en2cn/Utils/translator.py

#!/usr/bin/env/python
# -*- coding:utf-8 -*-


"""
在线翻译
"""

import http.client
import hashlib
import urllib
import random
import re
import json
import requests


def trans_baidu(str_text, mod="en2cn"):
    """
    2022.8月底开始收费了
    输入要翻译的文本(单词或句子或文章,但是<6000bytes)
    :param str_text:
    :return:
    """
    appid = '20191115000357320'  # 填写你的appid
    secretKey = 'ovn8spgUH6GQ_GhF7V6u'  # 填写你的密钥

    httpClient = None
    myurl = '/api/trans/vip/translate'

    fromLang = 'en'   # 原文语种
    toLang = 'zh'   # 译文语种
    salt = random.randint(32768, 65536)
    q = str_text
    sign = appid + q + str(salt) + secretKey
    sign = hashlib.md5(sign.encode()).hexdigest()
    myurl = myurl + '?appid=' + appid + '&q=' + urllib.parse.quote(q) + '&from=' + fromLang + '&to=' + toLang + '&salt=' + str(
    salt) + '&sign=' + sign

    try:
        httpClient = http.client.HTTPConnection('api.fanyi.baidu.com', timeout=5)
        httpClient.request('GET', myurl)
        # response是HTTPResponse对象
        response = httpClient.getresponse()
        result_all = response.read().decode("utf-8")
        result = json.loads(result_all).get("trans_result")[0]["dst"]
        # print(result)
        return result

    except Exception as e:
        print(e)
        return ""
    finally:
        if httpClient:
            httpClient.close()


