'pdct_img_main_url'] and brm.find_brand(
pdt['pdct_name_on_eretailer'])['brand'] in mh_brands:
print(pdt['pdct_name_on_eretailer'] + "." +
pdt['pdct_img_main_url'].split('.')[-1])
response = requests.get(pdt['pdct_img_main_url'],
stream=True,
verify=False,
headers=headers)
# response.raw.decode_content = True
tmp_file_path = '/tmp/' + shop_id + 'mhers_tmp_{}.imgtype'.format(
abs(hash(pdt['pdct_img_main_url'])))
img_path = img_path_namer(shop_id, pdt['pdct_name_on_eretailer'])
with open(tmp_file_path, 'wb') as out_file:
shutil.copyfileobj(response.raw, out_file)
if imghdr.what(tmp_file_path) is not None:
img_path = img_path.split('.')[0] + '.' + imghdr.what(
'/tmp/' + shop_id + 'mhers_tmp_{}.imgtype'.format(
abs(hash(pdt['pdct_img_main_url']))))
shutil.copyfile(
'/tmp/' + shop_id + 'mhers_tmp_{}.imgtype'.format(
abs(hash(pdt['pdct_img_main_url']))), img_path)
products[url].update({
'img_path': img_path,
'img_hash': file_hash(img_path)
})
create_csvs(products, categories, searches, shop_id,
fpath_namer(shop_id, 'raw_csv'), COLLECTION_DATE)
validate_raw_files(fpath_namer(shop_id, 'raw_csv'))
driver.quit()
print(d['pdct_name_on_eretailer'], d['volume'])
url_mod = clean_url(url, root_url=root_url)
fpath = fpath_namer(shop_id, 'pdct', d['pdct_name_on_eretailer'], 0)
if not op.exists(fpath):
driver.get(url_mod)
sleep(2)
driver.save_page(fpath, scroll_to_bottom=True)
products = pdct_parsing(fpath, url, products)
print(products[url])
######################################
# # Download images ###########
######################################
# Download images
from ers import download_img
for url, pdt in products.items():
if 'pdct_img_main_url' in pdt and pdt['pdct_img_main_url'] and brm.find_brand(pdt['pdct_name_on_eretailer'])['brand'] in mh_brands:
print(pdt['pdct_name_on_eretailer'] + "." + pdt['pdct_img_main_url'].split('.')[-1])
orig_img_path = img_path_namer(shop_id, pdt['pdct_name_on_eretailer'])
img_path = download_img(pdt['pdct_img_main_url'], orig_img_path, shop_id=shop_id, decode_content=False, gzipped=False, debug=False)
if img_path:
products[url].update({'img_path': img_path, 'img_hash': file_hash(img_path)})
create_csvs(products, categories, searches, shop_id, fpath_namer(shop_id, 'raw_csv'), COLLECTION_DATE)
validate_raw_files(fpath_namer(shop_id, 'raw_csv'))
check_products_detection(shop_id, fpath_namer(shop_id, 'raw_csv'), shop_inventory_lw_csv)
driver.quit()