def dyS2L():
#用pandas包读取指定xlsx文档,转换为list数据格式
urlList = readFile().iloc[:, 0].tolist()
#创建名为“geturl”的功能，输入参数为url
def geturl(url):
res = requests.head(url)
#获取具体的长链接
url = res.headers.get('location')
#返回变量
return url
#创建名为list1的变量
list1 = []
#长度为urlList变量行数的循环
for i in urlList:
a = geturl(i)
#把返回得到的变量储存在变量名为list1的数组里
list1.append(a)
print(a)
time.sleep(2)
#写出list1里的所有内容到"iris.csv"文档里，不带有列名
pd.DataFrame(list1).to_csv(BASE_DIR + "\抖音结果.csv",
header=None,
index=False)
def test_33(self):
res = " class myClass_1; class myClass_2 how are you; class myClass_22 how ; class myClass_23 how; class myClass_3 ; class myClass_33 ; class myClass_4 ; class myClass_5;"
line = readFile("TestFiles/TestClass.cpp")
self.assertEqual(res, line)
class_name = classname()
mainloop(line, class_name)
length = len(class_name.listClasses)
self.assertEqual(5, length)
def test_88(self):
res = " "
line = readFile("TestFiles/comments.hpp")
self.assertEqual(res, line)
class_name = classname()
mainloop(line, class_name)
length = len(class_name.listClasses)
self.assertEqual(0, length)
def test_44(self):
res = " NGI_LOG_DEBUG(\"Original Flight period to get booking class filter for ASM TIM Wdc: \" << ioScheduleChange.getFlightPeriod()->shortDump()); NGI_LOG_DEBUG(\"Flight period to get booking class filter for ASM TIM Wdc: \" << theNewFlightPeriod.shortDump()); NGI_LOG_DEBUG(\"Selected booking class filters:\");"
line = readFile("TestFiles/TestFallClass.cpp")
self.assertEqual(res, line)
class_name = classname()
mainloop(line, class_name)
length = len(class_name.listClasses)
self.assertEqual(1, length)
def test_55(self):
res = " class TestTestCalss : public COM::Abstract { friend class CoverTestTestCalss; friend class CoverTestClass2 ; }; } "
line = readFile("TestFiles/TestFriendClass.cpp")
self.assertEqual(res, line)
class_name = classname()
mainloop(line, class_name)
length = len(class_name.listClasses)
self.assertEqual(3, length)
def test_99(self):
res = " #include \"iostream\" using namespace std; class myClass{ public: void setpVar(int pvar){pVar = pvar;} void setpfvar(int pfvar){this.pfvar = pfvar;} void setplvar(long plvar){ this.plvar = plvar; } private: int piVar; float pfvar; long plvar; std::string myString; }"
line = readFile("TestFiles/class_method/Test.hpp")
self.assertEqual(res, line)
class_name = classname()
mainloop(line, class_name)
length = len(class_name.listClasses)
self.assertEqual(1, length)
def test_2(self):
res = " #include <iostream> using namespace std; class Shape2 { public: void setWidth2(int w) { width2 = w; } void setHeight2(int h) { height2 = h; } protected: int width2; int height2; }; class Shape { public: void setWidth(int w) { width = w; } void setHeight(int h) { height = h; } protected: int width; int height; }; class Rectangle: public Shape { public: int getArea() { return (width * height); } }; class Box : public Shape { public: int getArea() { return (width * height); } }; class SecondBox : public Shape { public: int getArea() { return (width * height); } }; class ThirdBox : public Shape { public: int getArea() { return (width * height); } }; class FourthBox : public Shape { public: int getArea() { return (width * height); } }; class FifthBox : public Shape { public: int getArea() { return (width * height); } }; class SixthBox : public Shape { public: int getArea() { return (width * height); } }; class SeventhBox : public Shape { public: int getArea() { return (width * height); } }; class EighthBox : public Shape ,Shape2 { public: int getArea() { return (width * height); } }; class NinethBox : public Shape ,Shape2 { public: int getArea() { return (width * height); } }; int main(void) { Rectangle Rect; Rect.setWidth(5); Rect.setHeight(7); cout << \"Total area: \" << Rect.getArea() << endl; return 0; }"
