def get_brand_from_parser(asin, debug_log):
# 根据asin获取url
urls = BaseCrawler.make_url(asin)
url = urls[0]
refer = urls[1]
# 获取ua
ua = UaPond.get_new_ua()
cookies = ''
ip = ''
ipQ = ''
# 调用下载器方法获取页面数据
html_data, cookie, is_error = get_html_useRequest(url,
ua,
ip,
cookies,
debug_log,
refer,
ipQ,
url_type='goods',
asin=asin)
# 调用商品解析的方法获取页面的品牌信息
brand = GoodsParser(html_data)._get_brand()
return brand
img = get_img(url, ua, ip, cookie, debug_log, referer, ipQ)
if img:
print('img: ', len(img), type(img))
img_str_list= amazon_captcha_crack.main(img)
img_string = ''.join(img_str_list)
return img_string
"""
if __name__ == '__main__':
time1 = time.time()
# from pprint import pprint
#
ip = '192.126.168.2:3128'
proxy = dict(https='https://%s' % (ip), )
print(proxy)
# html = get_html('https://www.amazon.com/dp/B01C4N6IBA', ip, proxy=proxy)
# print(type(html))
# print(len(html))
# parser = HtmlParser()
# pprint(parser.parser_goods(html, 'B01C4N6IBA'))
time2 = time.time()
print(time2 - time1)
# from conf.setting import DB_CONFIG, REDIS_CONFIG, BASE_DIR
#
UA = UaPond.get_new_ua()
# print(DB_CONFIG)
# print(REDIS_CONFIG)
# print(BASE_DIR)
print(UA)
def get_kw_ua(self):
return UaPond.get_kw_new_ua()