如下代码是关于python django通过正则搜索页面上的email地址的代码,应该对码农有一些好处。
import refrom django.shortcuts import renderfrom pattern.web import URL, DOM, abs, find_urlsdef index(request): """ find email addresses in requested url or contact page """ error = '' emails = set() url_string = request.GET.get('url', '') EMAIL_REGEX = re.compile(r'[A-Z0-9._%+-]+@[A-Z0-9.-]+.[A-Z]{2,6}', re.IGNORECASE) # use absolute url or domain name url = URL(url_string) if url_string.startswith('http') else URL(domain=url_string,protocol='http') if url_string: try: dom = DOM(url.download(cached=True)) except Exception, e: error = e else: contact_urls = { url.string } # search links of contact page for link in dom('a'): if re.search(r'contact|about', link.source, re.IGNORECASE): contact_urls.add( abs(link.attributes.get('href',''), base=url.redirect or url.string)) for contact_url in contact_urls: # download contact page dom = DOM(URL(contact_url).download(cached=True)) # search emails in the body of the page for line in dom('body')[0].content.split('n'): found = EMAIL_REGEX.search(line) if found: emails.add(found.group()) data = { 'url': url_string, 'emails': emails, 'error': error, } return render(request, 'index.html', data) 复制代码