def table():#在这里写下您的乘法口诀表代码吧！for i in range(1,10):result = ''for j in range(1,i+1):result += "{}*{}={:<2d}  ".format(j, i, j*i)print(result)

import os
#待搜索的目录路径
path = "Day1-homework"
#待搜索的名称
filename = "2020"
#定义保存结果的数组
result = []
def findfiles():#在这里写下您的查找文件代码吧！global pathindex = 1for root, subs, files in os.walk(path):for f in files:if filename in f:result.append([index, os.path.join(root, f)])index += 1for group in result:print(group)

import requests
from bs4 import BeautifulSoup
#重点就是知道这个库的基本使用
#关键用法就这三行
response = requests.get(url,headers=headers)
soup = BeautifulSoup(response.text,'lxml')
tables = soup.find_all('table',{'class':'table-view log-set-param'})

headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'}url='https://baike.baidu.com/item/青春有你第二季'                         try:response = requests.get(url,headers=headers)#将一段文档传入BeautifulSoup的构造方法,就能得到一个文档的对象, 可以传入一段字符串soup = BeautifulSoup(response.text,'lxml')#返回的是class为table-view log-set-param的<table>所有标签tables = soup.find_all('table',{'class':'table-view log-set-param'})crawl_table_title = "参赛学员"for table in  tables:           #对当前节点前面的标签和字符串进行查找table_titles = table.find_previous('div').find_all('h3')for title in table_titles:if(crawl_table_title in title):return table       except Exception as e:print(e)

# 下载中文字体
!wget https://mydueros.cdn.bcebos.com/font/simhei.ttf
# 将字体文件复制到matplotlib字体路径
!cp simhei.ttf /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/mpl-data/fonts/ttf/
# 一般只需要将字体文件复制到系统字体目录下即可，但是在aistudio上该路径没有写权限，所以此方法不能用
# !cp simhei.ttf /usr/share/fonts/
# 创建系统字体文件路径
!mkdir .fonts
# 复制文件到该路径
!cp simhei.ttf .fonts/
!rm -rf .cache/matplotlib
还有下面这一句。
# 设置显示中文
plt.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体

df = pd.read_json('data/data31557/20200422.json')
weight = df['weight']
def split_(x):value = x.split('kg')[0]return float(value)
df['weight_value'] = weight.apply(lambda x:split_( x) )
df['weight_value'] = pd.cut(df['weight_value'], [0,45,50,55,200])
counts = pd.value_counts(df['weight_value'])
values = counts.values
labels = ['<=45kg', '45~50kg','50~55kg','>55kg']
explode = (0,0.1,0,0)
# 画图
# 设置显示中文
plt.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体
plt.figure(figsize=(8,8))
patches,l_text,p_text = plt.pie(x=values, labels=labels, explode=explode, autopct='%1.1f%%',shadow=True, startangle=90, )
for t in l_text:t.set_size(25)
for t in p_text:t.set_size(25)
plt.axis('equal')
plt.title('''《青春有你2》选手体重分布''',fontsize = 24,y=-0.1)
plt.show()

import random
name = {'anqi':3, 'yushuxin':0, 'xujiaqi':1, 'wangchengxuan':4, 'zhaoxiaotang':2}
import os
train_img_path = list()
val_img_path = list()
for d in os.listdir('dataset'):if d in name.keys():img_path = list()index = name[d]for file in os.listdir(os.path.join('dataset',d)):if file != '.ipynb_checkpoints':string = d + '/'+ file+ ' ' + str(index) +'n'img_path.append(string)length = len(img_path)val_img_list = random.sample(img_path, int(len(img_path)*0.2)) for i in img_path:if i in val_img_list:val_img_path.append(i)else :train_img_path.append(i)
random.shuffle(train_img_path)
random.shuffle(val_img_path)
#print(train_img_path)
with open('dataset/train_list.txt', 'w') as f:for l in train_img_path:f.write(l)with open('dataset/validate_list.txt', 'w') as f:for l in val_img_path:f.write(l)

