ebay-ml-lister/ebay_api.py

import importlib
import numpy as np
import concurrent.futures
import json
import requests
import pandas as pd
import config as cfg
import wget # NOTE may not need this
import shutil

class FindingApi:
    '''Methods for accessing eBays FindingApi services'''
    def __init__(self, service, pageNumber):
        self.service = [
            'findItemsAdvanced', 'findCompletedItems',
            'findItemsByKeywords', 'findItemsIneBayStores', 'findItemsByCategory',
            'findItemsByProduct'
            ][service]
        self.pageNumber = list(range(1, pageNumber)) # 77 pgs will give equal weights to cats given call constraints

    # departments = ["3034","93427"] (womens and mens)

    # examples of additional params you may want to add:
    # 'itemFilter(0).value':'Used'
    # 'itemFilter(1).name':'ListingType'
    # 'itemFilter(1).value':'AuctionWithBIN'

    def get_data(self, category_id, i):

        '''
        Gets raw JSON data fom FindingApi service call
        Currently being used to get itemIDs from categories
        '''

        params = {
            "OPERATION-NAME":self.service,
            "SECURITY-APPNAME":cfg.sec['SECURITY-APPNAME'],
            "SERVICE-VERSION":"1.13.0",
            "RESPONSE-DATA-FORMAT":"JSON",
            "categoryId":category_id,
            "paginationInput.entriesPerPage":"100",
            "paginationInput.PageNumber":i
            }

        # TODO add try excepts here
        try:
            response = requests.get("https://svcs.ebay.com/services/search/FindingService/v1",
                params=params, timeout=3)
            response.raise_for_status()

        except requests.exceptions.RequestException:
            print('connection error') #TODO DECIDE HOW TO HANDLE EXCEPTION
        data = response.json()
        return data

# TODO add some other options to finding call api such as for possibly filtering for used items only. This might give you a better dataset for training. Or maybe a mixture of new and used. Maybe 
# try and come up with a way to mathematically determine your odds of maximizing the number of pictures in your training set while reducing the number of useless images. Say for example, if you took a
# random set of 3 of 8 pictures total from each listing you might have a better chance of getting 3 good pictures in addition to increasing your training set. Or maybe you would have better luck with limiting
# it to the first 5 pictures instead of random. 

# You may even have more consistency with used shoes since they are "one-off" items without confusing multiple variations and colors. What else you can do is run small training sets on both new and used
# to see which one is more accurate or if a combo of both is more accurate. 

    def get_ids_from_cats(self):
        '''
        Creates a 20-itemId list to use for the ShoppingApi
        call
        '''
        pages = self.pageNumber
        itemid_results_list = []

        with open('cat_list.txt') as jf:
            cat_list = json.load(jf)

        for category_id in cat_list:

            args = [(category_id, i) for i in pages]

            with concurrent.futures.ThreadPoolExecutor() as executor:
                for future in executor.map(lambda p: self.get_data(*p), args):
                    data = future

                    try: # TODO if conditionals are not working due to each thread checking the same unedited item_id_results list
                        training = pd.read_csv('training.csv')
                        for item in data['findItemsByCategoryResponse'][0]['searchResult'][0]['item']:
                            if (item not in training.values) and (item not in itemid_results_list):
                                itemid_results_list.append(item['itemId'][0])

                    except (pd.errors.EmptyDataError, FileNotFoundError):
                        for item in data['findItemsByCategoryResponse'][0]['searchResult'][0]['item']:
                            if item not in itemid_results_list:
                                itemid_results_list.append(item['itemId'][0])

        item_id_results = list(set(itemid_results_list))
        item_id_results = [','.join(itemid_results_list[n:n+20]) for n in list(range(0,
            len(itemid_results_list), 20))]
        return item_id_results

# TODO during your try except conditionals just check the csv files. At the end you can create sets. You can creat another condition that says if the final set is smaller than 100k then you can call finding
# service on more pages (but only pages you haven't tried) and repeat the search process. 

# TODO instead of running through multiple try except loops try to implement set methods for efficiency and ease. Remember symmetric_difference, difference, intersection, set()
#        for category_id in cat_list:

class ShoppingApi:
    '''
    Creates objects from ShoppingApi service calls that can interact with
    pandas dataframes
    '''
    def get_item_from_findItemsByCategory(self, twenty_id):
        '''
        Gets raw JSON data from multiple live listings given multiple itemIds
        '''
        params = {
            "callname":"GetMultipleItems",
            "appid":cfg.sec['SECURITY-APPNAME'],
            "version":"671",
            "responseencoding":"JSON",
            "ItemID":twenty_id,
            "IncludeSelector":"ItemSpecifics",
            }

        # TODO Add try excepts here
        try:
            response = requests.get("https://open.api.ebay.com/shopping?", params=params, timeout=1)
            response.raise_for_status()
        except request.exceptions.RequestException:
            print('connection error')
        response = response.json()
        response = response['Item']
        return response

    def conky(self):
        '''
        For some reason item_id_results can only be passed as argument in executor.map
        if the variable is made within function
        '''
        data = [] # TODO I think you need to append a list of dictionaries rather than update a dictionary of dictionaries. Training var will require an updated dictionary though
        finding = FindingApi(4, 2)
        item_id_results = finding.get_ids_from_cats()
        with concurrent.futures.ThreadPoolExecutor() as executor:
            for future in executor.map(self.get_item_from_findItemsByCategory, item_id_results):
                #  print(future)
                for item in future:
                        data.append(item) # The end result should be a list of dicts where each dict in the list is a listing
                # data.update(future)
        # TODO save data here. You'll use this with your curate data class. SAve this as text file
        return data # TODO each future is a list of dictionaries because the output of any multithreader in this method is a list. 

