|
| 1 | + |
| 2 | +# author: Bartlomiej "furas" Burek (https://blog.furas.pl) |
| 3 | +# date: 2021.07.22 |
| 4 | +# |
| 5 | +# title: How to use loops to scrape data from API |
| 6 | +# url: https://stackoverflow.com/questions/68478524/how-to-use-loops-to-scrape-data-from-api/68479878?noredirect=1#comment121025287_68479878 |
| 7 | + |
| 8 | +import requests |
| 9 | + |
| 10 | +# --- functions --- |
| 11 | + |
| 12 | +def main(search_term, items_number=250): |
| 13 | + |
| 14 | + url = "https://shopee.sg/api/v4/search/search_items" |
| 15 | + |
| 16 | + params = { |
| 17 | + "by": "relevancy", |
| 18 | + "categoryids": 100630, |
| 19 | + "keyword": search_term, |
| 20 | + "limit": 100, |
| 21 | + "newest": 0, # default value at start |
| 22 | + "order": "desc", |
| 23 | + "page_type": "search", |
| 24 | + "scenario": "PAGE_GLOBAL_SEARCH", |
| 25 | + "version": "2" |
| 26 | + } |
| 27 | + |
| 28 | + for offset in range(0, items_number, 100): |
| 29 | + |
| 30 | + print('\n--- offset:', offset, '---\n') |
| 31 | + |
| 32 | + params["newest"] = offset # other parameters are the same |
| 33 | + |
| 34 | + limit = items_number - offset |
| 35 | + if limit < 100: |
| 36 | + params["limit"] = limit |
| 37 | + |
| 38 | + r = requests.get(url, params=params) |
| 39 | + data = r.json() |
| 40 | + |
| 41 | + print('>> items number in data:', len(data['items']), '\n') |
| 42 | + |
| 43 | + for number, item in enumerate(data['items']): |
| 44 | + |
| 45 | + print('number:', offset+number+1) |
| 46 | + |
| 47 | + basic = item['item_basic'] |
| 48 | + |
| 49 | + #print('keys:', basic.keys()) |
| 50 | + #for key, value in basic.items(): |
| 51 | + # print(f"{key}: {value}") |
| 52 | + |
| 53 | + # NAME |
| 54 | + name = basic['name'] |
| 55 | + #name = basic.get('name', '- unknown -') # safer if `name` may not exists in `data` |
| 56 | + print("Name:", name) |
| 57 | + |
| 58 | + # BRAND |
| 59 | + #brand = basic['brand'] |
| 60 | + brand = basic.get('brand') # safer if `brand` may not exists in `data` |
| 61 | + if brand is None: |
| 62 | + print() |
| 63 | + else: |
| 64 | + print("Brand:", brand) |
| 65 | + |
| 66 | + print('---') |
| 67 | + |
| 68 | +# --- main --- |
| 69 | + |
| 70 | +main("make-up") |
| 71 | +#main("make-up", 60) |
| 72 | +#main("make-up", 270) |
0 commit comments