(self, response):
items = []
img = CraigsItem()
hxs = HtmlXPathSelector(response)
img['title'] = hxs.select('//h2[contains(@class, "postingtitle")]/text()').extract()
img['posting_id'] = hxs.select('//html/body/article/section/section[2]/div/p/text()').extract()
items.append(img)
return items[0]
return img[0]
設定.py
BOT_NAME = 'craigs'
BOT_VERSION = '1.0'
SPIDER_MODULES = ['craigs.spiders']
NEWSPIDER_MODULE = 'craigs.spiders'
USER_AGENT = '%s/%s' % (BOT_NAME, BOT_VERSION)