piaoquan_crawler/common/translate.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2023/2/8
import time
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities


class Translate:
    @classmethod
    def google_translate(cls, strs, machine):
        # 打印请求配置
        ca = DesiredCapabilities.CHROME
        ca["goog:loggingPrefs"] = {"performance": "ALL"}

        # 不打开浏览器运行
        chrome_options = webdriver.ChromeOptions()
        chrome_options.add_argument("--headless")
        chrome_options.add_argument('--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36')
        chrome_options.add_argument("--no-sandbox")

        # driver初始化
        if machine == 'aliyun' or machine == 'aliyun_hk':
            driver = webdriver.Chrome(desired_capabilities=ca, options=chrome_options)
        elif machine == 'macpro':
            driver = webdriver.Chrome(desired_capabilities=ca, options=chrome_options, service=Service('/Users/lieyunye/Downloads/chromedriver_v86/chromedriver'))
        elif machine == 'macair':
            driver = webdriver.Chrome(desired_capabilities=ca, options=chrome_options, service=Service('/Users/piaoquan/Downloads/chromedriver'))
        else:
            driver = webdriver.Chrome(desired_capabilities=ca, options=chrome_options, service=Service('/Users/wangkun/Downloads/chromedriver/chromedriver_v110/chromedriver'))

        driver.implicitly_wait(10)
        # url = 'https://fanyi.baidu.com/?aldtype=16047#auto/zh'  # 百度翻译
        url = 'https://translate.google.de/?hl=zh-CN'  # 谷歌翻译
        driver.get(url)
        time.sleep(3)
        # driver.save_screenshot('./1.png')
        accept_btns = driver.find_elements(By.XPATH, '//span[text()="全部接受"]')
        accept_btns_eng = driver.find_elements(By.XPATH, '//span[text()="Accept all"]')
        if len(accept_btns) != 0:
            accept_btns[0].click()
            time.sleep(2)
        elif len(accept_btns_eng) != 0:
            accept_btns_eng[0].click()
            time.sleep(2)

        textarea = driver.find_element(By.XPATH, '//textarea[@class="er8xn"]')
        textarea.send_keys(strs)
        time.sleep(5)
        translate_list = driver.find_elements(By.XPATH, '//span[@class="ryNqvb"]')
        translate_word_list = []
        for text in translate_list:
            word = text.get_attribute("innerHTML")
            translate_word_list.append(word)
        translate_word = "".join(translate_word_list)
        time.sleep(1)
        driver.quit()
        return translate_word

    @classmethod
    def baidu_translate(cls, strs, machine):
        # 打印请求配置
        ca = DesiredCapabilities.CHROME
        ca["goog:loggingPrefs"] = {"performance": "ALL"}

        # 不打开浏览器运行
        chrome_options = webdriver.ChromeOptions()
        chrome_options.add_argument("--headless")
        chrome_options.add_argument('--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36')
        chrome_options.add_argument("--no-sandbox")

        # driver初始化
        if machine == 'aliyun' or machine == 'aliyun_hk':
            driver = webdriver.Chrome(desired_capabilities=ca, options=chrome_options)
        elif machine == 'macpro':
            driver = webdriver.Chrome(desired_capabilities=ca, options=chrome_options, service=Service('/Users/lieyunye/Downloads/chromedriver_v86/chromedriver'))
        elif machine == 'macair':
            driver = webdriver.Chrome(desired_capabilities=ca, options=chrome_options, service=Service('/Users/piaoquan/Downloads/chromedriver'))
        else:
            driver = webdriver.Chrome(desired_capabilities=ca, options=chrome_options, service=Service('/Users/wangkun/Downloads/chromedriver/chromedriver_v110/chromedriver'))

        # driver.implicitly_wait(10)
        url = 'https://fanyi.baidu.com/?aldtype=16047#auto/zh'  # 百度翻译
        # url = 'https://translate.google.de/?hl=zh-CN'  # 谷歌翻译
        driver.get(url)
        time.sleep(1)
        # driver.save_screenshot('./1.png')
        close_btns = driver.find_elements(By.XPATH, '//span[@class="app-guide-close"]')
        accept_btns = driver.find_elements(By.XPATH, '//span[text()="全部接受"]')
        accept_btns_eng = driver.find_elements(By.XPATH, '//span[text()="Accept all"]')
        if len(close_btns) != 0:
            close_btns[0].click()
            time.sleep(2)
        elif len(accept_btns) != 0:
            accept_btns[0].click()
            time.sleep(2)
        elif len(accept_btns_eng) != 0:
            accept_btns_eng[0].click()
            time.sleep(2)

        textarea = driver.find_element(By.XPATH, '//textarea[@id="baidu_translate_input"]')
        textarea.send_keys(strs)
        time.sleep(5)
        translate_list = driver.find_elements(By.XPATH, '//p[@class="ordinary-output target-output clearfix"]')
        translate_word_list = []
        for text in translate_list:
            word = text.find_elements(By.TAG_NAME, 'span')
            for word_text in word:
                word = word_text.text
                translate_word_list.append(word)
                # print(word)
        translate_word = "".join(translate_word_list)
        # print(translate_word)
        time.sleep(1)
        driver.quit()
        return translate_word

    @classmethod
    def is_contains_chinese(cls, strs):
        """
        检查语句中是否包含中文字符
        :param strs: 需要查询的句子
        :return: 包含：True，不包含：False
        """
        for _char in strs:
            if '\u4e00' <= _char <= '\u9fa5':
                return True
        return False

    @classmethod
    def is_all_chinese(cls, strs):
        """
        检查语句中是否全是中文字符，有标点符号也会返回 False
        :param strs:需要查询的句子
        :return:包含：True，不包含：False
        """
        for _char in strs:
            if not '\u4e00' <= _char <= '\u9fa5':
                return False
        return True


if __name__ == "__main__":
    # is_contains_chinese = Translate.is_contains_chinese('SENSATIONAL Singer Wins the GROUP GOLDEN BUZZER with a STUNNING Audition!  | Got Talent Global')
    # print(is_contains_chinese)
    # # is_all_chinese = Translate.is_all_chinese('SENSATIONAL Singer Wins the GROUP GOLDEN BUZZER with a STUNNING Audition!')
    # is_all_chinese = Translate.is_all_chinese('啊啊啊')
    # print(is_all_chinese)

    strs1 = 'SENSATIONAL Singer Wins the GROUP GOLDEN BUZZER with a STUNNING Audition!  | Got Talent Global'
    # Translate.google_translate(strs1, 'local')
    Translate.baidu_translate(strs1, 'local')

    pass