python二级大题—1-12

f = open(‘命运.txt’,’r’)
txt = f.read()#读取整个文本
d={}
for i in txt:
	if i not in“，。！？《》【】“””:
		d[i] = d.get(i,0)+1
ls = list(d.items())
ls.sort(key = lambda x:x[1],reverse = True)
print(“{}:{}”.format(ls[0][0],ls[0][1]))
f.close()

f = open(“命运.txt”,’r’)
txt = f.read()
d = {}
for i in txt:
	if i not in”\n”:
		d[i] = d.get(i,0)
ls = list(d.items())
ls.sort(key = lambda x,x[1],reverse = True)
for i in range(10):
	print(ls[i][0],end =“”)
f.close()

f = open(“命运.txt”,’r’)
fi = open(“命运-频次排序.txt”,’w’j
txt = f.read()
d={}
for i in txt:
	if i not in “\n”:
		d[i] = d.get(i,0) + 1
ls = list(d.items())
ls.sort(key = lambda x:x[1],reverse = True)
s=“”
for i in range(len(ls)):
	s += “{}:{}”.format(ls[i][0],ls[i][1]) + “,”
fi.write(s[:-1]
f.close()
fi.close()

f = open('PY301-SunSign.csv','r')
ls = []
name = input('请输入星座名称(例如，双子座）：')
for i in f.readlines():
	ls = i.strip('\n').split(',')
	if ls[1] == name:
		print('{}的生日位于{}-{}之间'.format(ls[1],ls[2],ls[3]))
f.close()

f = open('PY301-SunSign.csv','r')
ls = []
ls = f.readlines()
while True:
	s = input('请输入星座序号(例如，5）：')
	for i in s.split():
		for line in ls:
			lt = line.strip('\n').split()
			if i = lt[0]:
				print("{}的生日是{}至{}之间".format(lt[1],lt[2],lt[3])
f.close()

f = open('PY301-SunSign.csv','r')
ls = []
ls = f.readlines()
while True:
	s = input('请输入星座序号(例如，5）：')
	for i in s.split():
		for i in lt:
			if 0<int(i)<13: 
				flag = True
			else:
				flag = False
		for line in ls:
			lt = line.strip('\n').split()
			if i = lt[0]:
				if flag = True:
					print("{}的生日是{}至{}之间".format(lt[1],lt[2],lt[3])
				else:
					print('输出有误')
					break
f.close()			

import jieba
f = open('data.txt','r')
f1 = open('out.txt','w')
lines = f.readlines()
for line in lines:
	line = line.strip('')
	lt = jieba.lcut(line)
	f1.writelines(lt)
f1.close()
f.close()

import jieba
f = open('out.txt','r')
lines = f.readlines()
f.close()
D={}
for w in lines:
	D[w[:-1]]=D.get(w[:-1],0) + 1
print("曹操出现了{}次".format(D["曹操"]))

import jieba
f = open('data.txt','r')
f1 = open('out1.txt','w')
lines = f.readlines()
f.close()
D=[]
for line in lines:
	lt = jieba.lcut(line)
	for word in lt:
		if len(word) < 3:
			continue
		else:
			if word not in D:
				D.append(word)
f1.writelines('\n'.join(D))
f1.close()

import jieba
f = open('data.txt','r')
f1 = open('out1.txt','w')
lines = f.readlines()
f.close()
D={}
for line in lines:
	lt = jieba.lcut(line)
	for word in lt:
		if len(word) < 3:
			continue
		else:
			D[word] = D.get(word,0) + 1
lt = list(D.items())
lt.sort(key = lambda x:x[1],reverse = True)
for i in range len(lt):
	f1.write('{}:{}\n'.join(lt[i][0],lt[i][1]))
f1.close()

f = open('score.txt','r')
f1 = open('candidate0.txt','w')
lines = f.readlines()
lt = []
d = []
for line in lines:
	score = 0
	lt = line.strip('\n').split()
	for i in lt[2:]:
		score += int(i)
	lt.append[i]
	d.append[lt]
d.sort(key = lambda x:x[-1],reverse = True)
for i in range(10):
	f1.write(' '.join(d[i][:-1]+'\n')
f.close()
f1.close()

f = open('candidate0.txt','r')
f1 = open('candidate.txt','w')
lines = f.readlines()
c = []
for line in lines:
	lt = line.strip('\n').split()
	for i in lt[2:]:
		if int(i) < 60:
			break
		else:
			f1.write(' '.join(lt[:2])+'\n')
f.close()
f1.close()
		

8

f = open('data.txt','r')
lines = f.readlines()
f.close()
f1 = open('univ.txt','w')
for line in lines:
	if 'alt' in line:
		word = line.split('alt=')[-1].split(")[2]
	f1.write('{}\n'.format(word))
f1.close()

f = open('univ.txt','r')
lines = f.readlines()
f.close()
c1,c2 = 0
for line in lines:
	if "大学生" in line:
		continue
	elif "大学" in line:
		print('{}'.format(line))
		c1 += 1
	elif "学院" in line:
		print('{}'.format(line))
		c2 += 1
print('包含大学的数量是{}'.format(c1))
print('包含学院的数量是{}'.format(c2))

