0.1.19

PyPI/src/guan/data_processing.py

@@ -140,26 +140,6 @@ def split_text(text, wrap_width=3000):
     guan.statistics_of_guan_package()
     return split_text_list
 
-# 从网页的标签中获取内容
-def get_html_from_tags(link, tags=['title', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'li', 'a']):
-    from bs4 import BeautifulSoup
-    import urllib.request
-    import ssl
-    ssl._create_default_https_context = ssl._create_unverified_context
-    html = urllib.request.urlopen(link).read().decode('utf-8')
-    soup = BeautifulSoup(html, features="lxml")
-    all_tags = soup.find_all(tags)
-    content = ''
-    for tag in all_tags:
-        text = tag.get_text().replace('\n', '')
-        if content == '':
-            content = text
-        else:
-            content = content + '\n\n' + text
-    import guan
-    guan.statistics_of_guan_package()
-    return content
-
 # 将RGB转成HEX
 def rgb_to_hex(rgb, pound=1):
     import guan
@@ -195,14 +175,6 @@ def encryption_SHA_256(password, salt=''):
     guan.statistics_of_guan_package()
     return hashed_password
 
-# 生成二维码
-def creat_qrcode(data="https://www.guanjihuan.com", filename='a', file_format='.png'):
-    import qrcode
-    img = qrcode.make(data)
-    img.save(filename+file_format)
-    import guan
-    guan.statistics_of_guan_package()
-
 # 获取CPU使用率
 def get_cpu_usage(interval=1):
     import psutil
@@ -352,183 +324,6 @@ def history_data_of_one_stock(symbol='000002', period='daily', start_date="19000
     guan.statistics_of_guan_package()
     return title, stock_data
 
