爬虫破解腾讯网页翻译翻译文档内容

最新推荐文章于 2025-06-28 21:21:36 发布

原创最新推荐文章于 2025-06-28 21:21:36 发布 · 1.5k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#文档文本翻译

python爬虫同时被 2 个专栏收录

4 篇文章

订阅专栏

数据处理

3 篇文章

订阅专栏

本文深入解析了腾讯翻译API的使用方法，包括获取必要参数、构建请求头、发送翻译请求及处理响应结果。通过实例展示了如何利用该API进行文本翻译，并介绍了如何将翻译结果保存到文件。适用于希望快速上手腾讯翻译服务的开发者。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import re
import time
import requests
from dataclasses import dataclass
import linecache
import os


def get_filter(text):
    if isinstance(text, list):
        text = ''.join(text)
    text = str(text)
    text = text.strip()
    filter_list = [
        '\r', '\n', '\t', '\u3000', '\xa0', '\u2002',
        '<br>', '<br/>', '    ', '	', '&nbsp;', '>>', '&quot;',
        '展开全部', ' '
    ]
    for fl in filter_list:
        text = text.replace(fl, '')
    return text


def get_qtv_qtk():
    api_url = 'https://fanyi.qq.com/'

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, '
                      'like Gecko) Chrome/73.0.3683.86 Safari/537.36', }

    res = requests.get(api_url, headers=headers)
    data = res.text

    fy_guid = res.cookies.get('fy_guid')

    reg = re.compile(r'var qtv = "(.*?)"')
    qtv = reg.search(data).group(1)

    reg = re.compile(r'var qtk = "(.*?)"')
    qtk = reg.search(data).group(1)

    return fy_guid, qtv, qtk


@dataclass
class SougoTrans(object):
    fromlang: str
    tolang: str
    text: str

    def __post_init__(self):
        self.api_url = 'https://fanyi.qq.com/api/translate'
        self.headers = {
            'Cookie': 'fy_guid=605ead81-f210-47eb-bd80-ac6ae5e7a2d8; '
                      'qtv=ed286a053ae88763; '
                      'qtk=wfMmjh3k/7Sr2xVNg/LtITgPRlnvGWBzP9a4FN0dn9PE7L5jDYiYJnW03MJLRUGHEFNCRhTfrp/V+wUj0dun1KkKNUUmS86A/wGVf6ydzhwboelTOs0hfHuF0ndtSoX+N3486tUMlm62VU4i856mqw==; ',
            'Host': 'fanyi.qq.com',
            'Origin': 'https://fanyi.qq.com',
            'Referer': 'https://fanyi.qq.com/',
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, '
                          'like Gecko) Chrome/73.0.3683.86 Safari/537.36', }
        if not self.fromlang:
            self.fromlang = 'auto'
        if not self.tolang:
            self.tolang = 'en'  # 设置默认为英语
        self.sessionUuid = str(int(time.time() * 1000))

        self.fy_guid, self.qtv, self.qtk = get_qtv_qtk()

        self.headers['Cookie'] = self.headers['Cookie'].replace(
            '605ead81-f210-47eb-bd80-ac6ae5e7a2d8', self.fy_guid)

        self.headers['Cookie'] = self.headers['Cookie'].replace(
            'ed286a053ae88763', self.qtv)
        self.headers['Cookie'] = self.headers['Cookie'].replace(
            'wfMmjh3k/7Sr2xVNg/LtITgPRlnvGWBzP9a4FN0dn9PE7L5jDYiYJnW03MJLRUGHEFNCRhTfrp/V+wUj0dun1KkKNUUmS86A/wGVf6ydzhwboelTOs0hfHuF0ndtSoX+N3486tUMlm62VU4i856mqw==',
            self.qtk)

    def get_trans_result(self):
        data = {
            'source': self.fromlang,
            'target': self.tolang,
            'sourceText': self.text,
            'qtv': self.qtv,
            'qtk': self.qtk,
            'sessionUuid': self.sessionUuid, }

        trans_result = requests.post(
            self.api_url, data=data, headers=self.headers)

        try:
            datas = trans_result.json()['translate']['records']
            trans_result = ''.join([data['targetText'] for data in datas])
        except:
            print(trans_result.text)
            trans_result = ''

        return trans_result


def save_to_file(file_name, contents):
    fh = open(file_name, 'w', encoding='utf-8')
    fh.write(contents)
    fh.close()


def run(filepath_name: object) -> object:
    fromlang = ''
    tolang = 'en'
    text = ''
    i = 0
    for filename in os.listdir(filepath_name):
        i += 1
        fileout_name = './英文数据/' + str(i) + '.txt'
        start = time.clock()
        filename = filepath_name + '/' + filename
        reqs = linecache.getlines(filename)
        for a in reqs:
            text = text + a
        Sougou = SougoTrans(fromlang, tolang, text)
        res = Sougou.get_trans_result()
        save_to_file(fileout_name, res)
        end = time.clock()
        print('Running time: %s Seconds' % (end - start))
        time.sleep(1)


if __name__ == '__main__':
    # run("./原始数据")
    Flag = True
    a = 9115
    while (Flag):
        if(a <= 14927):
            start = time.clock()
            a = a + 1
            fromlang = ''
            tolang = 'en'
            text = ''
            reqs = linecache.getlines('./原始数据/'+str(a)+'.csv')
            for i in reqs:
                text = text + i
            # text = get_filter(text)
            Sougou = SougoTrans(fromlang, tolang, text)
            res = Sougou.get_trans_result()
            fileout_name = './英文数据/' + str(a) + '.txt'
            save_to_file(fileout_name, res)
            end = time.clock()
            print('Running time: %s Seconds' % (end - start))
            time.sleep(1)
        else:
            Flag = False