def googleTranslate(text):
    headers = {
            'origin': "https://translate.google.cn",
            'referer': "https://translate.google.cn/",
            'sec-fetch-dest': "empty",
            'sec-fetch-mode': "cors",
            'sec-fetch-site': "same-origin",
            'x-same-domain': "1",
            # 'cookie': "NID=511=mJLHCmmZj7H4zcU4YUucXYSlaD67X5HEt4VVVm9Q04ZNr82Hoei_fig0IPjcnpmteHRktufKmckQtyTe6w3GdT0Uk8xTG8F3-ymMn1u6xNiQp4EGlTtFrmXYbCqGw-RJWtM3eQHBGJhxSSxGFCMEZwDuhRAM0bUy1uN2EKdftAI; _ga=GA1.3.126656540.1654615557; OTZ=6538526_24_24__24_; _gid=GA1.3.490013375.1656158367",
            # 'cookie': "NID=511=mJLHCmmZj7H4zcU4YUucXYSlaD67X5HEt4VVVm9Q04ZNr82Hoei_fig0IPjcnpmteHRktufKmckQtyTe6w3GdT0Uk8xTG8F3-ymMn1u6xNiQp4EGlTtFrmXYbCqGw-RJWtM3eQHBGJhxSSxGFCMEZwDuhRAM0bUy1uN2EKdftAI; _ga=GA1.3.126656540.1654615557; OTZ=6538526_24_24__24_; _gid=GA1.3.490013375.1656158367",
            # 'user-agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.53 Safari/537.36 Edg/103.0.1264.37",
            # 'user-agent': "'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36",
            # 'user-agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.53 Safari/537.36 Edg/103.0.1264.37",
            'user-agent': "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36",
            'accept-encoding': "gzip, deflate, br",
            'content-type': "application/x-www-form-urlencoded;charset=UTF-8",
            # 'x-client-data': 'CIW2yQEIpbbJAQjEtskBCKmdygEIrMfKAQj2x8oBCPfHygEItMvKAQihz8oBCNzVygEIi5nLAQjBnMsB',
            # 'Decoded': 'message ClientVariations {repeated int32 variation_id = [3300101, 3300133, 3300164, 3313321, 3318700, 3318774, 3318775, 3319220, 3319713, 3320540, 3329163, 3329601];}',
            # 'x-goog-batchexecute-bgr':'[";qrS4tPnQAAYvqchvD6lftQckgqu-IikmACkAIwj8Rl2XS1QudgthqdZU0SqH0vq1-Bet3w6a53VSL12iqjefO-AFZh8AAAD0TwAAAAZ1AQcXAM87g0YlzGEpU91FDlXisD9zIJjkeYnnWCmMotddHWrZBkIpzy46jxKdAuo3aVXneE15f0O10ZpS9nTBSJdcScQqzGcI93uNpDbDtSbwr8Xz67U4XIz5FW3C9I5y7bOK5pX3nMy3dad3_gdoicKNjO1U7ey1NqdWArjc5PE6uCn3YnoiN-YUhlwK-j702Vm8nz-6B4oKWr-e3NSr2nkrHLBU4WZ9AmIg4CpGGGfk8Ri2aTLchvslaLcG0gs3p1LqCVGrFMmCDR5oG7KKjZStPtiEAkYJaGGP8_RMLYiPzFieCluXD2UXjFr-l8wWYcE65veCnnk_m7F4LZwnbl9BLPcnaHzkvNYTP9ATsK-N8-_YZQoNRnZ6nAuuO6y5GnHRtdluT_7kcN8VNiARohU-Ml0FPK2KWhO0pwtaaYVlAREQLhliaB9QSRjsZ3px1ehUoYiHhXKb5X70ohOC4Slkt7XcbHziir_qaOZpf73UAucLEE_PEKkTWZ5ZbssiwmPpYsuZI7Blw92neAb2sgbOsltR3iO6We3_vBpZd7hFZMFBrTrD_VZKqAWntKZXCmhG5YIcCR8Td4I35BG_YugQ60Gh_tVzN877HHARJXxEcHM743G7GsqZAxbqqNu_Rj5q9VPbCR_nDD24Me-PMzyTKUUGR3I970nngEu6vLFl-0tEb7wJLzm2K_LwzdkJ2ZHxJlNI-YsNB5IwczOMSJwNwPqjzKy2BxRzSOHuDr2zEnCW-p9G4HLP84fVo9kJQdmTN7mt54oMuqgr7jpaVDNo-8tMFVNnY2Q1HoO2xG8MvKMVrOcqqdnKabsTlcCSHVkL8kOGSQY_m_5MUs2o_XRd5gGhZ57ounYDD6GOWJOH_8QCZMHdwgFt77aD4wN-5YX5WKLTVwBFY3lyr1I2TrlzJxDJJDnypdxsQBc3hheLtQQT4b0ESR7EL_2QxwAcQXSf7ZS93a9MkTaHilyhFu7vZCcAPTLt6EhWauUp-c0jB7RPv197GlKwszoW4Cxc7j6tudGTa5LL8L2zl3loLp5D3c2Oo9xORYYof0A",null,null,45,null,null,null,0,"2"]'
            # 'x-goog-batchexecute-bgr': '[";9-m46aTQAAYvqchvD6lfvixoEmPOG-YmACkAIwj8RmVE4Uk-wgpjt980C0vAZ5LBbEfkpJEt4ex2_2NMH89REoPTQx8AAAIqTwAAABh1AQcXANB82_W4qupq8ZfSWi61a126SF6X1py4DkFHHFKqueP-WTlQE6Z0E8C-Uw4o33saxgtvueS4jE2ohXNyZfkhqLj7oNw7BTvQOFyb1z2Wiie6BtVIqgCFjUzAuMM0_mvAJHY6VMVkvFTC8-O9oEzfWh_Axeq8xo-lMVUnjVkgMRBDDBGvrpyY1qbovJNH1NOkvIDy_rljBzS0RPi_37sa8sUFQ2OwFt1kmu6JS1YE-NbTSJpcZKuQKxP9EA4vqXN5l_m4T4xjrrqcrKlvwefRRXAKhAJQRBbT-YgNfCkOzgpGH5qVvEPKk7Ieax5SCs8_bE7ZWgB8vRxMfCQ8a_gd6U4hVQC_z5ZJ7AZOiSHJNAeAvv7RUZnXbILpOUV4YZr3jUt384lXzXuDeYiXR3XZHxoKi7F72FOcVrJsSnNETVS9mEkzSEnC5espGRlBFy0OaCxhjLgXZ07sHvDh4os82DDbDVPKBljrGCES1sYC1YwlHEAK0UJvz1PjM-DYiXxXM4Wnj5t3PL1g3Blgrb2jFHfOhLHq63AIo2HdWqawTggJpkpDH0fFBgQPc5rOPLK-6t7qTfR4v00kae6Qk5LHovqOoDuY87UUGbnUvzL3U1U7E2rhGsaTAt-CxMIx6NN_0LJdfsX_17oj_1d6ImRseI6xrFgwZDtoO5Wn2JsL77yBbZCZP3PNos0FhINR2o8qAVjEKDTb6Ymg7-T-fVB3iBq-AngHpCL2d6KwSgrEzdo4IdBzzWjBqU3JwxF-gzBm7b_FBy_knJbkXsHrdl9aFdMiPqCNBHbMVZnYH0i6ny2cLduqq3Pd-KB7CHwJixyF1vz-583xbpYcs2i5al68ScMhwuLqikoSAjGbGbxyjZEWl0n2FapLDLSs4RtWIYFnlrIUh5PKgLC6qPaa_iW6dWdQJoyyEvpUr90LsduNyzTlW2menACrUW2w6GMBkQ1SVhAOptbxLWyNggCLGT9Kyg5aeXS_NAKn7Y3y10eqILu_aGMOnGBizeiO2_brmmgtYPG6AeeT5X1RF08ECbZhSfAOTPiQvgQ5VaO-ybUMVq8EanCb9Q",null,null,1047,103,null,null,0,"2"]',
            'x-goog-batchexecute-bgr': '[";x9m42ZTQAAYEzRk0JM1f55ylXij7ksAmACkAIwj8RvxaMzZ1iOvebhAxZVDBGfAZwvR3YpljVZMeO6IUNBDwy5wDMh8AAABSTwAAAAJ1AQcXAIlC1pgskV32-yOzV6FmYVKrbi30KaxqJklCs1zPpGHX_hLbfLToBJPYoWuAZ_EDLf25YVbCAKmrwVah78G7syapqN1EYiNKZfShvZp60vbhcqeJWm7zwznMjhKjfdKuTq5Rq41JelMT_EQVGypnsHBqTderknEjPtt6TmIMIJjWRfjZsUVvRnde3oQCTLCuZUBVv3eTx3oT7W-EyIImn9XZEs8AKxQKK2vZRRc6VkveQMHi5DqyNT8YgqSntvAGOLImK402fdeua07F-nXkiiULeaJJ-7vjCMM-3jJNgEO6Vw6UJ6U74c_esPqwbtehb8dAO1uv_Lv9WJDX0KnHNkSRrsdD1z0lqxCQBZOxUpDGLc4Cvz_1FmWBU3Hy9RXuT_NW149LFR5JG6TgRQchengsqAUaC48H1vejyaG9Q6MDJdbWdnQxFtcNjIJDM7fOvVlsHzcNcCW11uP4AA55e28eCrbIi3ZeVRSRpWhWfRvoWg8Yzp1dIwnDS6vlnjr1UwZ6wLTfqF5ho0kSe1qcwza73nSZvi73NeyeaSkbsnO25bi4Jzp5sronwfrOqQALcgYWKX-krf6j-ug17IQm278z-sP4dJy3s4bZyWndiF5wO9tlJ7vZ_GRDiUVAZUNho_9WGi9oB89WvzjzqDMxvlx1WV_SonpzVaX9WZX0oIoDEs0FqRW165sinSZGAk63gejcPbH9ADj1xYQpP6YrS_iYNpabpSR544jwXT0V-f8bGf-bOBMViidcwgW0UloFN8i9v7ppuOxXbrp83H7Q8Lh5Lw0YCWijHaZ_JC3w-FZOa_j66ujYsxCF8t5cVB_O2Ttnks1eRYutJwg7a7nKvhDv24N_CPPvgn4bLG8WzEs_av9QGIfwGt1_ADJ4f8snG9rMsVOXzL7FMtV4b5Q9olCSi-CsXhwqxWIxDs9xdiolrpKKupfK89U6x13vv8kiq0Y5qnU9Un6AuQ",null,null,3,null,null,null,0,"2"]',
        }