line = readFile("TestFiles/Inheriteance.cpp")
self.assertEqual(res, line)
class_name = classname()
mainloop(line, class_name)
length = len(class_name.listClasses)
self.assertEqual(12, length)
def test_66(self):
res = " DequeueAction Test_Calss::dequeueCallback(Message& msg) { try { std::string theMessageAsString; } NGI_SUPERCATCH_ACT_L(\"unexpected exception in first callback\", _aSC = NULL; return DequeueAction::MOVE_TO_EXCEPTION_QUEUE;); }"
line = readFile("TestFiles/TestMultiline.cpp")
self.assertEqual(res, line)
class_name = classname()
mainloop(line, class_name)
length = len(class_name.listClasses)
print(class_name)
self.assertEqual(0, length)
def test_77(self):
res = " #include <iostream> #include <vector> using namespace std; int main() { vector<int> g1; for (int i = 1; i <= 5; i++) g1.push_back(i); cout << \"Output of begin and end: \"; for (auto i = g1.begin(); i != g1.end(); ++i) cout << *i <<; return 0; }"
line = readFile("TestFiles/comments.cpp")
self.assertEqual(res, line)
class_name = classname()
mainloop(line, class_name)
length = len(class_name.listClasses)
print(class_name)
self.assertEqual(0, length)
def encode(filename):
filepath = Path(filename)
# checking to see if the file we have been given is valid
if not filepath.is_file():
print("Error, cannot find file: " + filename)
return
# calling the parser to decode the file
file_str, frequency = readFile(filename)
def main():
(char_to_int, int_to_char) = readFile()
valid_set = loadFile(mode='valid')
for i in range(50):
sentence = predict(i, char_to_int, int_to_char, valid_set)
for wd in sentence:
print wd,
print('\n')
'''
def weChatBiz():
# 读取txt文档但不读取文档的抬头，把位置为在最左的字串更换为list数据格式
wechatlist = readFile()[0].tolist()
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--window-size=400,600')
#创建两个新变量
name = []
biz = []
for i in wechatlist:
browser = webdriver.Chrome(options=chrome_options, executable_path=".\chromedriver.exe")
url = 'https://weixin.sogou.com/weixin?type=1&s_from=input&query='+ i +'&ie=utf8&_sug_=n&_sug_type_='
# 打开浏览器预设网址
browser.get(url)
urls = browser.find_elements_by_xpath("//a")
window_before = browser.window_handles[0]
time.sleep(0.5)
if (urls[17] is not None) and (urls[17].get_attribute("href") != "javascript:void(0);") :
urls[17].click()
window_after = browser.window_handles[1]
browser.switch_to_window(window_after)
time.sleep(0.5)
res3 = requests.get(browser.current_url)
a = re.findall('var biz = "(\w+==)',res3.text)
b = re.findall('var title ="([a-zA-Z0-9_\u4e00-\u9fa5]+)', res3.text)
biz.append(a)
name.append(b)
else:
a = []
b = []
biz.append(a)
name.append(b)
browser.quit()
print(a, b)
final=pd.DataFrame((pd.Series([x[0] if len(x[:])!=0 else x[:] for x in name]),pd.Series([y[0] if len(y[:])!=0 else y[:] for y in biz]))).T
final.to_excel(BASE_DIR + "\微信biz结果.xlsx", header=["name", "biz"], index=False)
def weiboM2W():
data = readFile()
# 历遍每个网址
for i in range(data.shape[0]):
# 以“://m.weibo”判断是否为手机端
if "://m.weibo" in data.iloc[i, 0]:
# 将每个手机端网址的后16位取出来
mobile_url = data.iloc[i, 0][-16:]
# 后七位进行转换
first = changeBase(int(mobile_url[-7:]), 62)
