项目地址: https://github.com/ssut/py-googletrans
安装:
sudo pip install googletrans
使用:
#!/usr/bin/python # coding: UTF-8 import sys reload(sys) sys.setdefaultencoding('UTF-8') from googletrans import Translator translator = Translator() print translator.translate('co-founder', dest='zh-CN',src='en')
结果:
/usr/bin/python2.7 /home/dahu/PycharmProjects/SpiderLearning/pytorch_lianxi/gugeapi.py Translated(src=en, dest=zh-cn, text=联合创始人, pronunciation=None) Process finished with exit code 0
本来想直接构造查询单词的url地址,但是在爬取的时候获取不到那个值,里面有个tk值不知道.
看了下源码又修改了一下:
#!/usr/bin/python # coding: UTF-8 import sys reload(sys) sys.setdefaultencoding('UTF-8') from googletrans import Translator translator = Translator() with open('tmp1','r') as f: for line in f: # print translator.translate('co-founder', dest='zh-CN',src='en') a=translator.translate(line, dest='zh-CN',src='en') print line.strip(),getattr(a,"text")
Segmentation 分割
Motivation 动机
evaluate 评估
Perplexity 困惑
Process finished with exit code 0
直接提取所翻译的字