scrapy.log.INFO - python examples

Here are the examples of the python api scrapy.log.INFO taken from open source projects. By voting up you can indicate which examples are most useful and appropriate.

2 Examples 7

3 View Complete Implementation : middlewares.py
Copyright GNU General Public License v3.0
Author : snjoer
    def process_request(self,request,spider):
        user_agent = UserAgent()
        ua = user_agent.random
        if ua:
            log.msg('Current UserAgent: '+ua, level=log.INFO) 
            request.headers.setdefault('User-Agent', ua)

0 View Complete Implementation : middlewares.py
Copyright MIT License
Author : Karmenzind
    def process_response(self, request, response, spider):
        url = response.url

        if response.status in [301, 307]:
            log.msg("trying to redirect us: %s" % url, level=log.INFO)
            reason = 'redirect %d' % response.status

            return self._retry(request, reason, spider) or response
        interval, redirect_url = get_meta_refresh(response)
        # handle meta redirect

        if redirect_url:
            log.msg("trying to redirect us: %s" % url, level=log.INFO)
            reason = 'meta'

            return self._retry(request, reason, spider) or response

        hxs = HtmlXPathSelector(response)
        # test for captcha page
        captcha = hxs.select(
            ".//input[contains(@id, 'captchacharacters')]").extract()

        if captcha:
            log.msg("captcha page %s" % url, level=log.INFO)
            reason = 'capcha'

            return self._retry(request, reason, spider) or response

        return response