    # url = "https://translate.google.cn/_/TranslateWebserverUi/data/batchexecute?rpcids=MkEWBc&source-path=/&f.sid=-127429216746380775&bl=boq_translate-webserver_20220622.08_p0&hl=zh-CN&soc-app=1&soc-platform=1&soc-device=1&_reqid=882057&rt=c"
    # url = "https://translate.google.cn/_/TranslateWebserverUi/data/batchexecute?rpcids=rpcids=MkEWBc&f.sid=-2984828793698248690&bl=boq_translate-webserver_20201221.17_p0&hl=zh-CN&soc-app=1&soc-platform=1&soc-device=1&_reqid=5445720&rt=c"
    # url = "https://translate.google.cn/_/TranslateWebserverUi/data/batchexecute?rpcids=MkEWBc&source-path=/&f.sid=5723009767851758792&bl=boq_translate-webserver_20220622.08_p0&hl=zh-CN&soc-app=1&soc-platform=1&soc-device=1&_reqid=66251&rt=c"
    url = "https://translate.google.cn/_/TranslateWebserverUi/data/batchexecute?rpcids=MkEWBc&source-path=/&f.sid=424574510049276369&bl=boq_translate-webserver_20220803.08_p0&hl=zh-CN&soc-app=1&soc-platform=1&soc-device=1&_reqid=1235460&rt=c"
    # data = {'f.req': f'[[["MkEWBc","[[\\"{text}\\",\\"zh-CN\\",\\"en\\",true],[null]]",null,"generic"]]]'}
    data = {'f.req': f'[[["MkEWBc","[[\\"{text}\\",\\"en\\",\\"zh-CN\\",true],[null]]",null,"generic"]]]'}

    means = []
    try:
        res=requests.post(url, headers=headers, data=data, timeout=5).text
        print(res)
        pattern = '\)\]\}\'\s*\d{3,4}\s*\[(.*)\s*'
        part1 = re.findall(pattern, res)
        part1_list = json.loads('[' + part1[0])[0]
        if part1_list[2] is None:
            # print(text)
            return text
        content1 = part1_list[2].replace('\n', '')
        content1 = json.loads(content1)
        print(content1)
        if len(content1) > 3 and content1[3]:
            if len(content1[3]) > 5:
                specific_means = content1[3][5:]
                # print("specific_means:", specific_means)
                if specific_means[0]:
                    part2_list = specific_means[0][0]
                    means = [j[0] for i in part2_list for j in i[1]]  # i[0]是词性
                    return "；".join(means)
        part2_list = content1[1][0][0][5:][0]
        means = [i[0] for i in part2_list]
        print(means)
        return "；".join(means)
    except:
        return ""


def translate_youdao(word=None):
    """
    结果不全
    :param word:
    :return:
    """
    url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule'
    # url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
    Form_data = {
        'i': word,
        'from': 'AUTO',
        'to': 'AUTO',
        'smartresult': 'dict',
        'client': 'fanyideskweb',
        'salt': '1528199964615',
        'sign': 'f6cf55466c876c404ff85ea3fc8c453f',
        'doctype': 'json',
        'version': '2.1',
        'keyfrom': 'fanyi.web',
        'action': 'FY_BY_REALTIME',
        'typoResult': 'false'
    }

