zy content

ydyspider/bash/command.sh

@@ -2,4 +2,5 @@
 pwd=/home/www/ydyspider
 cd $pwd
 spider_name=$1
-/usr/local/python2.7.14/bin/scrapy crawl $spider_name
+cp_name=$2
+/usr/local/python2.7.14/bin/scrapy crawl $spider_name -a cp_name=$cp_name

ydyspider/spiders/zycontentSpider.py

@@ -18,13 +18,14 @@ class zycontentSpider(scrapy.Spider):
     def start_requests(self):
         self.crawler.stats.set_value('bid_list', [])
         param = self.bid
+        cp_name = '' if self.cp_name is None or self.cp_name == 'zycontent' else self.cp_name
         if param is not None:
             bid_list = param.split(',')
             for bid in bid_list:
                 url = self.base_url + '/bookdetail/{}'.format(bid) + self.query
                 yield scrapy.Request(url, callback=self.parse2, meta={"zhiyu_book_id": bid, "i": 0})
         else:
-            url = self.base_url + '/booklist' + self.query
+            url = self.base_url + '/booklist' + self.query + '&cp_name={}'.format(cp_name)
             yield scrapy.Request(url, callback=self.parse1, meta={"zhiyu_book_id": bid, "i": 0})
 
     def parse1(self,response):