kindle manager

parseweb.py

@@ -1,8 +1,10 @@
 
 #########################################################
-## @file   : tbook.py
-## @desc   : douban book spide
-## @create : 2020/6/13
+## @file   : parseweb.py
+## @desc   : douban and amazon book spide
+##           amazon ASIN B07VKS1DRZ - https://www.amazon.cn/s?k=B07VKS1DRZ
+##           douban SID  25742200   - https://book.douban.com/subject/25742200
+## @create : 2020/6/14
 ## @author : Chengan
 ## @email  : douboer@gmail.com
 #########################################################
@@ -126,7 +128,7 @@ div class="result">
     </div>
   </div>"""
 
-class doubanSpide():
+class bookInfoSpide():
 
     """
     re_bn = re.compile(r'''
@@ -154,12 +156,11 @@ class doubanSpide():
         #re_end = re.compile(r'''<\/body><\/html>''')
         re_end = re.compile(r'''^<span class=\"a-letter-space\"><\/span><\/div><\/div>''')
 
-    #amazon ASIN B07VKS1DRZ - https://www.amazon.cn/s?k=B07VKS1DRZ
 
     def __init__(self):
         pass
 
-    def parse_books(self, mbkn: str):
+    def grab_book_info(self, mbkn: str):
         """mbkn - bookname to be spided
         return: {
             "25853071": { # sid
@@ -315,12 +316,12 @@ class doubanSpide():
 
 if __name__ == '__main__':
 
-    spide = doubanSpide()
+    spide = bookInfoSpide()
 
     for bkname in testbooks:
         bkname = re.split(r'[\(（\-\:：_\s]',bkname.strip())[0]
         print(bkname)
-        bkinfo = spide.parse_books(bkname)
+        bkinfo = spide.grab_book_info(bkname)
         filter_bkinfo = spide.filter_spide_books(bkname, bkinfo)
 
         logger.debug('================ {} ================'.format(bkname))