    try:
        response = requests.post(url=url, data=Form_data, timeout=5)
        content = json.loads(response.text)
        print(content)
        # print(content['translateResult'][0][0]['tgt'])
        return content['translateResult'][0][0]['tgt']
    except:
        return ""


def youdaoTranslate(text):
    """
    通过html标签获取
    :param text:
    :return:
    """
    r = requests.get("http://dict.youdao.com/w/eng/{}/#keyfrom=dict2.top.suggest".format(text))
    all_content = r.content.decode('utf-8')
    trans_container = re.findall(r'<div class="trans-container">\s*<ul>(.+?)</ul>',
                                 all_content.replace("  ", " ").replace("\t", ""), flags=re.S)
    # print(trans_container)
    if trans_container:
        trans = [i for i in re.split(r"</?li>", trans_container[0]) if i.strip() and re.search(
                "[(（]\s*人名\s*[）)]", i) is None]  # 人名的翻译不需要
        return ";#;" .join(trans)
    return ""


def haiciTranslate(text):
    """
    通过html标签获取
    :param text:
    :return:
    """
    r = requests.get("https://dict.cn/search?q={}".format(text))
    all_content = r.content.decode('utf-8')
    # print(all_content)
    dict_basic = re.findall(r'<ul class="dict-basic-ul">(.+?)</ul>',
                            all_content.replace("  ", " ").replace("\t", ""), flags=re.S)
    if not dict_basic:
        dict_basic = re.findall(r'<div class="basic clearfix">[\n\s]*<ul\s*>(.+?)</ul>',
                                all_content.replace("  ", " ").replace("\t", ""), flags=re.S)
    if dict_basic:
        trans = [re.sub("</?span>|</?strong>", "", i).replace("\n", "") for i in
                 re.findall(r"<li>(.+?)</li>", dict_basic[0], flags=re.S) if i.strip() and re.search(
                "[(（]\s*人名\s*[）)]", i) is None]
        return ";#;".join(trans)
    return ""


def haici_zh2en(text):
    r = requests.get("https://dict.cn/search?q={}".format(text), timeout=0.5)
    all_content = r.content.decode('utf-8')
    # print(all_content)
    dict_basic = re.findall(r'<div class="layout cn">(.+?)</div>',
                            all_content.replace("  ", " ").replace("\t", ""), flags=re.S)
    if dict_basic:
        en_list = re.findall('<a href=[^<]+?>(.+?)</a>', dict_basic[0], flags=re.S)
        en_list = [en.strip() for en in en_list]
        # print(en_list)
        return en_list


def baiduTranslate(text):
    """
    通过html标签获取
    :param text:
    :return:
    """
    # url = "https://fanyi.baidu.com/translate?aldtype=16047&query=break+down&keyfrom=baidu&smartresult=dict&lang=auto2zh#en/zh/break%20down"
    # url = "https://fanyi.baidu.com/#en/zh/break%20down"
    url = "https://fanyi.baidu.com/sug"
    Form_data = {
        'kw': text,
    }
    response = requests.post(url=url, data=Form_data, timeout=5)
    content = json.loads(response.text)
    print(content)


