search.py 文件源码

 复制代码def _solve_google_captcha(self, resp):
        # set up the captcha page markup for parsing
        tree = fromstring(resp.text)
        # extract and request the captcha image
        #captchaUrl = 'https://ipv4.google.com' + tree.xpath('//img/@src')[0]
        #print(captchaUrl)
        resp = self.request('https://ipv4.google.com' + tree.xpath('//img/@src')[0], redirect=False, cookiejar=self.cookiejar, agent=self.user_agent)
        # store the captcha image to the file system

        with open('/tmp/111.jpg','w') as fp:
            fp.write(resp.raw)
            fp.flush()
            print(fp.name)
            # open the captcha image for viewing in gui environments
            w = webbrowser.get()

            w.open('file://' + fp.name)
            self.alert(fp.name)

            _payload = {'captcha':raw_input('[CAPTCHA] Answer: ')}
            # temporary captcha file removed on close
        # extract the form elements for the capctah answer request
        form = tree.xpath('//form[@action="index"]')[0]
        for x in ['q', 'continue', 'submit']:
            _payload[x] = form.xpath('//input[@name="%s"]/@value' % (x))[0]
        # send the captcha answer
        return self.request('https://ipv4.google.com/sorry/CaptchaRedirect', payload=_payload, cookiejar=self.cookiejar, agent=self.user_agent)