Python3 爬谷歌翻译

weixin_44176564

已于 2024-07-05 14:34:43 修改

阅读量208

点赞数 3

文章标签： python

于 2024-07-05 09:49:17 首次发布

本文链接：https://blog.csdn.net/weixin_44176564/article/details/140199704

版权



import requests
import re
import json

def translated_content(text, target_language):
    headers = {
        "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
        # "accept-language": "en,zh-CN;q=0.9,zh;q=0.8",
        #"Accept - Language": "zh - CN, zh;q = 0.8, zh - TW;q = 0.7, zh - HK;q = 0.5, en - US;q = 0.3, en;q = 0.2",
        #"Accept - Encoding": "gzip, deflate, br, zstd",
        "content-type": "application/x-www-form-urlencoded;charset=UTF-8",
        #"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; rv:127.0) Gecko/20100101 Firefox/127.0",
        "Cookie": "AEC=AQTF6HxzoGksZJVcld21mTmjj7tDOWCC9LKpsU8BMiF1lC3IJLtmfL3GxA; NID=515=F_eUDYoDD6BtTmmljZCCgtmWZmNIXHMPgYmETsVW75AJYTUf7VgRNTiQlRWHklK_XN96cVK94ssEHIO3lmalN4_ibMQSxvpfe4dPXQU04KAPfwOuHBq2ZjNB9hK45k_NTujMczJ4VgMAonOBsfiw3gPW555l4gjF_BY50mozreXogXHgwtuogq2hZuK0ADg9JGuxgd7nmsWO3qq5j9usLjtrzshkNA_hCEytQ8SK12uQ7dWZ6VQLF5_BdxECnwAf0QSfmYJvHxSqq1UhTuSXd9zKihlMWT2NGgVnq_k7nlv93r7RGVf9-Mw7_q0; OTZ=7591850_24_24__24_; ANID=AHWqTUlgs0Vzw53UV4z0TPMogEgkJw7hpi_bw53U1ydPCjucOn2juLJuSICmn_TW",
    }
    # 请求url
    url = "https://translate.google.com/_/TranslateWebserverUi/data/batchexecute?rpcids=MkEWBc&source-path=%2F&f.sid=1672201524388925858&bl=boq_translate-webserver_20240619.08_p0&hl=zh-CN&soc-app=1&soc-platform=1&soc-device=1&_reqid=2060929&rt=c HTTP/2"
    # 数据参数
    from_data = {
        "f.req": r"""[[["MkEWBc","[[\"{}\",\"auto\",\"{}\",true],[null]]",null,"generic"]]]""".format(text, target_language)
    }
    try:
        r = requests.post(url, headers=headers, data=from_data, timeout=60)
        if r.status_code == 200:
            # 正则匹配结果
            #response = re.findall(r',\[\[\\"(.*?)\\",\[\\', r.text)
            #response = re.findall(r',\[\[\\"(.*?)\\",', r.text)
            response = re.findall(r',"\[(.*?)]",', r.text)

            if response:
                parsed_data = "["
                parsed_data += response[0]
                parsed_data += "]"
                parsed_data = parsed_data.replace('\\', '')
                # 解析 JSON 字符串
                test = json.loads(parsed_data)
                test = test[1][0][0][5]
                
                result = ""
                for element in test:
                    if len(element) > 0:
                        result += element[0]

                #print(result)
                return result
            else:
                response = re.findall(r',\[\[\\"(.*?)\\"]', r.text)
                if response:
                    response = response[0]
            return response
    except Exception as e:
        print(e)
        return False



if __name__ == "__main__" :
    '''
    '''
    # 翻译各个国家语言
    for i in ['en', 'zh', 'fr', 'ja', 'de', 'ko', 'pl', 'tr', 'th', 'it', 'ru', 'pt', 'es']:
        response = translated_content("The APP is being upgraded, It will restart after the upgrade, Please do not turn off the power.", i)
        print(response)

    print("trans end")