def get_content(lastId):base_url = 'https://sns-comment.iqiyi.com/v3/comment/get_comments.action?agent_type=118&agent_version=9.11.5&authcookie=null&business_type=17&content_id=15068699100&hot_size=0&last_id='last_url = '&page=&page_size=20&types=time&callback=jsonp'url = base_url + str(lastId) + last_urlhtml=urllib.request.urlopen(url).read().decode("utf-8","ignore")    return html#从源码中获取评论的数据
def get_comment(html):    pat='"content":"(.*?)"'    rst = re.compile(pat,re.S).findall(html)    return rst#获取下个id
def get_id(html):pat = '"id":"(.*?)"'rst = re.compile(pat,re.S).findall(html)return rst
if __name__ == "__main__":total = 0first_id = 240947941221html=get_content(first_id)with open('comment.txt','w') as f:while True:commentlist=get_comment(html)        for j in range(1,len(commentlist)):            f.write(str(commentlist[j]) + 'n') total +=1#获取下一轮刷新页ID if total > 1100:break         lastId=get_id(html)[-1]       html=get_content(lastId)print("【完成】 总共爬取了{}条评论".format(total))

#去除文本中特殊字符
def clear_special_char(content):'''正则处理特殊字符参数 content:原文本return: 清除后的文本'''s = re.sub(r"</?(.+?)>|&nbsp;|t/r*",'', content)s = re.sub(r"n",'', s)s = re.sub(r"*", "*", s)s = re.sub('[^u4E00-u9FA5A-Za-z0-9 ]','',s)a = re.sub('[001002003004005006007x08x09x0ax0bx0cx0dx0ex0fx10x11x12x13x14x15x16x17x18x19x1a]+', '', s)s = re.sub('{a—zA-Z}','',s)s = re.sub('^d+(.d+)?$','',s)return s

def fenci(text):'''利用jieba进行分词参数 text:需要分词的句子或文本return：分词结果'''jieba.load_userdict("add_words.txt")seg = jieba.lcut(text,cut_all=False)return segdef stopwordslist(filepath):'''创建停用词表参数 file_path:停用词文本路径return：停用词list'''stopwords = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]return stopwords

def drawcounts(counts,num):'''绘制词频统计表参数 counts: 词频统计结果 num:绘制topNreturn：none'''x_aixs = []y_aixs = []c_order = sorted(counts.items(), key=lambda x:x[1],reverse=True)#print(c_order)#通过高频词的数量进行排序for c in c_order[:num]:x_aixs.append(c[0])y_aixs.append(c[1])matplotlib.rcParams['font.family'] = ['SimHei'] # 指定默认字体matplotlib.rcParams['axes.unicode_minus'] = False plt.figure(figsize=(12,8))plt.bar(x_aixs, y_aixs)plt.title ( '词频统计')plt.show( )

def drawcloud(word_f):'''根据词频绘制词云图参数 word_f:统计出的词频结果return：none'''cloud_mask = np.array(Image.open('cloud.png'))st = set(['东西','这是'])wc = WordCloud(font_path='fonts/simhei.ttf',  # 设置字体mask=cloud_mask,background_color="white",  # 背景颜色max_words=200,  # 词云显示的最大词数max_font_size=80,  # 字体最大值min_font_size=10, #字体最小值random_state=42, #随机数collocations=False, #避免重复单词stopwords=st,relative_scaling=0.3,width=400,margin=10, #图像宽高，字间距，需要配合下面的plt.figure(dpi=xx)放缩才有效)wc.fit_words(word_f)wc.to_file('pic.png')

def text_detection(text,file_path):'''使用hub对评论进行内容分析return：分析结果'''porn_detection_lstm = hub.Module(name="porn_detection_lstm")test_text = list()with open('chean_comment.txt','r') as f:for line in f:if len(line) == 1:continueelse:test_text.append(line)input_dict = {"text": test_text}results = porn_detection_lstm.detection(data=input_dict,use_gpu=True, batch_size=1)for index, result in enumerate(results):if result['porn_detection_key'] == 'porn':print(result['text'], ":", result['porn_probs'])