Python execjs.compile() Examples

def request(self, content, retries=3):
        '''
        请求网页得到翻译结果
        :param content: 
        :param timeout: 每次请求的超时秒数
        :param retries: 最大重试次数，请求失败后有效
        :return: {'out':'翻译结果','word_mean':'单词解释'} 两者选一
        '''
        if time.time() - self.tkk_updatetime > 3600:
            self.update_tkk()
        for _ in range(retries):
            try:
                tk = execjs.compile(open(r"translate_google.js").read()).call('Ho', content, self.tkk)
                content = urllib.parse.quote(content)
                # sl:原始语言 tl:目标语言
                url = 'https://translate.google.cn/translate_a/single?client=webapp&sl=auto&tl=zh-CN&hl=en&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca&dt=rw&dt=rm&dt=ss&dt=t&otf=2&ssel=0&tsel=4&kc=1&tk=%s&q=%s' % (
                tk, content)
                res_trans = requests.get(url, **REQUEST_PARAMS)
                res_trans = res_trans.json()[0]
                res_trans_target = [i[0] for i in res_trans[:-1]]
                res_trans_target = ''.join(res_trans_target)
                return dict(out=res_trans_target)
            except Exception as e:
                pass
        return {} 

def get_csrf_token(skey):
    # 读取js脚本
    js = get_js('decrypt/getCSRFToken.js')

    # 加载js脚本引擎
    ctx = compile(js)

    # 调用js脚本中某个函数
    # 第1个参数为函数名，第2到第n个参数为该函数依次所需的参数
    tmp_data = ctx.call('getCSRFToken', str(skey))


    # 读取js脚本
    js = get_js('decrypt/md5.js')

    # 加载js脚本引擎
    ctx = compile(js)

    # 调用js脚本中某个函数
    # 第1个参数为函数名，第2到第n个参数为该函数依次所需的参数
    result = ctx.call('hex_md5', str(tmp_data))

    return result 

def get_sck(skey):

    # 读取js脚本
    md5 = get_js('decrypt/md5.js')

    # 加载js脚本引擎
    ctx = compile(md5)

    # 调用js脚本中某个函数
    # 第1个参数为函数名，第2到第n个参数为该函数依次所需的参数
    result = ctx.call('hex_md5', str(skey))

    return str(result)


# 获取g_tk值，这里的g_tk值算法由vip.qq.com获取，暂不清楚是否能直接用于其他域名 

def happigo(fun, mobile):
    s = requests.session()
    s.headers = headers
    g = s.get('https://www.happigo.com/register/')
    send_mobile_key = re.findall('<input type="hidden" id="send_mobile_key" name="send_mobile_key" value="(.*?)" />',g.text)[0]
    m = s.get('https://ecimg.happigo.com/resource/web/js/md5.js')
    ctx = execjs.compile(m.text)
    send_mobile_token = ctx.call('hex_md5',send_mobile_key+mobile)
    data = {'token':'ok','mobile':mobile,'send_mobile_key':send_mobile_key,'send_mobile_token':send_mobile_token,'v':'1.0','t':str(int(time.time()*1000))}
    s.headers['referer'] = 'https://www.happigo.com/register/'
    s.headers['x-requested-with'] = 'XMLHttpRequest'
    s.headers['x-tingyun-id'] = 'JEZ7HInwfsc;r=747473032'
    s.cookies['traceguid'] = 'webportalef19626169fd56134181bae74abdfd59'
    r = s.post('https://www.happigo.com/shop/index.php?act=login&op=send_auth_code&type=2',data=data)
    decoded_data = codecs.decode(bytes(r.text,encoding='utf-8'), 'utf-8-sig')
    if json.loads(decoded_data)['state'] == 'true':
        return success(fun, r.text)
    failure(fun, r.text) 

