Learn more  » Push, build, and install  RubyGems npm packages Python packages Maven artifacts PHP packages Go Modules Bower components Debian packages RPM packages NuGet packages

hemamaps / Scrapy   python

Repository URL to install this package:

/ downloadermiddlewares / useragent.py

"""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):
        o = cls(crawler.settings['USER_AGENT'])
        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)