From 622b824eaf4580d8702b3dba2701cede92bf2a2a Mon Sep 17 00:00:00 2001
From: spbeach46 <spbeacg46@gmail.com>
Date: Mon, 5 Apr 2021 14:38:07 -0700
Subject: [PATCH] fixed dict_pics errors. made more robust regex pattern

---
 ebay_api.py | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/ebay_api.py b/ebay_api.py
index e115655..f1077fe 100644
--- a/ebay_api.py
+++ b/ebay_api.py
@@ -267,21 +267,21 @@ class CurateData:
         instances. Modifies both class training and dropd dfs. Appends custom
         image url dict {'source':'destination'}.
         '''
-        expanded_class_training = class_training.explode('PictureURL').reset_index(drop=True)
-        # expanded_class_training.PictureURL.apply(lambda x: 'c:/users/unknown/
-        expanded_dropd = dropd.explode('PictureURL').reset_index(drop=True)
+        expanded_class = class_training.explode('PictureURL').reset_index(drop=True) # TODO DROp rows with nan values in PicturlURL cell
+        expanded_class = expanded_class.dropna(subset=['PictureURL'])
+        expanded_dropd = dropd.explode('PictureURL').reset_index(drop=True) # TODO Drop rows with nan values in PictureURL cells either here or before somewhere
+        expanded_dropd = expanded_dropd.dropna(subset=['PictureURL'])
         expanded_dropd = self.extract_df(expanded_dropd) # convert lists to values
-        # expanded_dropd.PictureURL.apply(lambda x: 'c:/users/unknown/
 
-        # curate.make_dict_pics(expanded_class_training) # custom image url dict
-        dict_pics_list = set(expanded_class_training.PictureURL.to_list()) # prolly need to create set long before df... immediately after Shopping or trading call
+        dict_pics_list = list(set(expanded_class.PictureURL.to_list())) # prolly need to create set long before df... immediately after Shopping or trading call
         destination = 'your target folder' # decide whether or not you want to set a default folder to have the user define it as input every time. or have this only 
         # defined in the download function
-        dict_pics = {k:destination+re.search(r'\w+(?=/\$_)', k).group()+'.jpg' for k in dict_pics_list} # TODO determine how to implement destination variable
+        dict_pics = {k:destination+re.search(r'[^/]+(?=/\$_|.jpg)', k).group()+'.jpg' for k in dict_pics_list} # TODO determine how to implement destination variable
+        # TODO still getting exceptions such as 'https://i.ebayimg.com/images/g/RG8AAOSwqMtd1esL/s-l1600.jpg'. add conditions to dict comprehension. 
 
         # re.search(r'\w+(?=/\$_)', a).group()
 
-        return expanded_class_training, expanded_dropd, dict_pics # TODO still need to replace source url to destination url in df cols and create custom dict {<source>, <distination>}
+        return expanded_class, expanded_dropd # TODO still need to replace source url to destination url in df cols and create custom dict {<source>, <distination>}
 
     def dl_pictures(self):
         '''