    # data dictionary can't update from list of dicts unless iterated over. Might need a different way to update. 
# TODO It seems like the problem with updating the dictionary/csv file is starting here possibly; I think the item data is getting appended out of order from the item itself. 

class CurateData:
    '''
    Contains functions for curating data for machine learning training sets;
    Takes item in data from ShoppingApi request as argument and extracts/ creates key
    value pairs that gets updated to custom dataframe used in Ml training sets.
    '''

    def import_raw(self):
        '''
        imports raw response json from local file
        '''
        with open('raw_data.txt') as f:
            raw_data = json.load(f)
            return raw_data

    def raw_df(self, raw_data):
        '''
        creates pandas df from raw json. Indended to be used inline with direct
        data stream from ebay's APIs
        '''
        to_json = json.dumps(raw_data)
        raw_df = pd.read_json(to_json)
        return raw_df

    def to_training(self, raw_data): # NOTE need to create copies not views 
        '''
        creates first pass of potential labels for training set. This is the base
        df used to produce other training sets to use.
        '''
        raw_df = self.raw_df(raw_data)
        interm_df1 = raw_df.loc[:,['ItemID', 'PictureURL', 'PrimaryCategoryID', 'PrimaryCategoryName', 'Title', 'ItemSpecifics']]
        interm_df1[['ItemID', 'PrimaryCAegoryID']] = interm_df1.loc[:, ['ItemID', 'PrimaryCategoryID']].astype(str)
        training = interm_df1
        return training # TODO RENAME THIS FUNC AND RETURN VALUE

    def class_training(self, training):
        '''Training set for multiclass portion of training set. Used to train
        seprately from multilabel portion
        '''
        class_training = training.loc[:, ['PictureURL', 'PrimaryCategoryID']]
        return class_training

    def nvl_training(self, training):
        '''
        Training set for multilabel portion
        '''
        interm_df1 = pd.Series(training.ItemSpecifics)
        interm_df1 = interm_df1.apply(lambda x: x['NameValueList'])
        nvl_dict = interm_df1.apply(lambda x: {k:v for (k, v) in zip([n['Name'] for n in x], [v['Value'] for v in x])})
        nvl_df = pd.json_normalize(nvl_dict)
        nvl_training = pd.concat([pd.Series(training.PictureURL), nvl_df], axis=1)
        # TODO MAY HAVE TO RUN drop_nvl_cols and extract_contents in here
        return nvl_training

    def extract_contents(self, df):
        '''
        converts single-value lists of strings of any df to string if not null
        '''
        extracted_df = df.applymap(lambda x: ' '.join(x) if np.any(pd.notnull(x)) else np.nan)
        return extracted_df

    def drop_nvl_cols(self, nvl_training):
        col_drop = [
                'Fabric Type', 'Type of Sport', 'Mid Sole', 'Modified Item',
                'Modification Description', 'Article Type', 'Customized',
                'Character', 'Features', 'Colors', 'Shade', 'Product ID',
                'Personalized', 'Platform Height', 'Year Manufactured',
                'Trim Material', 'Fashion Element', 'Shaft Material',
                'Character Family', 'Heel to Toe Drop', 'Custom Bundle',
                'California Prop 65 Warning', 'Manufacturer Color', 'Main Color',
                'Collection', 'Midsole Type', 'Signed', 'US Shoe Size (Men#!#s)',
                'Calf Circumference', 'Handmade', 'Safety Standards',
                'Customised', 'Cleat Type', 'Cushioning Level', 'AU Shoe Size',
                'Country/Region of Manufacture', 'Type of Sport', 'Main Colour',
                'Look', 'Sole Type', 'Manufacturer Colour', 'Sole Material',
                'Toe Material', 'Feature', 'Length', 'Width', 'Size Chart',
                'Boot Height', 'Water Resistance Level', 'Material Composition',
                'Calf Width', 'Insole Material', 'UPC', 'Size Type'
                ]
        col_keep = [
                'PictureURL', 'Style', 'Department', 'Type', 'Gender', 'Closure', 'Performance/Activity',
                'Accents', 'Occasion', 'Toe Shape', 'Pattern', 'Activity',
                'Heel Style', 'Fastening', 'Heel Type', 'Toe Type', 'Departement',
                'Product Type', 'Sub Style', 'Season', 'Theme', 'Upper Material',
                ]
        # May be no difference between Product type and sub style; fastening and
        # closure; toe shape and toe type; occasion and performance/activity;
        # see if you can combine these somehow (you may not want this though).
        # Also consider keeping only cols that have plenty of values