def en2ch_baidu(text):
    """
     百度翻译
     :return:
     """
    url = "https://fanyi.baidu.com/transapi"
    Form_data = {
        'query': text,  # .replace(" ", "+")
        'from': "en",
        'to': "zh",
        'source': "txt"
    }
    headers = {
        # "Acs-Token": "1662274986285_1662362866177_PZ9RGDfoZT611QxcCOPF8OFKwuWbo2SxPixIRvRUghgD6AKWj+XA4XpEy7jAsAxs3jxn/CnuUNVYI3E2GZI/pkKZt9XbuQOuHUVVAf6WjA7RfsNhNa0Va1Rr9au9Fskav7ZLIVmTCJ+cFFnstBktKqO8OFOYHfdVgXFcqjPzmz34yuMe/0xH8FmAibeLtkQE/OHK4rJ18afENGyeGlFpY1R/mQUCfROo1CjZ1wk9yhUFxFZmgToyLDDuIfngU3HPylJZtk6LmV20vbSS8hA+7vJk4XPppOLRI/+Uapoks//SxVm2OtpMlmM4zGuQ82N9YBaQy3nS2NjbYy08hnNI1rsPDikdQI0tBawhm91wsrgMsdXaRSfkEqy7ZpAOMH0ebMYck5r4l+OSXe7lR3XoA4CZU6Rd+eaQ9xHktcdtaKA=",
        "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
        "Cookie": 'PSTM=1646122173; BIDUPSID=4A46D96DC8423B1990661EC67CB17B97; __yjs_duid=1_5eebbceeddec85cf72e17b95994355071646122377960; REALTIME_TRANS_SWITCH=1; HISTORY_SWITCH=1; FANYI_WORD_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; APPGUIDE_10_0_2=1; BAIDUID=68FE11EE3BE9ADA190124B58EB36B628:FG=1; MCITY=-289%3A; H_PS_PSSID=; BDORZ=FFFB88E999055A3F8A630C64834BD6D0; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1666148184,1666156674,1666168716,1666248882; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1666248882; BAIDUID_BFESS=68FE11EE3BE9ADA190124B58EB36B628:FG=1; delPer=0; PSINO=5; BA_HECTOR=218l21alahak2g00ak0k45e51hl268u1a; ZFY=tzTetLMt:AQKpcqHBdtdKVRVB8GNVB7XLc:BQRFb:BJvjQ:C; BDRCVFR[b3Q6T2w4uHD]=qdOo65HpBYTTh7znWc8mvqV; ab_sr=1.0.1_NWU3MmM0NWQyOWQxZmY5ZTBhZDNhODcwNTBmN2JkMjM3YmVjZWFlNzE2ODJmZWFjMzNhNWQwM2RmZDc4NGQ4ODJiMTVhMGUxZWM4YzkzMmI2ZDY2N2YzMWY0MWFkOWZkMjFkNzQ0YTc1NmFjOWJhNzRmZjVlZjUwZmNmNjc1ZTlhNzYxYTEzODkxY2NiZWMzOGVmMGIwMWFlYmNjNzhlYg==',
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36",
    }
    # url = "https://fanyi.baidu.com/translate?aldtype=16047&query=break+down&keyfrom=baidu&smartresult=dict&lang=auto2zh"
    response = requests.post(url=url, data=Form_data, headers=headers, timeout=5)
    # re = eval("u" + "\'" + response.text + "\'")
    # aa = response.content.decode('unicode_escape')
    content = json.loads(response.content)
    print(content)
    # try:
    if "result" in content:
        res = eval(content["result"].replace("null", "\"\""))["content"]
        mean_list = []
        for i in res[0]['mean']:
            # print(i)
            ptag = i["pre"] if "pre" in i else ""
            mean = list(i["cont"].keys())
            mean_list.append(ptag + ";".join(mean))
        return "\n".join(mean_list)
    if "data" in content:
        mean_list = []
        for i in content['data']:
            # print(i['dst'])
            mean_list.append(i['dst'])
        return "\n".join(mean_list)
    # except:
    #     return ""


def ch2en_baidu(text):
    url = "https://fanyi.baidu.com/transapi"
    Form_data = {
        'query': text.replace(" ", "+"),
        'from': "zh",
        'to': "en",
        'source': "txt"
    }
    headers = {
        # "Acs-Token": "1662274986285_1662362866177_PZ9RGDfoZT611QxcCOPF8OFKwuWbo2SxPixIRvRUghgD6AKWj+XA4XpEy7jAsAxs3jxn/CnuUNVYI3E2GZI/pkKZt9XbuQOuHUVVAf6WjA7RfsNhNa0Va1Rr9au9Fskav7ZLIVmTCJ+cFFnstBktKqO8OFOYHfdVgXFcqjPzmz34yuMe/0xH8FmAibeLtkQE/OHK4rJ18afENGyeGlFpY1R/mQUCfROo1CjZ1wk9yhUFxFZmgToyLDDuIfngU3HPylJZtk6LmV20vbSS8hA+7vJk4XPppOLRI/+Uapoks//SxVm2OtpMlmM4zGuQ82N9YBaQy3nS2NjbYy08hnNI1rsPDikdQI0tBawhm91wsrgMsdXaRSfkEqy7ZpAOMH0ebMYck5r4l+OSXe7lR3XoA4CZU6Rd+eaQ9xHktcdtaKA=",
        "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
        "Cookie": 'PSTM=1646122173; BIDUPSID=4A46D96DC8423B1990661EC67CB17B97; __yjs_duid=1_5eebbceeddec85cf72e17b95994355071646122377960; REALTIME_TRANS_SWITCH=1; HISTORY_SWITCH=1; FANYI_WORD_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; APPGUIDE_10_0_2=1; BAIDUID=68FE11EE3BE9ADA190124B58EB36B628:FG=1; MCITY=-289%3A; H_PS_PSSID=; BDORZ=FFFB88E999055A3F8A630C64834BD6D0; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1666148184,1666156674,1666168716,1666248882; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1666248882; BAIDUID_BFESS=68FE11EE3BE9ADA190124B58EB36B628:FG=1; delPer=0; PSINO=5; BA_HECTOR=218l21alahak2g00ak0k45e51hl268u1a; ZFY=tzTetLMt:AQKpcqHBdtdKVRVB8GNVB7XLc:BQRFb:BJvjQ:C; BDRCVFR[b3Q6T2w4uHD]=qdOo65HpBYTTh7znWc8mvqV; ab_sr=1.0.1_NWU3MmM0NWQyOWQxZmY5ZTBhZDNhODcwNTBmN2JkMjM3YmVjZWFlNzE2ODJmZWFjMzNhNWQwM2RmZDc4NGQ4ODJiMTVhMGUxZWM4YzkzMmI2ZDY2N2YzMWY0MWFkOWZkMjFkNzQ0YTc1NmFjOWJhNzRmZjVlZjUwZmNmNjc1ZTlhNzYxYTEzODkxY2NiZWMzOGVmMGIwMWFlYmNjNzhlYg==',
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36",
    }
    response = requests.post(url=url, data=Form_data, headers=headers, timeout=0.5)
    content = json.loads(response.content)
    # print(content)
    mean_list = []
    if "result" in content:
        res = eval(content["result"].replace("null", "\"\""))["content"]
        for i in res[0]['mean']:
            # print(i)
            ptag = i["pre"]
            mean = list(i["cont"].keys())
            # mean_list.append(ptag + ";".join(mean))
            mean_list.extend(mean)
        # print("\n".join(mean_list))
    if "data" in content:
        for i in content['data']:
            # print(i['dst'])
            mean_list.append(i['dst'])
    return mean_list