# 后八 -- 十四位进行转换
second = changeBase(int(mobile_url[-14:-7]), 62)
# 前两位进行转换
third = changeBase(int(mobile_url[:2]), 62)
# 微博机制：如果7位十进制数字转换后不满4个占位符，则需要在前面加一个0
if len(second) != 4:
second = "0" + second
if len(first) != 4:
first = "0" + first
# 转换后的62进制，位数必定是9位
fix_url = third + second + first
# 将原有的10进制数字替换成62进制
data.iloc[i, 0] = data.iloc[i, 0][:30] + fix_url
# 规整格式
data.iloc[i, 0] = data.iloc[i, 0].replace("m.", "")
data.iloc[i, 0] = data.iloc[i, 0].replace("cn", "com")
else:
pass
# 更换表头名
data.columns = ['网页端url']
# 输出excel
return data.to_excel(BASE_DIR + "\微博网页URL结果.xlsx", index=False)
def test_8(self):
res = " "
line = readFile("TestFiles/comments.hpp")
self.assertEqual(res, line)
def test_7(self):
res = " #include <iostream> #include <vector> using namespace std; int main() { vector<int> g1; for (int i = 1; i <= 5; i++) g1.push_back(i); cout << \"Output of begin and end: \"; for (auto i = g1.begin(); i != g1.end(); ++i) cout << *i <<; return 0; }"
line = readFile("TestFiles/comments.cpp")
self.assertEqual(res, line)
def test_6(self):
res = " DequeueAction Test_Calss::dequeueCallback(Message& msg) { try { std::string theMessageAsString; } NGI_SUPERCATCH_ACT_L(\"unexpected exception in first callback\", _aSC = NULL; return DequeueAction::MOVE_TO_EXCEPTION_QUEUE;); }"
line = readFile("TestFiles/TestMultiline.cpp")
self.assertEqual(res, line)
def test_5(self):
res = " class TestTestCalss : public COM::Abstract { friend class CoverTestTestCalss; friend class CoverTestClass2 ; }; } "
line = readFile("TestFiles/TestFriendClass.cpp")
self.assertEqual(res, line)
def check_for_duplicates(paths, hash=hashlib.sha1):
hashes_by_size = {}
hashes_on_1k = {}
hashes_full = {}
duplicates = []
for path in paths:
for dirpath, dirnames, filenames in os.walk(path):
for filename in filenames:
full_path = os.path.join(dirpath, filename)
try:
file_size = os.path.getsize(full_path)
except (OSError, ):
# not accessible (permissions, etc) - pass on
pass
duplicate = hashes_by_size.get(file_size)
if duplicate:
hashes_by_size[file_size].append(full_path)
else:
hashes_by_size[file_size] = [
] # create the list for this file size
hashes_by_size[file_size].append(full_path)
# For all files with the same file size, get their hash on the 1st 1024 bytes
for __, files in hashes_by_size.items():
if len(files) < 2:
continue # this file size is unique, no need to spend cpy cycles on it
for filename in files:
small_hash = get_hash(filename, first_chunk_only=True)
duplicate = hashes_on_1k.get(small_hash)
if duplicate:
hashes_on_1k[small_hash].append(filename)
else:
hashes_on_1k[small_hash] = [
] # create the list for this 1k hash
hashes_on_1k[small_hash].append(filename)
# For all files with the hash on the 1st 1024 bytes, get their hash on the full file - collisions will be duplicates
for __, files in hashes_on_1k.items():
if len(files) < 2:
continue # this hash of fist 1k file bytes is unique, no need to spend cpy cycles on it
for filename in files:
full_hash = get_hash(filename, first_chunk_only=False)
duplicate = hashes_full.get(full_hash)
if duplicate:
duplicates.append((filename, duplicate))
print("Duplicate found: %s and %s" % (filename, duplicate))
else:
hashes_full[full_hash] = filename
# Writing to the file.
mfile = open('../Docs/duplicates.txt', mode='w')
for row in duplicates:
mfile.write("Duplicate found: %s and %s \n" % (row[0], row[1]))
mfile.close()