def get_us_page_count() -> int:
    """
    新浪财经-美股-总页数
    :return: 美股总页数
    :rtype: int
    """
    page = "1"
    us_js_decode = f"US_CategoryService.getList?page={page}&num=20&sort=&asc=0&market=&id="
    js_code = execjs.compile(js_hash_text)
    dict_list = js_code.call("d", us_js_decode)  # 执行js解密代码
    us_sina_stock_dict_payload.update({"page": "{}".format(page)})
    res = requests.get(
        us_sina_stock_list_url.format(dict_list), params=us_sina_stock_dict_payload
    )
    data_json = json.loads(res.text[res.text.find("({") + 1: res.text.rfind(");")])
    if not isinstance(int(data_json["count"]) / 20, int):
        page_count = int(int(data_json["count"]) / 20) + 1
    else:
        page_count = int(int(data_json["count"]) / 20)
    return page_count 

def bond_zh_hs_daily(symbol="sh010107"):
    """
    新浪财经-债券-沪深债券的的历史行情数据, 大量抓取容易封IP
    http://vip.stock.finance.sina.com.cn/mkt/#hs_z
    :param symbol: 沪深债券代码; e.g., sh010107
    :type symbol: str
    :return: 指定沪深债券代码的日 K 线数据
    :rtype: pandas.DataFrame
    """
    res = requests.get(
        zh_sina_bond_hs_hist_url.format(
            symbol, datetime.datetime.now().strftime("%Y_%m_%d")
        )
    )
    js_code = execjs.compile(hk_js_decode)
    dict_list = js_code.call(
        "d", res.text.split("=")[1].split(";")[0].replace('"', "")
    )  # 执行js解密代码
    data_df = pd.DataFrame(dict_list)
    data_df["date"] = data_df["date"].str.split("T", expand=True).iloc[:, 0]
    data_df.index = pd.to_datetime(data_df["date"])
    del data_df["date"]
    data_df.astype("float")
    return data_df 

def get_zh_bond_hs_page_count():
    """
    行情中心首页-债券-沪深债券的总页数
    http://vip.stock.finance.sina.com.cn/mkt/#hs_z
    :return: 总页数
    :rtype: int
    """
    params = {
        "node": "hs_z",
    }
    res = requests.get(zh_sina_bond_hs_count_url, params=params)
    page_count = int(re.findall(re.compile(r"\d+"), res.text)[0]) / 80
    if isinstance(page_count, int):
        return page_count
    else:
        return int(page_count) + 1 

def bond_zh_hs_cov_daily(symbol: str = "sh113542") -> pd.DataFrame:
    """
    新浪财经-债券-沪深可转债的历史行情数据, 大量抓取容易封IP
    http://vip.stock.finance.sina.com.cn/mkt/#hskzz_z
    :param symbol: 沪深可转债代码; e.g., sh010107
    :type symbol: str
    :return: 指定沪深可转债代码的日 K 线数据
    :rtype: pandas.DataFrame
    """
    res = requests.get(
        zh_sina_bond_hs_cov_hist_url.format(
            symbol, datetime.datetime.now().strftime("%Y_%m_%d")
        )
    )
    js_code = execjs.compile(hk_js_decode)
    dict_list = js_code.call(
        "d", res.text.split("=")[1].split(";")[0].replace('"', "")
    )  # 执行js解密代码
    data_df = pd.DataFrame(dict_list)
    data_df["date"] = data_df["date"].str.split("T", expand=True).iloc[:, 0]
    data_df.index = pd.to_datetime(data_df["date"])
    del data_df["date"]
    data_df.astype("float")
    return data_df 

def _get_zh_bond_hs_cov_page_count() -> int:
    """
    行情中心首页-债券-沪深可转债的总页数
    http://vip.stock.finance.sina.com.cn/mkt/#hskzz_z
    :return: 总页数
    :rtype: int
    """
    params = {
        "node": "hskzz_z",
    }
    res = requests.get(zh_sina_bond_hs_cov_count_url, params=params)
    page_count = int(re.findall(re.compile(r"\d+"), res.text)[0]) / 80
    if isinstance(page_count, int):
        return page_count
    else:
        return int(page_count) + 1 