def KM_en2ch(text):
    """
    KM词典，通过html标签获取   https://kmcha.com
    :param text:
    :return:
    """
    word = str(text).strip().replace(" ", "%20").replace("!", " ")  # .replace(".", "")
    r = requests.get("https://kmcha.com/dict/{}".format(word.strip()))
    text = r.content.decode('utf8')
    # print(text)
    res_means = re.findall("<ul>(.+?)</ul>", text, flags=re.S)
    if res_means:
        means = re.findall('<li(?=[\s>])[^>]*?>(.+?)</li>', res_means[0])
        means = [i.replace("&lt;", "<").replace("&gt;", ">") for i in means if "人名" not in i]
        # print(means)
        # print(";##;".join(means))
        return ";#;".join(means)
    return ""


def Bing_en2ch(text):
    """
    必应词典，通过html标签获取 https://cn.bing.com/dict/
    :param text:
    :return:
    """
    print("raw_word:", text)
    word = str(text).replace("!", " ").replace("  ", " ").strip()
    while "  " in word:
        word = word.replace("  ", " ")

    if len(re.findall("…+|\.{3,}", word)) > 1:
        word = re.sub("(…+|\.{3,})$", "", word.strip())
        word = re.sub("(…+|\.{3,})\s*", "…", word.strip())
    # word = word.replace(" ", "+").replace(".", "").strip()
    print(word)

    r = requests.get("https://cn.bing.com/dict/{}".format(word))
    text = r.content.decode('utf8')
    if '<div class=" contentPadding">' not in text:
        r = requests.get("https://cn.bing.com/dict/search?q={}".format(word))
        text = r.content.decode('utf8')
    # print(text)
    a = re.findall('<div class=" contentPadding">(.+?)</ul></div><!--foo--></footer><script type="text/javascript">', text, flags=re.S)
    # print(a[0])
    all_mean = []
    mean_net = []
    mean_text = ""
    synonyms = []
    antonyms = []
    if a:
        mean1 = []
        mean_head = re.findall("<ul>(.+?)</ul>", a[0], flags=re.S)  # 开头给出的释义
        if mean_head:
            mean_1 = re.findall('<span class="[^>]*?">(.*?)</span><span [^>]*?"><span>(.+?)</span></span>', a[0], flags=re.S)
            # mean_1 = [i[0]+i[1] for i in mean_1 if i[0] != "网络"]
            # mean_net = [i[1] for i in mean_1 if i[0] == "网络"]
            new_mean_1 = []
            for i in mean_1:
                mm = i[1]
                if '<a href' in i[1]:
                    mm = re.sub(r'<a href=[^>]+?">(.+?)</a>', r"\1", mm)
                    mm = re.sub('</?span>', "", mm)
                if i[0] != "网络":
                    new_mean_1.append(i[0]+mm)
                else:
                    mean_net.append(mm)
            mean1.extend(new_mean_1)
            # mean_text = ";##;".join(all_mean)
            # print(mean_text)
        # print("开头的释义", mean1)
        # ----------------------不带词性----------------------------
        # # b = re.findall("<table>.*?</table>", a[0])
        # # b = [re.search('<span class="bil b_primtxt">(.+?)</span>', i).group(1) for i in b if "bil b_primtxt" in i]
        # b = re.findall('<span class="bil b_primtxt">(.+?)</span>', a[0])
        # print("b权威英汉双解：", b)
        # b1 = re.findall('<span class="p1-1 b_regtxt">(.+?)</span>', a[0])
        # print("b1英汉：", b1)
        # -------------------------------------------------
        mean2 = []
        pos2 = ""
        bi2 = re.split('<div class="li_pos"><div class="pos_lin">', a[0])
        for i in bi2[1:]:
            pos2 = re.findall('<div class="pos">(.+?)</div>', i)[0]
            b = re.findall('<span class="bil b_primtxt">(.+?)</span>', i)
            mean2.append(pos2 + "; ".join(list(set(b))))
        # print("mean2权威英汉双解：", mean2)

        mean3 = []
        pos3 = ""
        bi = re.findall('<div id="crossid" style="display:none;"><table>(.+?)</table>', a[0])
        if bi:
            for n, i in enumerate(re.findall('<td>(.+?)</td>', bi[0])):
                if n % 2 == 0:
                    pos3 = re.findall('<div class="pos pos1">(.+?)</div>', i)[0]
                else:
                    b1 = re.findall('<span class="p1-1 b_regtxt">(.+?)</span>', i)
                    mean3.append(pos3+"; ".join(list(set(b1))))
        # print("mean3英汉：", mean3)

