ebay-ml-lister/scrape_ids.py

from bs4 import BeautifulSoup as b
import re
import json
import requests
import concurrent.futures
import config as cfg

def get_isurl(category_id): # "get itemSearchURL"

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

    params = {
        "OPERATION-NAME":'findItemsByCategory',
        "SECURITY-APPNAME":cfg.sec['SECURITY-APPNAME'],
        "SERVICE-VERSION":"1.13.0",
        "RESPONSE-DATA-FORMAT":"JSON",
        "categoryId":category_id,
        "paginationInput.entriesPerPage":"1",
        "paginationInput.PageNumber":1,
        "itemFilter(0).name":"Condition",
        "itemFilter(0).value":"Used",
        "itemFilter.name":"HideDuplicateItems",
        "itemFilter.value":"true",
        }
    
    try:
        response = requests.get("https://svcs.ebay.com/services/search/FindingService/v1",
            params=params, timeout=24)
        response.raise_for_status()

    except requests.exceptions.RequestException:
        print('connection error')
        return url
    try:
        data = response.json()
        # NOTE approx 220 pages of listings per cat @ 35 items per page
        item_cond = "&rt=nc&LH_ItemCondition=3000&mag=1" # preowned
        urls = []
        url = data['findItemsByCategoryResponse'][0]['itemSearchURL'][0] 
        url = url+item_cond
        j = list(range(1,221))
        for i in j:
            pg = "&_pgn={}".format(str(i))
            url = url.replace('&_pgn=1', pg)
            urls.append(url)
            
    except (AttributeError, KeyError):
        print('AttributeError or KeyError. Exiting')

    return urls

def threaded_urls():

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

    with concurrent.futures.ThreadPoolExecutor() as executor:
        for future in executor.map(get_isurl, cat_list):
            urls.extend(future)

    return urls

def get_ids(url):
    '''
    Scrapes listing links for item ID in url
    '''
    html = requests.get(url).text
    soup = b(html, "html.parser")
    ids = list(soup.find_all(href=re.compile(r"[\d]+(?=\?hash)")))
    ids = [id['href'] for id in ids]
    ids = [re.findall(r"[\d]+(?=\?)", id)[0] for id in ids]
    ids = list(set(ids)) # necessary; two links are returned with pattern match

    return ids

def threaded_get_ids(urls):
    
    try:
        with open('item_id_results.txt') as f:
            ids = json.load(f)
    except FileNotFoundError:
        ids = []

    with concurrent.futures.ThreadPoolExecutor() as executor:
        for future in executor.map(get_ids, urls):
            ids.extend(future)

    item_id_results = [','.join(ids[n:n+20]) for n in list(range(0,
    len(ids), 20))] # 20-ItemID list created to maximize dataset/decrease calls given call constraints

    with open('item_id_results.txt', 'w') as f:
        json.dump(item_id_results, f)

    return item_id_results

def main():
    urls = threaded_urls()
    item_id_results = threaded_get_ids(urls)
    return item_id_results

if __name__=="__main__":
    main()