translate.py 文件源码

def query(self, word):
        import requests
        from bs4 import BeautifulSoup
        sess = requests.Session()
        headers = {
            'Host': 'open.iciba.com',
            'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:50.0) Gecko/20100101 Firefox/50.0',
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
            'Accept-Language': 'en-US,en;q=0.5',
            'Accept-Encoding': 'gzip, deflate'
        }
        sess.headers.update(headers)
        url = 'http://open.iciba.com/huaci_new/dict.php?word=%s' % (word)
        try:
            resp = sess.get(url, timeout=100)
            text = resp.text
            pattern = r'(<div class=\\\"icIBahyI-group_pos\\\">[\s\S]+?</div>)'
            text = re.search(pattern, text).group(1)
        except:
            return None
        if (resp.status_code == 200) and (text):
            soup = BeautifulSoup(text, 'lxml')
            ps = soup.find_all('p')
            trans = []
            for item in ps:
                transText = item.get_text()
                transText = re.sub(
                    r'\s+', ' ', transText.replace('\t', '')).strip()
                if transText:
                    trans.append(transText)
            return '\n'.join(trans)
        else:
            return None