        b2 = re.findall('<div class="p1-1 b_regtxt">(.+?)</div>', a[0])
        print("b2:", b2)
        b2 = [k for k in b2 if k not in mean_net and re.search("([；;]\s*|^)"+k+"([；;]\s*|$)",
                                                               ";".join(mean_net)) is None]
        print("mean_net开始：", mean_net)
        if b2:
            mean_net.append("【次】->")
            mean_net.extend(b2)

        if mean1:
            all_mean.append("【第一种】"+";<br>".join(mean1))
        if mean2:
            all_mean.append("【第二种】"+";<br>".join(mean2))
        if mean3:
            all_mean.append("【第三种】"+";<br>".join(mean3))
        if mean_net:
            # all_mean.append("<网络>"+";".join([j for j in mean_net if j not in mean_text]))
            mean_net_nodupl = list(set(mean_net))
            mean_net_nodupl.sort(key=mean_net.index)
            all_mean.append("<网络>" + ";".join(mean_net_nodupl))
        mean_text = ";<br>".join(all_mean)

        antoid = re.search('(<div id="antoid" .*?</div></div></div>)', a[0])
        if antoid:
            antonyms = re.findall('<span class="p1-4 b_alink">(.+?)</span>', antoid.group(1))

        synoid = re.search('(<div id="synoid" .*?</div></div></div>)', a[0])
        if synoid:
            synonyms = re.findall('<span class="p1-4 b_alink">(.+?)</span>', synoid.group(1))
        print("反义词:", antonyms)
        print("同义词:", synonyms)
        print(mean_text)
    return mean_text, synonyms, antonyms


def KM_ch2en(word_zh):
    r = requests.get("https://kmcha.com/dict/{}".format(word_zh.strip()), timeout=0.5)
    text = r.content.decode('utf8')
    if "{}的英文翻译".format(word_zh.strip()) in text:
        en_list = re.findall("的英文翻译</strong>[\s\n]*</p>[\s\n]*<p>(.+?)</p>", text, flags=re.S)
        en_list = sum([re.findall("<span>(.+?)</span>", i) for i in en_list], [])
        # print(en_list)
        return en_list


if __name__ == '__main__':
    import time
    import concurrent
    t1 = time.time()
    # KM_ch2en("高速公路")
    # Bing_en2ch("二百")
    # haici_zh2en("高速公路")
    print(haici_zh2en("稳"))
    # print(youdaoTranslate("at worst"))
    # print(haiciTranslate("at worst"))
    # print(KM_en2ch("at worst"))
    # trans_baidu("break down")
    # baiduTranslate("salad")
    # baiduTranslate("无害的")
    # print(en2ch_baidu("salad"))
    # print(en2ch_baidu("the voice stress analyser"))
    # print(haici_zh2en("乌七八糟的东西"))
    print(ch2en_baidu("稳"))
    print(KM_ch2en("稳"))
    # print(time.time() - t1)

    # st = time.time()
    # ch2en_baidu("征求意见")
    # print(time.time() - st)
    # baiduTranslate2("声音")
    # print("::::", time.time() - t1)
    # t = requests.get("https://fanyi.baidu.com/translate?aldtype=16047&query=break+down&keyfrom=baidu&smartresult=dict&lang=auto2zh#en/zh/break%20down")
    # print(t.content)

    Bing_en2ch("fresh water")
    # KM_en2ch("Mrs.")
    # -----------------------------------------------------------
    # bing搜集近义词
    # wordnet = json.loads(open(r"G:\zwj\WL\en2cn\files\词汇整理\res_without_baidu.json", encoding='utf8').read())
    # from Words.Dicts import phrases_dict
    #
    # near_synonym = {}
    # go = False
    # for i in list(phrases_dict.keys()):
    #     # if str(i).strip() == 'windsurfing' and not go:
    #     #     go = True
    #     # if not go:
    #     #     continue
    #
    #     if re.search("[()（）\d,，]", i):
    #         pass
    #     else:
    #         mean_text, synonyms, antonyms = Bing_en2ch(i)
    #         if mean_text:
    #             with open(r"G:\zwj\WL\en2cn\files\Bing_phrases_dict.txt", 'a+', encoding='utf-8') as f1:
    #                 f1.write('"{}": "{}",\n'.format(i.strip(), mean_text.strip()))
    #                 f1.close()
    #         if synonyms or antonyms:
    #             with open(r"G:\zwj\WL\en2cn\files\Bing_phrases_synonyms", 'a+', encoding='utf-8') as f2:
    #                 dd = {"synonyms": synonyms,
    #                       "antonyms": antonyms}
    #                 f2.write('"{}": {},\n'.format(i.strip(), dd))
    #                 f2.close()
    # ------------------yhk搜集短语释义---------
    # from Words.Phrase_dict import phrases_dict_tk
    #
    # new_en2ch = {}
    # for k, v in phrases_dict_tk.items():
    #     k = k.strip()
    #     try:
    #         a = youdaoTranslate(k)
    #         print(a)
    #         if a:
    #             new_en2ch[k] = a
    #         b = haiciTranslate(k)
    #         print(b)
    #         if b:
    #             new_en2ch[k] += ";##;" + b
    #         c = KM_en2ch(k)
    #         print(c)
    #         if c:
    #             new_en2ch[k] += ";##;" + c
    #     except:
    #         re_f = open(r"G:\zwj\WL\en2cn\files\yhk_phrases_dict.json", 'w', encoding='utf-8')
    #         json.dump(new_en2ch, re_f, ensure_ascii=False)
    # ----------------百度词义搜集--------------
    import os
    path1 = r"G:\zwj\WL\en2cn\files\main\en-ch_dict_from_3_website.json"
    path2 = r"G:\zwj\WL\en2cn\files\main\en-ch_dict_bd3.json"
    # ens = json.loads(open(path1, encoding="utf8").read())
    # from Words.Dicts import words_dict, more_words_dict