9

import jieba
fa = open('data2019.txt','r')
txt = fa.read()
fa.close()
words = jieba.lcut(txt)
d={}
for i in words:
	if len(i) < 2:
		continue
	else:
		d[i] = d.get(i,0) + 1
lt = list(d.items())
lt.sort(key = lambda x:x[1],reverse = True)
print("2019:",end="")
for i in range(10):
	word = lt[i][0]
	count = lt[i][1]
	if i < 9:
		print("{}:{},".format(word,count),end=",")
	else:
		print("{}:{},".format(word,count))
import jieba
fa = open('data2018.txt','r')
txt = fa.read()
fa.close()
words = jieba.lcut(txt)
d={}
for i in words:
	if len(i) < 2:
		continue
	else:
		d[i] = d.get(i,0) + 1
lt = list(d.items())
lt.sort(key = lambda x:x[1],reverse = True)
print("2018:",end="")
for i in range(10):
	word = lt[i][0]
	count = lt[i][1]
	if i < 9:
		print("{}:{},".format(word,count),end=",")
	else:
		print("{}:{},".format(word,count))
		

import jieba
fa = open('data2019.txt','r')
txt = fa.read()
fa.close()
words = jieba.lcut(txt)
d={}
for i in words:
	if len(i) < 2:
		continue
	else:
		d[i] = d.get(i,0) + 1
lt = list(d.items())
lt.sort(key = lambda x:x[1],reverse = True)
da = {}
for i in range(10):
	da[i] = lt[i][0]
fa = open('data2018.txt','r')
txt = fa.read()
fa.close()
words = jieba.lcut(txt)
d={}
for i in words:
	if len(i) < 2:
		continue
	else:
		d[i] = d.get(i,0) + 1
lt = list(d.items())
lt.sort(key = lambda x:x[1],reverse = True)
db = {}
for i in range(10):
	db[i] = lt[i][0]
m = 0
gy = {}
for i in range(10):
	for j in range(10):
		if da[i] == db[j]:
			gy[m] == da[i]
			da[i] = ""
			db[i] = ""
			m = m+1
			break
print("共有词语:",end="")
for i in range(m):
	if i < m-1:
		print("{},".format(gy[i]))
	else:
		print("{}".format(gy[i])
print("2019特有:",end="")
j = 0
for i in range(10):
	if da[i] != "":
		if j<10-m-1:
			print("{},".format(da[i]),end=",")
		else:
			print("{}".format(da[i]))
		j = j+1
print("2018特有:",end="")
k = 0
for i in range(10):
	if da[i] != "":
		if k < 10-m-1:
			print("{},".format(da[i]),end=",")
		else:
			print("{}".format(da[i]))
		k = k + 1

10

f = open('data.txt','r')
f1 = open('clean.txt','w')
txt = f.read()
s = ''
for i in txt:
	if i not in '，。！？——《》（）【】；：“”‘’、¥\n':
		s += i
f1.write(s)
f1.close()
f.clsoe()

import jieba
f = open('clean.txt','r')
txt = f.read()
words = jieba.lcut(txt)
d = {}
for word in words:
	if len(word) < 3:
		continue
	else:
		d[word] = d.get(word,0) + 1
lt = list(d.items())
lt.sort(key = lambda x:x[1],reverse = True)
j = 0
for i in range(10):
	if j < 9:
		print('{}:{}'.foramt(lt[0],lt[1],end=",")
	else:
		print('{}:{}'.foramt(lt[0],lt[1])
	j += 1
f.clsoe()

11

import jieba
f = open('红楼梦.txt','r',encoding='utf-8')
f1 = open('停用词.txt','r',encoding='utf-8')
txt = jieba.lcut(f.read())
c = []
#将停用词添加到列表
stops_words=[]
for i in f1.read().spitlines():
	stop_words.append(i)
txt0 = []
for x in txt:
	if x not in stop_words:
		txt0.append(x)
#统计词频
counts = {}
for word in txt0:
	if len(word) == 1:
		continue
	elif word =='凤姐' or word == '凤姐儿' or word == '凤丫头':
		rword = '凤姐'
	elif word =='宝玉' or word == '二爷' or word == '宝二爷':
		rword = '宝玉'
	elif word =='黛玉' or word == '颦儿' or word == '林妹妹' or word == '黛玉道':
		rword = '黛玉'
	elif word =='宝钗' or word == '宝丫头':
		rword = '宝钗'
	elif word =='贾母' or word == '老祖宗':
		rword = '贾母'
	elif word =='袭人' or word == '袭人道':
		rword = '袭人'
	elif word =='贾政' or word == '贾政道':
		rword = '贾政'
	elif word =='贾涟' or word == '贾涟道':
		rword = '贾涟'
	counts[rword] = counts.get(rword,0) + 1
ls = list(counts.items())
ls.sort(key = lambda x:x[1],reverse=True)
with open('result.csv','a',encoding='gbk') as fo:
	for i in ls:
		key,value = i
		if value < 40:
			break
		fo.write(key+','+value+'\n')
fo.close()

12

f = open('八十天环游地球.txt','r',encoding='utf-8')
f1 = open('八十天环游地球-章节.txt','w',encoding='utf-8')
#一行行遍历
for i in f:
	text = i.split(" ")[0]
	if text[0] == "第" and text[-1] == "章":
		f1.write("{}\n".format(i.replace("\n",""))
f1.close()
f.close()

import jieba
f = open('八十天环游地球.txt','r',encoding='utf-8')
datas = f.readlines()
lt = []
for i in range(len(datas)):
	line = datas[i].split('')
	if datas[i][0] == "第" and "章" in lines[0]:
		l.append(i)
for i in range(len(lt)):
	if i != len(lt) - 1:
		data = "".join(datas[lt[i]:lt[i+1]])
	else:
		data = "".join(datas[l[i]:])
	s=data.split()[0]
	words = jieba.lcut(data)
	d = {}
	for y in words:
		if len(y) < 2:
			continue
		d[y] = d.get(y,0) + 1
	ls = list(d.items())
	ls.sort(key = lambda x:x[1],reserve = True)
	print(s,ls[0][0],ls[0][1])
f.close()