crawler.py 文件源码

def extractSummary(self, response):
        scripts = response.findAll('script')
        for script in scripts:
            if 'bookDesc_iframe' in script.text:
                group = re.search('bookDescEncodedData = "(.*)"', script.text)
                if group:
                    encoded_summary = urllib2.unquote(group.group(1))
                    summary_text = BeautifulSoup(encoded_summary, "html.parser") 
                    return summary_text.text
        return ""