def get_us_stock_name() -> pd.DataFrame:
    """
    u.s. stock's english name, chinese name and symbol
    you should use symbol to get apply into the next function
    :return: stock's english name, chinese name and symbol
    :rtype: pandas.DataFrame
    """
    big_df = pd.DataFrame()
    page_count = get_us_page_count()
    for page in tqdm(range(1, page_count + 1)):
        # page = "1"
        us_js_decode = "US_CategoryService.getList?page={}&num=20&sort=&asc=0&market=&id=".format(
            page
        )
        js_code = execjs.compile(js_hash_text)
        dict_list = js_code.call("d", us_js_decode)  # 执行js解密代码
        us_sina_stock_dict_payload.update({"page": "{}".format(page)})
        res = requests.get(
            us_sina_stock_list_url.format(dict_list), params=us_sina_stock_dict_payload
        )
        data_json = json.loads(res.text[res.text.find("({") + 1: res.text.rfind(");")])
        big_df = big_df.append(pd.DataFrame(data_json["data"]), ignore_index=True)
    return big_df[["name", "cname", "symbol"]] 

def stock_us_spot() -> pd.DataFrame:
    """
    新浪财经-所有美股的数据, 注意延迟 15 分钟
    :return: 美股所有股票实时行情
    :rtype: pandas.DataFrame
    """
    big_df = pd.DataFrame()
    page_count = get_us_page_count()
    for page in tqdm(range(1, page_count + 1)):
        # page = "1"
        us_js_decode = "US_CategoryService.getList?page={}&num=20&sort=&asc=0&market=&id=".format(
            page
        )
        js_code = execjs.compile(js_hash_text)
        dict_list = js_code.call("d", us_js_decode)  # 执行js解密代码
        us_sina_stock_dict_payload.update({"page": "{}".format(page)})
        res = requests.get(
            us_sina_stock_list_url.format(dict_list), params=us_sina_stock_dict_payload
        )
        data_json = json.loads(res.text[res.text.find("({") + 1: res.text.rfind(");")])
        big_df = big_df.append(pd.DataFrame(data_json["data"]), ignore_index=True)
    return big_df 

def __init__(self, **kwargs):
        super().__init__(**kwargs)
        self.year_list = ['1996', '1997', '1998', '1999', '2000']
        self.guid = 'aaaabbbb-aaaa-aaaabbbb-aaaabbbbcccc'
        with open('Wenshu\spiders\get_vl5x.js', encoding='utf-8') as f:
            jsdata_1 = f.read()
        with open('Wenshu\spiders\get_docid.js', encoding='utf-8') as f:
            jsdata_2 = f.read()
        self.js_1 = execjs.compile(jsdata_1)
        self.js_2 = execjs.compile(jsdata_2) 

def aes_enc(data, key, iv):
    bjs = get_jsfile('crypto.js')
    result = execjs.compile(bjs).call('enc', data, key, iv)
    return result 

def _get_zh_a_page_count() -> int:
    """
    所有股票的总页数
    http://vip.stock.finance.sina.com.cn/mkt/#hs_a
    :return: 需要抓取的股票总页数
    :rtype: int
    """
    res = requests.get(zh_sina_a_stock_count_url)
    page_count = int(re.findall(re.compile(r"\d+"), res.text)[0]) / 80
    if isinstance(page_count, int):
        return page_count
    else:
        return int(page_count) + 1 

def air_quality_watch_point(city: str = "杭州", start_date: str = "2018-01-01", end_date: str = "2020-04-27") -> pd.DataFrame:
    """
    真气网-监测点空气质量-细化到具体城市的每个监测点
    https://www.zq12369.com/
    :param city: 调用 air_city_list 接口获取
    :type city: str
    :param start_date: e.g., "2019-03-27"
    :type start_date: str
    :param end_date: e.g., ""2020-03-27""
    :type end_date: str
    :return: 指定城市指定日期区间的观测点空气质量
    :rtype: pandas.DataFrame
    """
    url = "https://www.zq12369.com/api/zhenqiapi.php"
    file_data = _get_file_content(file_name="crypto.js")
    ctx = execjs.compile(file_data)
    method = "GETCITYPOINTAVG"
    ctx.call("encode_param", method)
    ctx.call("encode_param", start_date)
    ctx.call("encode_param", end_date)
    city_param = ctx.call("encode_param", city)
    ctx.call("encode_secret", method, city_param, start_date, end_date)
    payload = {
        "appId": "a01901d3caba1f362d69474674ce477f",
        "method": ctx.call("encode_param", method),
        "city": city_param,
        "startTime": ctx.call("encode_param", start_date),
        "endTime": ctx.call("encode_param", end_date),
        "secret": ctx.call("encode_secret", method, city_param, start_date, end_date),
    }
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36"
    }
    r = requests.post(url, data=payload, headers=headers)
    data_text = r.text
    data_json = demjson.decode(ctx.call("decode_result", data_text))
    temp_df = pd.DataFrame(data_json["rows"])
    return temp_df 