-# 播放学术单词
-def play_academic_words(reverse=0, random_on=0, bre_or_ame='ame', show_translation=1, show_link=1, translation_time=2, rest_time=1):
-    from bs4 import BeautifulSoup
-    import re
-    import urllib.request
-    import requests
-    import os
-    import pygame
-    import time
-    import ssl
-    import random
-    ssl._create_default_https_context = ssl._create_unverified_context
-    html = urllib.request.urlopen("https://www.guanjihuan.com/archives/4418").read().decode('utf-8')
-    if bre_or_ame == 'ame':
-        directory = 'words_mp3_ameProns/'
-    elif bre_or_ame == 'bre':
-        directory = 'words_mp3_breProns/'
-    exist_directory = os.path.exists(directory)
-    html_file = urllib.request.urlopen("https://file.guanjihuan.com/words/"+directory).read().decode('utf-8')
-    if exist_directory == 0:
-        os.makedirs(directory)
-    soup = BeautifulSoup(html, features='lxml')
-    contents = re.findall('<h2.*?</a></p>', html, re.S)
-    if random_on==1:
-        random.shuffle(contents)
-    if reverse==1:
-        contents.reverse()
-    for content in contents:
-        soup2 = BeautifulSoup(content, features='lxml')
-        all_h2 = soup2.find_all('h2')
-        for h2 in all_h2:
-            if re.search('\d*. ', h2.get_text()):
-                word = re.findall('[a-zA-Z].*', h2.get_text(), re.S)[0]
-                exist = os.path.exists(directory+word+'.mp3')
-                if not exist:
-                    try:
-                        if re.search(word, html_file):
-                            r = requests.get("https://file.guanjihuan.com/words/"+directory+word+".mp3", stream=True)
-                            with open(directory+word+'.mp3', 'wb') as f:
-                                for chunk in r.iter_content(chunk_size=32):
-                                    f.write(chunk)
-                    except:
-                        pass
-                print(h2.get_text())
-                try:
-                    pygame.mixer.init()
-                    track = pygame.mixer.music.load(directory+word+'.mp3')
-                    pygame.mixer.music.play()
-                    if show_link==1:
-                        print('https://www.ldoceonline.com/dictionary/'+word)
-                except:
-                    pass
-                translation = re.findall('<p>.*?</p>', content, re.S)[0][3:-4]
-                if show_translation==1:
-                    time.sleep(translation_time)
-                    print(translation)
-                time.sleep(rest_time)
-                pygame.mixer.music.stop()
-                print()
-    import guan
-    guan.statistics_of_guan_package()
-
-# 播放挑选过后的学术单词
-def play_selected_academic_words(reverse=0, random_on=0, bre_or_ame='ame', show_link=1, rest_time=3):
-    from bs4 import BeautifulSoup
-    import re
-    import urllib.request
-    import requests
-    import os
-    import pygame
-    import time
-    import ssl
-    import random
-    ssl._create_default_https_context = ssl._create_unverified_context
-    html = urllib.request.urlopen("https://www.guanjihuan.com/archives/24732").read().decode('utf-8')
-    if bre_or_ame == 'ame':
-        directory = 'words_mp3_ameProns/'
-    elif bre_or_ame == 'bre':
-        directory = 'words_mp3_breProns/'
-    exist_directory = os.path.exists(directory)
-    html_file = urllib.request.urlopen("https://file.guanjihuan.com/words/"+directory).read().decode('utf-8')
-    if exist_directory == 0:
-        os.makedirs(directory)
-    soup = BeautifulSoup(html, features='lxml')
-    contents = re.findall('<li>\d.*?</li>', html, re.S)
-    if random_on==1:
-        random.shuffle(contents)
-    if reverse==1:
-        contents.reverse()
-    for content in contents:
-        soup2 = BeautifulSoup(content, features='lxml')
-        all_li = soup2.find_all('li')
-        for li in all_li:
-            if re.search('\d*. ', li.get_text()):
-                word = re.findall('\s[a-zA-Z].*?\s', li.get_text(), re.S)[0][1:-1]
-                exist = os.path.exists(directory+word+'.mp3')
-                if not exist:
-                    try:
-                        if re.search(word, html_file):
-                            r = requests.get("https://file.guanjihuan.com/words/"+directory+word+".mp3", stream=True)
-                            with open(directory+word+'.mp3', 'wb') as f:
-                                for chunk in r.iter_content(chunk_size=32):
-                                    f.write(chunk)
-                    except:
-                        pass
-                print(li.get_text())
-                try:
-                    pygame.mixer.init()
-                    track = pygame.mixer.music.load(directory+word+'.mp3')
-                    pygame.mixer.music.play()
-                    if show_link==1:
-                        print('https://www.ldoceonline.com/dictionary/'+word)
-                except:
-                    pass
-                time.sleep(rest_time)
-                pygame.mixer.music.stop()
-                print()
-    import guan
-    guan.statistics_of_guan_package()
-
-# 播放元素周期表上的单词
-def play_element_words(random_on=0, show_translation=1, show_link=1, translation_time=2, rest_time=1):
-    from bs4 import BeautifulSoup
-    import re
-    import urllib.request
-    import requests
-    import os
-    import pygame
-    import time
-    import ssl
-    import random
-    ssl._create_default_https_context = ssl._create_unverified_context
-    html = urllib.request.urlopen("https://www.guanjihuan.com/archives/10897").read().decode('utf-8')
-    directory = 'prons/'
-    exist_directory = os.path.exists(directory)
-    html_file = urllib.request.urlopen("https://file.guanjihuan.com/words/periodic_table_of_elements/"+directory).read().decode('utf-8')
-    if exist_directory == 0:
-        os.makedirs(directory)
-    soup = BeautifulSoup(html, features='lxml')
-    contents = re.findall('<h2.*?</a></p>', html, re.S)
-    if random_on==1:
-        random.shuffle(contents)
-    for content in contents:
-        soup2 = BeautifulSoup(content, features='lxml')
-        all_h2 = soup2.find_all('h2')
-        for h2 in all_h2:
-            if re.search('\d*. ', h2.get_text()):
-                word = re.findall('[a-zA-Z].* \(', h2.get_text(), re.S)[0][:-2]
-                exist = os.path.exists(directory+word+'.mp3')
-                if not exist:
-                    try:
-                        if re.search(word, html_file):
-                            r = requests.get("https://file.guanjihuan.com/words/periodic_table_of_elements/prons/"+word+".mp3", stream=True)
-                            with open(directory+word+'.mp3', 'wb') as f:
-                                for chunk in r.iter_content(chunk_size=32):
-                                    f.write(chunk)
-                    except:
-                        pass
-                print(h2.get_text())
-                try:
-                    pygame.mixer.init()
-                    track = pygame.mixer.music.load(directory+word+'.mp3')
-                    pygame.mixer.music.play()
-                    if show_link==1:
-                        print('https://www.merriam-webster.com/dictionary/'+word)
-                except:
-                    pass
-                translation = re.findall('<p>.*?</p>', content, re.S)[0][3:-4]
-                if show_translation==1:
-                    time.sleep(translation_time)
-                    print(translation)
-                time.sleep(rest_time)
-                pygame.mixer.music.stop()
-                print()
-    import guan
-    guan.statistics_of_guan_package()
-
 # 获取Guan软件包当前模块的所有函数名
 def get_all_function_names_in_current_module():
     import inspect