DoubanSpider/Spider.py

@@ -124,19 +124,3 @@ class DoubanBook(object):
         else:
             print('[Spider]检测到现有TAG数据，开始抓取...')
             self.get_data()
-
-
-def url_pool():
-    for row in douban.session.query(Douban.url, Douban.tag).all():
-        yield row
-
-
-if __name__ == '__main__':
-    logger = logging.getLogger("PAPA")
-    sleeptime = random.randint(0, 3)
-    with open("results.csv", "a", encoding='utf-8') as f:
-        writer = csv.writer(f)
-        writer.writerow(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime()))
-        writer.writerow(["书名", "作者", "上市时间", "价格", "评分", "书籍分类", "内容简介"])
-    douban = DoubanBook()
-    douban.main()

DoubanSpider/db.py

@@ -15,11 +15,13 @@ class Douban(Base):
     def __repr__(self):
         return "<Douban(id='%d', tag='%s',url='%s')>" % (self.id, self.tag, self.url)
 
+
 class Recording(Base):
     __tablename__ = 'Recording'
     id = Column(Integer, primary_key=True)
     data = Column(Integer, unique=True, nullable=False)
 
+
 if os.path.isfile('douban.db') is False:
     print('正在创建数据库...')
     Base.metadata.create_all()

main.py

@@ -2,9 +2,31 @@ import csv
 import logging
 import random
 import time
+from cmd import Cmd
 
+from DoubanSpider.db import Douban
 from DoubanSpider.Spider import DoubanBook
 
+
+class SpiderMain(Cmd):
+    def __init__(self):
+        super().__init__()
+        pass
+
+    def do_help(self, arg):
+        pass
+
+    def do_start(self, arg):
+        pass
+
+    def do_tag(self,arg):
+        pass
+
+def url_pool():
+    for row in douban.session.query(Douban.url, Douban.tag).all():
+        yield row
+
+
 if __name__ == '__main__':
     logger = logging.getLogger("PAPA")
     sleeptime = random.randint(0, 3)