scrapy源碼閱讀-UserAgentMiddleware

源碼閱讀如下：

"""Set User-Agent header per spider or use a default value from settings"""

from scrapy import signals


class UserAgentMiddleware(object):
    """This middleware allows spiders to override the user_agent"""

    def __init__(self, user_agent='Scrapy'):
        self.user_agent = user_agent

    @classmethod
    def from_crawler(cls, crawler):
        # 傳遞配置中的USER_AGENT值給初始化函數
        o = cls(crawler.settings['USER_AGENT'])
        # 在開始爬蟲任務時，嘗試讀取爬蟲的user_agent值來覆蓋配置中對應的值
        crawler.signals.connect(o.spider_opened, signal=signals.spider_opened)
        return o

    def spider_opened(self, spider):
        self.user_agent = getattr(spider, 'user_agent', self.user_agent)

    def process_request(self, request, spider):
        if self.user_agent:
            request.headers.setdefault(b'User-Agent', self.user_agent)

值得注意的是，在開啓此中間件時，如果不主動配置USER_AGENT請求就變得很有意思，因爲項目中USER_AGENT配置默認值是這樣的：

USER_AGENT = 'Scrapy/%s (+https://scrapy.org)' % import_module('scrapy').__version__

實際上我們需要的可能是能夠切換user_agent的中間件，所以可以這樣去實現：

1.在配置中將所有的user_agent組成一個列表

2.在中間件中用choice隨機獲取

from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware
from random import choice


class MyUserAgentMiddleware(UserAgentMiddleware):
    def process_request(self, request, spider):
        if self.user_agent:
            request.headers.setdefault(
                b'User-Agent',
                choice(self.user_agent)
            )