我有一个非常简单的代码,如下所示。抓取没问题,我可以看到所有生成正确数据的print语句。在Pipeline中,初始化工作正常。但是,process_item函数没有被调用,因为函数开头的print语句从未执行过。在
蜘蛛:comosham.py在
import scrapy
from scrapy.spider import Spider
from scrapy.selector import Selector
from scrapy.http import Request
from activityadvisor.items import ComoShamLocation
from activityadvisor.items import ComoShamActivity
from activityadvisor.items import ComoShamRates
import re
class ComoSham(Spider):
name = "comosham"
allowed_domains = ["www.comoshambhala.com"]
start_urls = [
"http://www.comoshambhala.com/singapore/classes/schedules",
"http://www.comoshambhala.com/singapore/about/location-contact",
"http://www.comoshambhala.com/singapore/rates-and-offers/rates-classes",
"http://www.comoshambhala.com/singapore/rates-and-offers/rates-classes/rates-private-classes"
]
def parse(self, response):
category = (response.url)[39:44]
print 'in parse'
if category == 'class':
pass
"""self.gen_req_class(response)"""
elif category == 'about':
print 'about to call parse_location'
self.parse_location(response)
elif category == 'rates':
pass
"""self.parse_rates(response)"""
else:
print 'Cant find appropriate category! check check check!! Am raising Level 5 ALARM - You are a MORON :D'
def parse_location(self, response):
print 'in parse_location'
item = ComoShamLocation()
item['category'] = 'location'
loc = Selector(response).xpath('((//div[@id = "node-2266"]/div/div/div)[1]/div/div/p//text())').extract()
item['address'] = loc[2]+loc[3]+loc[4]+(loc[5])[1:11]
item['pin'] = (loc[5])[11:18]
item['phone'] = (loc[9])[6:20]
item['fax'] = (loc[10])[6:20]
item['email'] = loc[12]
print item['address'],item['pin'],item['phone'],item['fax'],item['email']
return item
项目文件:
^{pr2}$ 管道文件:
class ComoShamPipeline(object):
def __init__(self):
self.locationdump = csv.writer(open('./scraped data/ComoSham/ComoshamLocation.csv','wb'))
self.locationdump.writerow(['Address','Pin','Phone','Fax','Email'])
def process_item(self,item,spider):
print 'processing item now'
if item['category'] == 'location':
print item['address'],item['pin'],item['phone'],item['fax'],item['email']
self.locationdump.writerow([item['address'],item['pin'],item['phone'],item['fax'],item['email']])
else:
pass
最终发现主要是以下两个原因 1将以下行添加到py设置! ITEM_PIPELINES = {‘[YOUR_PROJECT_NAME].pipelines.[YOUR_PIPELINE_CLASS]’: 300} 2当你的蜘蛛跑的时候交出物品! yield my_item 我的是第二个原因,设置完后立刻就好了 下载scrapy开发手册
参考文章
发表评论