設置 user -agent 和 打開(注意路徑)dom
DOWNLOADER_MIDDLEWARES = {
#'news.middlewares.NewsDownloaderMiddleware': 543,
'news.middlewares.UserAgentMiddleware': 300,
}
#隨機換user-agent
class UserAgentMiddleware(object):
"""
給每個請求隨機切換一個User-Agent
"""
def process_request(self, request, spider):
user_agent = random.choice(us_list)
request.headers['User-Agent'] = user_agent
注意這樣能夠打印
request.headers['User-Agent']