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

minor fixes

main
saif 2025-08-13 14:33:57 +05:00
parent e9ac547c8b
commit 44cf2b4395
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
scrapper.py
View File

@ -122,8 +122,8 @@ def get_amazon_ranks(url, marketplace, ratingPrefix, keyword, page, count):
sleep(3) # Wait for JS to load sleep(3) # Wait for JS to load
items = driver.find_elements(By.XPATH, '//div[contains(@class,"s-result-item") and @data-asin]') items = driver.find_elements(By.XPATH, '//div[contains(@class,"s-result-item") and @data-asin]')
for idx, item in enumerate(items, start=1): for idx, item in enumerate(items, start=1):
asin = item.get_attribute("data-asin")
try: try:
asin = item.get_attribute("data-asin")
sponsored = check_sponsored(item) sponsored = check_sponsored(item)
title = item.find_element(By.XPATH, './/h2//span').text title = item.find_element(By.XPATH, './/h2//span').text
rating = item.find_element(By.XPATH, './/span[@class="a-icon-alt"]') rating = item.find_element(By.XPATH, './/span[@class="a-icon-alt"]')
@ -147,6 +147,7 @@ def get_amazon_ranks(url, marketplace, ratingPrefix, keyword, page, count):
}) })
count += 1 count += 1
except: except:
print( f"[ERROR] Error getting Amazon Ranks for: {marketplace} {keyword} {page} {idx}" )
continue continue
file_path = f"{BASE_PATH}/{int(time.time() * 1000)}-{marketplace}-{keyword}.json" file_path = f"{BASE_PATH}/{int(time.time() * 1000)}-{marketplace}-{keyword}.json"