From aa963a7e5c66c36fd685e0fd9a297828791e07bb Mon Sep 17 00:00:00 2001
From: guanjihuan <guanjihuan@163.com>
Date: Wed, 8 Dec 2021 06:46:14 +0800
Subject: [PATCH] update

---
 .../download_word_mp3.py                      | 43 +++++++++++++++++++
 .../2021.12.08_academic_words/play_mp3.py     | 18 ++++++++
 2 files changed, 61 insertions(+)
 create mode 100644 language_learning/2021.12.08_academic_words/download_word_mp3.py
 create mode 100644 language_learning/2021.12.08_academic_words/play_mp3.py

diff --git a/language_learning/2021.12.08_academic_words/download_word_mp3.py b/language_learning/2021.12.08_academic_words/download_word_mp3.py
new file mode 100644
index 0000000..714fffc
--- /dev/null
+++ b/language_learning/2021.12.08_academic_words/download_word_mp3.py
@@ -0,0 +1,43 @@
+from bs4 import BeautifulSoup
+import re
+import requests
+import urllib.request
+import os
+import ssl
+ssl._create_default_https_context = ssl._create_unverified_context
+html = urllib.request.urlopen("https://www.guanjihuan.com/archives/4418").read().decode('utf-8')
+soup = BeautifulSoup(html, features='lxml')
+all_a_tag = soup.find_all('a', href=True)
+for a_tag in all_a_tag:
+    href = a_tag['href']
+    if re.search('https://www.ldoceonline.com/dictionary/', href):
+        print(href[39:])
+        exist_1 = os.path.exists('words_mp3_breProns/'+href[39:]+'.mp3')
+        exist_2 = os.path.exists('words_mp3_breProns/'+href[39:]+'.mp3')
+        if exist_1 and exist_2:
+            continue
+        header = {'User-Agent':'Mozilla/5.0 (X11; Fedora; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'}   # 头部信息
+        request = urllib.request.Request(href,headers=header)
+        reponse = urllib.request.urlopen(request).read()
+        soup2 = BeautifulSoup(reponse, features='lxml') 
+        span = soup2.find_all('span', {"class":"speaker brefile fas fa-volume-up hideOnAmp"})
+        for span0 in span:
+            href2 = span0['data-src-mp3']
+            if re.search('https://www.ldoceonline.com/media/english/breProns/', href2):
+                print(href2)
+                r = requests.get(href2, headers=header, stream=True)
+                with open('words_mp3_breProns/'+href[39:]+'.mp3', 'wb') as f:
+                    for chunk in r.iter_content(chunk_size=32):
+                        f.write(chunk)
+            break
+        span = soup2.find_all('span', {"class":"speaker amefile fas fa-volume-up hideOnAmp"})
+        for span0 in span:
+            href2 = span0['data-src-mp3']
+            if re.search('https://www.ldoceonline.com/media/english/ameProns/', href2):
+                print(href2)
+                r = requests.get(href2, headers=header, stream=True)
+                with open('words_mp3_ameProns/'+href[39:]+'.mp3', 'wb') as f:
+                    for chunk in r.iter_content(chunk_size=32):
+                        f.write(chunk)
+            break
+        print()
\ No newline at end of file
diff --git a/language_learning/2021.12.08_academic_words/play_mp3.py b/language_learning/2021.12.08_academic_words/play_mp3.py
new file mode 100644
index 0000000..5e70ef5
--- /dev/null
+++ b/language_learning/2021.12.08_academic_words/play_mp3.py
@@ -0,0 +1,18 @@
+import pygame
+import time
+import os
+import random
+
+# directory = 'C:/Users/user/Desktop/words_mp3_breProns/' # 英音
+directory = 'C:/Users/user/Desktop/words_mp3_ameProns/' # 美音
+pygame.mixer.init()
+for root, dirs, files in os.walk(directory):
+    num_array = list(range(len(files)))
+    random.shuffle(num_array)  # 随机播放
+    for i0 in num_array:
+        print(files[i0][:-4])
+        print('https://www.ldoceonline.com/dictionary/'+files[i0][:-4], '\n')
+        track = pygame.mixer.music.load(directory+files[i0])
+        pygame.mixer.music.play()
+        time.sleep(3)  # 调节间隔时间
+        pygame.mixer.music.stop()
\ No newline at end of file