def get_zh_index_page_count():
    """
    所有指数的总页数
    http://vip.stock.finance.sina.com.cn/mkt/#hs_s
    :return: int 需要抓取的指数的总页数
    """
    res = requests.get(zh_sina_index_stock_count_url)
    page_count = int(re.findall(re.compile(r"\d+"), res.text)[0]) / 80
    if isinstance(page_count, int):
        return page_count
    else:
        return int(page_count) + 1 

def stock_zh_index_daily(symbol="sh000922"):
    """
    从新浪财经-指数获取某个指数的历史行情数据, 大量抓取容易封IP
    :param symbol: str e.g., sz399998
    :return: pandas.DataFrame
                    open      high       low     close      volume
    date
    2015-06-16  2526.056  2577.092  2469.216  2487.513  2224345088
    2015-06-17  2476.863  2567.842  2422.229  2560.914  2181699840
    2015-06-18  2553.739  2587.655  2480.321  2480.674  2032781312
    2015-06-19  2431.218  2453.794  2286.967  2287.758  1687013248
    2015-06-23  2280.189  2341.795  2156.396  2341.359  1627453440
                  ...       ...       ...       ...         ...
    2019-11-11  1210.968  1210.968  1182.442  1182.718   415074658
    2019-11-12  1184.118  1196.425  1184.005  1195.790   397246387
    2019-11-13  1195.925  1195.925  1180.293  1185.293   334027614
    2019-11-14  1185.788  1187.431  1178.414  1180.791   271514767
    2019-11-15  1181.090  1181.739  1165.898  1166.536   338309880
    """
    params = {"d": "2020_2_4"}
    res = requests.get(zh_sina_index_stock_hist_url.format(symbol), params=params)
    js_code = execjs.compile(hk_js_decode)
    dict_list = js_code.call(
        "d", res.text.split("=")[1].split(";")[0].replace('"', "")
    )  # 执行js解密代码
    data_df = pd.DataFrame(dict_list)
    data_df["date"] = data_df["date"].str.split("T", expand=True).iloc[:, 0]
    data_df.index = pd.to_datetime(data_df["date"])
    del data_df["date"]
    data_df = data_df.astype("float")
    return data_df 

def _encrypt(form_data: dict):
        with open('./encrypt.js') as f:
            js = execjs.compile(f.read())
            return js.call('b', urlencode(form_data)) 

def py_to_js(js_file_path,js_func,*params):
	"""
	:usage:
		python传值给js脚本执行后获取其结果
	:param data:
		@js_file_path	: js脚本路径
		@js_func	 	: 要执行的js脚本的函数
		@*params	 	: python传给js函数的参数，可传多个
	:return:
		@result 	 	: js脚本执行后的结果
	"""
	js_script = get_js(js_file_path)
	JsContext = execjs.compile(js_script)
	result = JsContext.call(js_func,*params)
	return result 

