def get_title(url): s = requests.session() response = request.urlopen(url) html = response.read() charset = chardet.detect(html)['encoding'] # 对该html进行编码的获取 result = s.get(url) if (charset == "GB2312" or charset is None): result.encoding = 'gbk' else: result.encoding = 'utf-8' content = result.text title = re.findall('<title>(.*)</title>', content)[0] return title
