1/11

百度翻译/test.py

-#百度翻译 不登录翻译1000字 登录翻译5000字
+#百度翻译 不登录翻译1000字 登录翻译5000字
@@ -2,7 +2,7 @@
 import re
 import string
 import time
-
+from urllib.parse import quote
 import pymongo
 from bs4 import BeautifulSoup
 from selenium import webdriver
@@ -23,6 +23,7 @@ class Translate():
         # self._lang_list_original = ["中文", "英语", "韩语", "法语", "日语", "希腊语", "俄语"]
         # self._num = len(self._lang_list)
         self.url = "https://fanyi.baidu.com/#{}/{}/{}"
+        # self.url = "https://fanyi.baidu.com/#"
         self.header = {
             "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1"}
 
@@ -64,7 +65,8 @@ class Translate():
                 pass
             else:
                 word_type = lang
-            url = self.url.format(word_type, 'zh', sentence_)
+            url_ = self.url.format(word_type, 'zh', sentence_)
+            url = quote(url_, safe='/:#')
             browser.set_page_load_timeout(10)
             try:
                 browser.get(url)
@@ -193,8 +195,8 @@ class Translate():
             if lang == 'zh':
                 return contentWithTag
             for tag in html.find_all(text=True):
-                sentence = str(tag)
-                # sentence = "　実際に働き手の数が8がけ（8割）になる16年後、介護のようなケアサービスを今のような形で受けることは困難になると予測される。"
+                # sentence = str(tag)
+                sentence = "95% say hello"
                 if sentence == '\n' or sentence == '\t' or sentence == ' ':
                     continue
                 if self.is_punctuation(sentence):