Python基于有道翻译实现翻译功能_课程设计

基于PyQT5、OCR、文字转语言等实现翻译功能(自动识别语言)，实现词频统计，生成词云等，读取txt文件内容

---

前言

提示：基于PyQT5、OCR、文字转语言等实现翻译功能(自动识别语言)

参考链接：https://blog.csdn.net/m0_46778548/article/details/121042773?ops_request_misc=&request_id=&biz_id=102&utm_term=%E6%9C%89%E9%81%93%E7%BF%BB%E8%AF%91&utm_medium=distribute.pc_search_result.none-task-blog-2~all~sobaiduweb~default-3-121042773.nonecase&spm=1018.2226.3001.4187https://blog.csdn.net/melo_1/article/details/105036899https://blog.csdn.net/melo_1/article/details/105036899https://blog.csdn.net/melo_1/article/details/105036899

用Python破解有道翻译反爬虫机制_南窗客斯黄的博客-CSDN博客_爬虫有道翻译https://blog.csdn.net/m0_46778548/article/details/121042773?ops_request_misc=&request_id=&biz_id=102&utm_term=%E6%9C%89%E9%81%93%E7%BF%BB%E8%AF%91&utm_medium=distribute.pc_search_result.none-task-blog-2~all~sobaiduweb~default-3-121042773.nonecase&spm=1018.2226.3001.4187

---

一、程序演示

 

二、核心代码

1.翻译

代码如下：

    def translatefun(self):
        import urllib.request
        import urllib.parse
        import json
        a = "123"

        def translate_action(content):
            # print(content)
            url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule'
            # 需要打开网页的链接，这个在Request URL栏
            head = {}
            head[
                'User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
            # 模拟浏览器访问，简单的防止反爬机制。这个在Request Headers中的User-Agent栏。
            data = {}
            data['i'] = content
            data['from'] = 'AUTO'
            data['to'] = 'AUTO'
            data['smartresult'] = 'dict'
            data['client'] = 'fanyideskweb'
            data['salt'] = '15847864360501'
            data['sign'] = 'f762faa6901c6cf473fce719f8238ca8'
            data['ts'] = '1584786436050'
            data['bv'] = '0ed2e07b89acaa1301d499442c9fdf79'
            data['doctype'] = 'json'
            data['version'] = '2.1'
            data['keyfrom'] = 'fanyi.web'
            data['action'] = 'FY_BY_REALTlME'
            # 将Form Data数据存入data字典中。
            data = urllib.parse.urlencode(data).encode('utf-8')
            # 将data以utf-8的形式编码
            req = urllib.request.Request(url, data, head)
            # 以代码中的data与head形式访问代码中的url链接
            response = urllib.request.urlopen(req)
            # 打开url网页并传送data与head
            html = response.read().decode('utf-8')

            # 读取打开的网页并进行utf-8解码
            target = json.loads(html)
            # 识别json

            print(target['translateResult'])
            result = ''
            for i in target['translateResult']:
                for j in range(len(i)):
                    print(i[j]['tgt'])
                    result += i[j]['tgt']
                result += '\n'
            print(result)
            return result
        try:
            lt=translate_action(self.leftT.toPlainText())
            self.rightT.setText(str(lt))
        except:
            print("translatefun 128 err")

2.词频统计

代码如下：

    def analyseText(self):
        txt = self.rightT.toPlainText()
        words = jieba.lcut(txt)
        # print(words)
        counts = {}
        # while i<len(words):
        for word in words:
            if len(word) == 1:
                continue
            else:
                rword = word
            counts[rword] = counts.get(rword, 0) + 1  # 返回指定键的值，如果值不在字典中返回default值即0
        sed = sorted(counts.items(), key=lambda x: x[1], reverse=True)[:20]
        tk20=[]
        tv20=[]
        for (k, v) in sorted(counts.items(), key=lambda x: x[1], reverse=True)[:10]:
            print("{}\t\t\t\t{}".format(k, v))
            tk20.append(k)
            tv20.append(v)

        plt.rcParams['font.family'] = 'STsong'
        print(tk20,tv20)

        plt.bar(tk20, tv20, color='lightskyblue')
        plt.xlabel('出现词语')
        plt.ylabel('出现次数')
        plt.title('词频统计柱状图')
        plt.show()

3.词云图生成：

 def wordimg(self):
        import matplotlib.pyplot as plt
        from wordcloud import WordCloud
        import jieba
        getText=self.rightT.toPlainText()
        jtext = jieba.cut(getText, cut_all=True)

        jtextsplit = " ".join(jtext)

        font = r'C:\Windows\Fonts\simfang.ttf'  # 设置中文字体，否则词云图可能不显示中文
        my_wordcloud = WordCloud(font_path=font).generate(jtextsplit)
        plt.imshow(my_wordcloud)
        plt.axis("off")  # 消除坐标轴
        plt.show()

4.图片识别文字

 def extractText(self):
        from cnocr.utils import read_img
        from cnocr import CnOcr

        # 图片转文字
        def exT(imgpath):
            ocr = CnOcr()
            img_fp = imgpath
            img = read_img(img_fp)
            res = ocr.ocr(img)

            text = ''
            for i in res:
                # print("".join(i[0]))
                text += "".join(i[0])
                text += "\n"
            return text

        fname = QFileDialog.getOpenFileName()
        text=exT(fname[0])
        self.leftT.setText(text)

如需要整套源码请点击python有道翻译、ocr图片转文字、文字转语音、统计词频、生成词云-Python文档类资源-CSDN下载

---

总结

由于本人能力有限，以后的学习中将继续完善自己的编码能力