def __init__(self):
        self.ctx = execjs.compile("""
        function TL(a) {
        var k = "";
        var b = 406644;
        var b1 = 3293161072;
        var jd = ".";
        var $b = "+-a^+6";
        var Zb = "+-3^+b+-f";
        for (var e = [], f = 0, g = 0; g < a.length; g++) {
            var m = a.charCodeAt(g);
            128 > m ? e[f++] = m : (2048 > m ? e[f++] = m >> 6 | 192 : (55296 == (m & 64512) && g + 1 < a.length && 56320 == (a.charCodeAt(g + 1) & 64512) ? (m = 65536 + ((m & 1023) << 10) + (a.charCodeAt(++g) & 1023),
            e[f++] = m >> 18 | 240,
            e[f++] = m >> 12 & 63 | 128) : e[f++] = m >> 12 | 224,
            e[f++] = m >> 6 & 63 | 128),
            e[f++] = m & 63 | 128)
        }
        a = b;
        for (f = 0; f < e.length; f++) a += e[f],
        a = RL(a, $b);
        a = RL(a, Zb);
        a ^= b1 || 0;
        0 > a && (a = (a & 2147483647) + 2147483648);
        a %= 1E6;
        return a.toString() + jd + (a ^ b)
    };
    function RL(a, b) {
        var t = "a";
        var Yb = "+";
        for (var c = 0; c < b.length - 2; c += 3) {
            var d = b.charAt(c + 2),
            d = d >= t ? d.charCodeAt(0) - 87 : Number(d),
            d = b.charAt(c + 1) == Yb ? a >>> d: a << d;
            a = b.charAt(c) == Yb ? a + d & 4294967295 : a ^ d
        }
        return a
    }
    """) 

def __init__(self):
        self.headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
        self.tk_gen = TkGenerator()
        self.pattern = re.compile(r'\["(.*?)(?:\\n)')
        self.max_limited = 3500 

def get_sign(rid, post_v, tt, ub9):
    docjs = execjs.compile(ub9)
    res2 = docjs.call('ub98484234')
    str3 = re.sub(r'\(function[\s\S]*toString\(\)', '\'', res2)
    md5rb = hashlib.md5((rid + '10000000000000000000000000001501' + tt + '2501' +
                         post_v).encode('utf-8')).hexdigest()
    str4 = 'function get_sign(){var rb=\'' + md5rb + str3
    str5 = re.sub(r'return rt;}[\s\S]*','return re;};', str4) 
    str6 = re.sub(r'"v=.*&sign="\+', '', str5)
    docjs1 = execjs.compile(str6)
    sign = docjs1.call(
        'get_sign', rid, '10000000000000000000000000001501', tt)
    return sign 

def get_js_36_str(i):
    """
    整数、浮点数 js方式转36进制
    :param i:
    :return:
    """
    js_body = '''
        function get_36_str(i) {
            return i.toString(36);
        };
    '''
    ctx = execjs.compile(js_body)
    return ctx.call("get_36_str", i) 

def MsgHandler():
    html=HttpClient_Ist.Get(Referer+'/infocenter?via=toolbar',Referer)
    fkey=re.findall(r'<div class="f-item f-s-i" id=".*?" data-feedsflag=".*?" data-iswupfeed=".*?" data-key="(.*?)" data-specialtype=".*?" data-extend-info=".*?"',html)
    if not fkey:
        raise Exception, 'Fail to find any feeds'
    g_qzonetoken=re.search(r'window\.g_qzonetoken = \(function\(\)\{ try\{return (.*?);\} catch\(e\)',html)
    g_qzonetoken=g_qzonetoken.group(1)
    ctx = execjs.compile('function qz(){location = "./"; return '+g_qzonetoken+'}')
    qztoken=str(ctx.call("qz"))
    split_string=re.split(r'<div class="f-item f-s-i" id=".*?" data-feedsflag=".*?" data-iswupfeed=".*?" data-key=".*?" data-specialtype=".*?" data-extend-info=".*?"',html)
    for i in range (0,len(fkey)):
        try:
            btn_string = re.search(r'<a class="item qz_like_btn_v3.*?" data-islike="0" data-likecnt=".*?" data-showcount=".*?" data-unikey="(.*?)" data-curkey="(.*?)" data-clicklog="like" href="javascript:;">', split_string[i+1])
            if btn_string is None:
                continue
            abstime = re.search(r'data-abstime="(\d*?)"',split_string[i+1])
            if abstime is None:
                continue
            like(btn_string.group(1),btn_string.group(2),fkey[i],abstime.group(1),qztoken)
            logging.info('已点赞'+btn_string.group(2))
        except Exception, e:
            logging.error(str(e))