    # ens_bd = json.loads(open(path2, encoding="utf8").read())
    # print(len(ens_bd))
    # new_ens = [
    #     'Arab-Israeli',
    #     'English-language',
    #     'Feb.',
    #     'Israeli-Palestinian',
    #     'Mar.',
    #     'Mexican-American',
    #     'O. K.',
    #     'Oct.',
    #     'Spanish-language',
    #     'Spanish-speaking',
    #     'US-led',
    #     'Washington-based',
    #     'ad.',
    #     'agro-scientific',
    #     'all-white',
    #     'antispit',
    #     'arm-up',
    #     'asteriod',
    #     'at-bat',
    #     'at-large',
    #     'axe ax',
    #     'backward-curving',
    #     'beddings',
    #     'black-owned',
    #     'booby-hatch',
    #     'bumpkinly',
    #     'characteristi',
    #     'civil-military',
    #     'classificatio',
    #     'clean-burning',
    #     'correspondenc',
    #     'dress-down',
    #     'e-mailed',
    #     'early-morning',
    #     'eight-year',
    #     'eight-year-old',
    #     'eighteenth-century',
    #     'eighth-grade',
    #     'ex-gangster',
    #     'first-place',
    #     'five-day',
    #     'five-minute',
    #     'five-year-old',
    #     'four-day',
    #     'four-hour',
    #     'fourth-grade',
    #     'fourth-quarter',
    #     'free-trade',
    #     'generaliza-tion',
    #     'gloss-over',
    #     'gray-haired',
    #     'greyhound',
    #     'half-mile',
    #     'half-million',
    #     'hear-sensing',
    #     'hour-long',
    #     'identificatio',
    #     'iluminate',
    #     'interteam',
    #     'just-me-ism',
    #     'long-term-care',
    #     'low-wage',
    #     'malnutritious',
    #     'mileometre',
    #     'million-dollar',
    #     'mm-hmm',
    #     'more',
    #     'multimillion-dollar',
    #     'nine-year-old',
    #     'nineteenth-century',
    #     'no-fly',
    #     'non-verbal-leakage',
    #     'notwithstandi',
    #     'null',
    #     'nullify',
    #     'number-one',
    #     'one-party',
    #     'one-year',
    #     'over-emotional',
    #     'oˈclock',
    #     'public-relations',
    #     'reconciliatio',
    #     'saut',
    #     'saute',
    #     'scaper',
    #     'sea-shell',
    #     'second-floor',
    #     'second-largest',
    #     'second-round',
    #     'second-year',
    #     'self-critical',
    #     'seven-year',
    #     'seventeenth-century',
    #     'sideroad',
    #     'six-month',
    #     'six-week',
    #     'six-year-old',
    #     'sixteenth-century',
    #     'sixth-grade',
    #     'sling-shots',
    #     'small-business',
    #     'snowrafting',
    #     'sonwflake',
    #     'straightforwa',
    #     'stress-reducing',
    #     'sun-cream',
    #     'superintenden',
    #     'swim-suit',
    #     'teacher-librarian',
    #     'telecommunica',
    #     'ten-year',
    #     'the voice stress analyser',
    #     'third-largest',
    #     'three-day',
    #     'three-time',
    #     'three-week',
    #     'three-year',
    #     'two-year-old',
    #     'video-game',
    # ]
    # en2ch_bd = ens_bd.copy()
    # for k, v in ens.items():
    # for k in new_ens:
    #     # print(k)
    #     # if "(" in k or "（" in k:
    #     #     continue
    #     # if k not in ens_bd:
    #     #     print("'{}', ".format(k))
    #     if k in ens_bd:
    #         print("重复：", k)
    #         continue
    #     print('++++++++++++++++【{}】++++++++++++++++'.format(k))
    #     if "(" in k or "（" in k:
    #         continue
    #     try:
    #         ch = en2ch_baidu(k)
    #         print(2222222222, ch)
    #         if ch:
    #             en2ch_bd[k] = ch
    #     except:
    #         re_f = open(r"G:\zwj\WL\en2cn\files\main\en-ch_dict_bd3.json", 'w', encoding='utf-8')
    #         json.dump(en2ch_bd, re_f, ensure_ascii=False)
    # re_f = open(r"G:\zwj\WL\en2cn\files\main\en-ch_dict_bd3.json", 'w', encoding='utf-8')
    # json.dump(en2ch_bd, re_f, ensure_ascii=False)