        user_input = input('drop or keep cols?:')
        if 'keep' in user_input:
            dropd = nvl_training.loc[:,col_keep]
        else:
            dropd = nvl_training.drop(col_drop, axis=1)
        return dropd

    def combine_nvlclass(self, class_training, dropd):
        final_training = pd.concat([class_training, dropd], axis=1)
        return final_training # TODO might not need this

    def expand_nvlclass(class_training, dropd):
        '''
        takes image url list from each cell and expands them into separate/duplicate
        instances. Modifies both class training and dropd dfs. Appends custom
        image url dict {'source':'destination'}.
        '''
        #interm_s =class_training.PictureURL.apply(lambda x: len(x))
        #expanded_class_training = class_training.loc[np.repeat(class_training.index.values, interm_s)].reset_index(drop=True)
        expanded_class_training = class_training.explode('PictureURL').reset_index(drop=True)
        expanded_dropd = dropd.explode('PictureURL').reset_indext(drop=True)
        #expanded_dropd = dropd.loc[np.repeat(dropd.index.values, interm_s)].reset_index(drop=True) # TODO CHANGE this to use explode(). picture list needs preservation
        # prior to creating dropd and extracted. maybe run extraced_df after dropd or after running nvl_training

        #interm_s = interm_s.astype(str).applymap(lambda x: x.split(',')*4)
        return expanded_class_training, expanded_dropd

    def dl_pictures(self, dict_pic, expand=1):
        '''
        Downloads pictures from api to local storage using custom master dict
        '''

        with open('dict_pic.txt', 'w+') as jf: # TODO requires cleaning up
            dict_pics = json.load(jf)

        r = requests.get('<dict_pic>', stream=True)
        r.raw.decode_content = True
        filename = '<your destination + naming schem.jpg>'
        with open(filename, 'wb') as  f:
            shutil.copyfileobj(r.raw, f)
        # PictureURL in PictureURL list can't be downloaded....have to use indirect address in the form https://i.ebayimg.com/images/g/<unique code>/s-l<size>.jpg
        # in place of https://i.ebayimg.com/00/s/ODQwWDE2MDA=/z/<unique code>/$_1.JPG or use requests methods instead of wget and original PictureURL? yes, use requests
        # TODO pipeline gameplan: 5 files: master img download dict,raw_json.txt, raw_json.csv, master_class_training.csv, master_nvl_training.csv
        # cont... open raw_json.txt and append, same with csv --> process new data --> pull out image source+dest and expand new dfs for the additional pictures
        # if not exists and append to master img download dict
        # --> concat m_class_training df and m_nvl_training dfs with new data. Need to add inclusion tests for all files when opened and appended/concatted

        with concurrent.futures.ThreadPoolExecutor() as executor:
            for future in executor.map(download_function, master_url_dict):
                pass

    def update_df(self, data): # TODO save raw df as csv file
        '''
        Creates training instances for dataset. picture_url_list expanded to
        max available pictures with each picture url corresponding to features
        in common with same listing (i.e., because there are multiple pictures
        per listing, each picture will be its own training instance.
        '''
        pass

    # TODO You will have to mess around more with pandas df to find a better solution to creating your csv file: i.e., create dataframe from from instances, run through process to customize your df
    # for final training set for your ml model training. Contemplate on the future... you want ability to update main csv AND training csv; one for updating raw data instances from search queries, and 
    # the other for updating your training set. 


def main():
    '''
    Main program creates/updates a csv file to use for ML training from live
    ebay listings
    '''
    pass
# main goes here:

if __name__ == "__main__":
    main()

# Limited to 5000 calls to shopping api per day, and getMultpileitems service maxes out at 20 items
# per call leaving you 100,000 items per day for you pandas dataframe initially. So you'll have
# to divide these up into the categories. This will leave you with about 6.25K results per cat.
# More than enough data for your dataset.

# for future reference, to deal with inconsistent values in the nvl (due to sellers inputting custom values in the fields) you can drop either listings or k/v pairs that are unique which 
# can be determined from applying a function to determine frequency of k/v pairs--> list of unique k/v pairs--> function to determine frequency of unique k/v pairs--> drop those that have 1. 

# TODO NEED TO ADD TRY EXCEPT CONDITIONS FOR EVERY CALL MADE TO API SERVICES TO
# TO AVOID HICCUPS WHEN CREATING DATASET
# TODO YOU WILL HAVE TO FIND A WAY OF COLLECTING DATA FOR IMAGES OF TAGS EITHER USING YOUR OWN TAGS OR SOMEHOW FIND A WAY TO FIND TAGS ON OTHERS LISTINGS. CRUCIAL FOR THE LISTINGS PROCESS. May be as simple as adding a def to one of the apis to extract only the picture if it can identify what a tag looks like. So, it may actually be a good thing to include all the pictures in a training set but then when you're ready to begin training you'll have a data cleaning pipeline specific to training a model to either learn shoe features or information on tags. 

# Check the above list of cols I want to keep to see if there are duplicates with diff spelling and phrasing (e.g., Departement and Department, or Fastening and Closure Type)