# -----------------
# 主程序
# ----------------- 

def __init__(self):
        self.tkk = gettkk.get_tkk()  #从服务器获取TKK
        self.ctx = execjs.compile("""
        function b(a, b) {
            for (var d = 0; d < b.length - 2; d += 3) {
                var c = b.charAt(d + 2),
                    c = "a" <= c ? c.charCodeAt(0) - 87 : Number(c),
                    c = "+" == b.charAt(d + 1) ? a >>> c : a << c;
                a = "+" == b.charAt(d) ? a + c & 4294967295 : a ^ c
            }
            return a
        }

        function tk(a,TKK) {
            for (var e = TKK.split("."), h = Number(e[0]) || 0, g = [], d = 0, f = 0; f < a.length; f++) {
                var c = a.charCodeAt(f);
                128 > c ? g[d++] = c : (2048 > c ? g[d++] = c >> 6 | 192 : (55296 == (c & 64512) && f + 1 < a.length && 56320 == (a.charCodeAt(f + 1) & 64512) ? (c = 65536 + ((c & 1023) << 10) + (a.charCodeAt(++f) & 1023), g[d++] = c >> 18 | 240, g[d++] = c >> 12 & 63 | 128) : g[d++] = c >> 12 | 224, g[d++] = c >> 6 & 63 | 128), g[d++] = c & 63 | 128)
            }
            a = h;
            for (d = 0; d < g.length; d++) a += g[d], a = b(a, "+-a^+6");
            a = b(a, "+-3^+b+-f");
            a ^= Number(e[1]) || 0;
            0 > a && (a = (a & 2147483647) + 2147483648);
            a %= 1E6;
            return a.toString() + "." + (a ^ h)
        }
    """) 

def get_node_ctx():
        global ctx
        if ctx:
            return ctx
        with open(mainjs, encoding='utf-8') as f:
            jscode = f.read()
        ctx = execjs.compile(jscode, cwd=hnode)
        return ctx 

def Decrypt(content):
    ctx=execjs.compile(js)
    encodes=re.findall('strencode\("(.*?)","(.*?)"',content)[0]
    video=ctx.call('strencode',encodes[0],encodes[1])
    return video 

def auto_get_cookie(self):
        self.web = webdriver.Chrome()
        self.web.get(self.host)
        self.web.switch_to.frame('login_frame')
        log = self.web.find_element_by_id("switcher_plogin")
        log.click()
        time.sleep(1)
        username = self.web.find_element_by_id('u')
        username.send_keys(self.username)
        ps = self.web.find_element_by_id('p')
        ps.send_keys(self.password)
        btn = self.web.find_element_by_id('login_button')
        time.sleep(1)
        btn.click()
        time.sleep(10)
        print("begin...")
        self.web.get('https://user.qzone.qq.com/{}/main'.format(self.username))
        time.sleep(3)
        content = self.web.page_source
        qzonetoken = re.findall(re.compile("g_qzonetoken = \(function\(\)\{ try\{return \"(.*)?\""), content)[0]
        self.qzonetoken = qzonetoken
        cookie = ''
        # 获取cookie
        for elem in self.web.get_cookies():
            cookie += elem["name"] + "=" + elem["value"] + ";"
        self.cookies = cookie
        print(cookie)
        print("Login success")
        self.logging.info("login_success")
        self.web.quit()

    # 手动添加cookie完成登陆 

def extract_tid_from_unikey(self, unikey):
        tid = re.findall(re.compile('mood/(.*?)\.1'), unikey)
        if len(tid) > 0:
            return tid[0]
        else:
            return '' 

def calculate_qzone_token(self):
        ctx = execjs.compile(
            '''function qzonetoken(){ location = 'http://user.qzone.qq.com/%s'; return %s}''' % (
                self.raw_username, qzone_jother2))
        return ctx.call("qzonetoken")