# Deleting duplicates.
means = []
for i in range(1, 9):
means.append(findMean(i))
genres = {
"Metal": 1,
"Rock": 2,
"Jazz": 3,
"Rap": 4,
"Electronic": 5,
"Pop": 6,
"Soundtrack": 7,
"Classical": 8
}
for row in duplicates:
dup1genre = row[0].split("/")[-3]
dup2genre = row[1].split("/")[-3]
song = readFile(row[0], 0)
distance1 = distance.euclidean(song[1:], means[genres[dup1genre] - 1])
distance2 = distance.euclidean(song[1:], means[genres[dup2genre] - 1])
if distance1 > distance2:
if os.path.isfile(row[0]):
os.remove(row[0])
else:
os.remove(row[1])
else:
if os.path.isfile(row[1]):
os.remove(row[1])
else:
os.remove(row[0])
'''for row in duplicates:
from readFile import *
lst = readFile('test.txt')
print(lst)
print('*' * 120)
print('\n')
for y in lst:
for x in y:
a = int(x)
if (int(x) < 0) is True:
print(x, end='\t\t')
print('')
def test_4(self):
res = " NGI_LOG_DEBUG(\"Original Flight period to get booking class filter for ASM TIM Wdc: \" << ioScheduleChange.getFlightPeriod()->shortDump()); NGI_LOG_DEBUG(\"Flight period to get booking class filter for ASM TIM Wdc: \" << theNewFlightPeriod.shortDump()); NGI_LOG_DEBUG(\"Selected booking class filters:\");"
line = readFile("TestFiles/TestFallClass.cpp")
self.assertEqual(res, line)
def test_9(self):
res = " #include \"iostream\" using namespace std; class myClass{ public: void setpVar(int pvar){pVar = pvar;} void setpfvar(int pfvar){this.pfvar = pfvar;} void setplvar(long plvar){ this.plvar = plvar; } private: int piVar; float pfvar; long plvar; std::string myString; }"
line = readFile("TestFiles/class_method/Test.hpp")
self.assertEqual(res, line)
message = {}
message['packettype'] = "change"
message['sendingNode'] = "CostEditor"
message['node'] = node
message['cost'] = cost
message['port'] = port
message = json.dumps(message)
sock.sendto(message.encode(), ('localhost', port))
#reads the original distances between the nodes
#nodes: stores the read files data
nodes = {}
for x in range(1, len(sys.argv)):
node = sys.argv[x][-5]
nodes[node] = readFile(sys.argv[x])
#pointer: keep tracks of the arrow which points to the current highlighted option
#userInput: stores input from the keyboard; 'n' means no input
#nodestaken: used as a flag when nodes to be changed hace been selected
pointer = 0
userInput = 'n'
nodestaken = False
while True:
os.system("cls")
print("\n\t COST EDITOR\n")
print("\t Use Q and W for cursor\n\t Use double E to select\n\n")
print("=" * 44)
#done: stores the nodes that have been printed;
#makes sure same distances are not repeated that
from scipy.io import loadmat
from svmTrain import *
import numpy as np
from getVocabList import *
# ==================== Part 1: Email Preprocessing ====================
# To use an SVM to classify emails into Spam v.s. Non-Spam, you first need
# to convert each email into a vector of features. In this part, you will
# implement the preprocessing steps for each email. You should
# complete the code in processEmail.m to produce a word indices vector
# for a given email.
print('\nPreprocessing sample email (emailSample1.txt)\n')
# Read file
file_contents = readFile('emailSample1.txt')
word_indices = processEmail(file_contents)
# Print Stats
print('==== Word Indices ==== \n')
print(word_indices, '\n')
input('Program paused. Press enter to continue.\n')
# ==================== Part 2: Feature Extraction ====================
# Now, you will convert each email into a vector of features in R^n.
print('\nExtracting features from sample email (emailSample1.txt)\n')
# Extract Features
os.system("cls")
print("=" * 56)
print("\n I am Router " + self.name + '\n')
for node in self.routingTable:
if self.routingTable[node][
'cost'] != math.inf and node != self.name:
print(
" Least cost path to router " + node + " : through " +
self.routingTable[node]['through'] + " with cost " +
str("{0:.1f}".format(self.routingTable[node]['cost']) +
"\n"))
print("=" * 56)
def displayPacket(self, packet, sendingNode):
print("\nProcessing packet from ", sendingNode)
for x in packet:
print(x + " through " + packet[x]['through'] + " cost ",
packet[x]["cost"])
print()
def change(self, message):
self.neighbours[message['node']]['cost'] = float(message['cost'])
self.routingTable[message['node']]['cost'] = float(message['cost'])
print(message['node'] + " set to ",
self.neighbours[message['node']]['cost'])
if __name__ == '__main__':
node = Node(sys.argv[1], sys.argv[2], readFile(sys.argv[3]))
node.run()
input()
def test_3(self):
res = " class myClass_1; class myClass_2 how are you; class myClass_22 how ; class myClass_23 how; class myClass_3 ; class myClass_33 ; class myClass_4 ; class myClass_5;"
line = readFile("TestFiles/TestClass.cpp")
self.assertEqual(res, line)
