saif.haq
/
keyword_ranking_crawler
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add keywords json

main
saif 2025-08-12 11:54:49 +05:00
parent 06f6ee9646
commit 93d715a0f6
2 changed files with 1017 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1002
keywords.json Normal file
View File

File diff suppressed because it is too large Load Diff

24
scrapper.py
View File

@ -12,13 +12,17 @@ import re
with open("marketplaces.json", "r", encoding="utf-8") as f: with open("marketplaces.json", "r", encoding="utf-8") as f:
data = json.load(f) data = json.load(f)
with open("keywords.json", "r", encoding="utf-8") as f:
keywords = json.load(f)
with open("cookies.json", "r", encoding="utf-8") as f: with open("cookies.json", "r", encoding="utf-8") as f:
cookies_ref = json.load(f) cookies_ref = json.load(f)
# Or if it's a Python dict already: # Or if it's a Python dict already:
marketplaces = data["marketplaces"] marketplaces = data["marketplaces"]
BASE_PATH= '/mnt/AmazonReports/Amazon/keyword_ranking' #BASE_PATH= '/mnt/AmazonReports/Amazon/keyword_ranking'
BASE_PATH= 'data'
MAX_PAGE = 10 MAX_PAGE = 10
@ -149,14 +153,16 @@ def get_amazon_ranks(url, marketplace, ratingPrefix, keyword, page, count):
driver = get_driver() driver = get_driver()
for marketplace, details in marketplaces.items():
url = details['url'] for keyword in keywords:
ratingPrefix = details['ratingPrefix'] for marketplace, details in marketplaces.items():
count =1 url = details['url']
for i in range(1, MAX_PAGE): ratingPrefix = details['ratingPrefix']
count = get_amazon_ranks(url, marketplace, ratingPrefix, 'comforter navy queen', i, count) count =1
if count == -1: for i in range(1, MAX_PAGE):
break count = get_amazon_ranks(url, marketplace, ratingPrefix, keyword, i, count)
if count == -1:
break
sleep(3) sleep(3)
driver.quit() driver.quit()