def Excel():
for filename in os.listdir('.'):
if(filename.endswith('lts.txt')):
page=0
f_d=open(filename,'r')
f_ex=xlwt3.Workbook(encoding='utf-8')
sheet=f_ex.add_sheet('sheet')
count=0
for line in f_d.readlines():
lists=line.split('||')
try:
num=0
for text in lists:
sheet.write(count,num,text)
num+=1
count+=1
except:
f_ex.save(str(page)+'.xls')
page+=1
f_ex=xlwt3.Workbook(encoding='utf-8')
sheet=f_ex.add_sheet('sheet')
count=0
num=0
for text in lists:
sheet.write(count,num,text)
num+=1
count+=1
f_ex.save(str(page)+'.xls')
def main():
excel = xlwt3.Workbook()
sheet = excel.add_sheet('sheet')
count = 0
startpage = 1
keys = [
'date', 'name', 'industry', 'local', 'round', 'capital',
'Investmenters'
]
while startpage < 1143:
try:
results = get_infor('https://www.itjuzi.com/investevents?page=%s' %
startpage)
except:
time.sleep(5)
continue
for item in results:
num = 0
for key in keys:
sheet.write(count, num, item[key])
num += 1
count += 1
print(startpage, '--ok')
startpage += 1
time.sleep(3)
excel.save('investevents.xls')
def writexls(file_name,table_name,data_list):
book=xlwt.Workbook()
sheet=book.add_sheet(table_name)
row=0
url="http://www.baidu.com"
for datarow in data_list:
col=0
for data in datarow:
#sheet.row(row).write(col,data)
if col==1 and len(datarow[15])<255 and row>0:
sheet.write(row, col, Formula('HYPERLINK("%s"; "%s")'%(datarow[15],data)),h_style)
elif col==15:
col+=1
else:
sheet.write(row, col, data)
#print(data)
col+=1
row+=1
book.save(file_name)
def excel():
excel = xlwt3.Workbook()
sheet = excel.add_sheet('sheet')
count = 0
labels = [
'postiontype', 'company', 'salary', 'workYear', 'education',
'industryField', 'companySize', 'city', 'financeStage'
]
page = 1
while page < 300:
try:
jobs = get_job('', page)
except:
time.sleep(5)
continue
for job in jobs:
num = 0
for i in labels:
sheet.write(count, num, job[i])
num += 1
count += 1
print(page, count)
page += 1
time.sleep(2)
excel.save('jobs.xls')
def combine_xls():
all_lines = []
xls_files = glob('./' + '*.xls')
for file_name in xls_files:
if '_pages' in file_name:
info = xlrd.open_workbook(file_name)
content = info.sheets()[0]
nrows = content.nrows
ncols = content.ncols
for i in range(1, nrows):
row_lst = []
for j in range(0, ncols - 1):
row_lst.append(str(content.cell(i, j).value))
all_lines.append([row_lst[0].split('_')[0]] + row_lst[2:])
wb = xlwt3.Workbook()
sheet = wb.add_sheet("计算机类图书信息")
for i in range(0, len(all_lines)):
for j in range(0, len(all_lines[i])):
sheet.write(i, j, all_lines[i][j])
#wb.save("图书信息_04_16.xls")
wb.save("计算机类图书信息" + ".xls")
def work(self):
self.f = xlwt3.Workbook()
self.sheet = self.f.add_sheet('sheet')
self.count = 0
for page in range(338):
get_url = get_urls(
'http://shanghai.anjuke.com/community/W0QQp1Z7QQp' + 'Z' +
str(page + 1))
print(page)
urls = get_url.run()
for url in urls:
item = get_infor(url)
item.work()
if item.statue == 0:
continue
self.sheet.write(self.count, 0, '浦东')
num = 1
for infor in item.infortable:
self.sheet.write(self.count, num, infor)
num += 1
self.sheet.write(self.count, num, item.price)
num += 1
self.sheet.write(self.count, num, url)
self.count += 1
self.f.save('data.xls')
def main():
excel = xlwt3.Workbook()
sheet = excel.add_sheet('sheet')
keys = [
'summary', 'temperature', 'windSpeed', 'humidity', 'visibility',
'pressure'
]
count = 0
starttime = 1262318400
endtime = time.time()
session = requests.session()
while starttime < endtime:
result = getdata(starttime, session)
try:
data = result[10]
except:
continue
date = timetostr(starttime)
num = 1
for key in keys:
try:
sheet.write(count, num, data[key])
num += 1
except:
num += 1
continue
sheet.write(count, 0, date)
starttime += 86400
count += 1
print(date, '--ok')
excel.save('result.xls')
def work(self):
self.f=xlwt3.Workbook()
self.sheet=self.f.add_sheet('sheet')
self.count=0
for page in range(50):
get_url=get_urls('http://www.dianping.com/search/category/1/20/g187r12'+'p'+str(page+1))
print(page)
urls=get_url.run()
for url in urls:
try:
item=get_infor(url)
item.work()
except:
continue
if item.statue==0:
continue
self.sheet.write(self.count,0,'购物')
self.sheet.write(self.count,1,'超市便利店')
self.sheet.write(self.count,2,'闵行')
self.sheet.write(self.count,3,item.area)
self.sheet.write(self.count,4,item.title)
self.sheet.write(self.count,5,item.address)
self.sheet.write(self.count,6,item.tel)
self.sheet.write(self.count,7,item.price)
self.sheet.write(self.count,8,item.times)
self.sheet.write(self.count,9,url)
self.count+=1
self.f.save('data.xls')
def excel():
f = open('data.txt', 'r')
ex = xlwt3.Workbook()
sheet = ex.add_sheet('sheet')
count = 0
rels = [
'品牌等级：(.*?)\|\|', '关注指数：(.*?)\|\|', '\|\|.*?董事.*?：(.*?)品牌创立',
'时间：(.*?)\|\|', '发源地：(.*?)\|\|', '官方网站：(.*?)\|\|', '客服电话：(.*?)\|\|',
'告词：(.*?)\|\|', '(产品\d+)]', '(网点\d+)]', '(新闻\d+)]', '(网店.*?)]'
]
for line in f.readlines():
line = line.replace('\n', '').replace('信用指数：', '')
lists = []
for rel in rels:
try:
i = re.findall(rel, line)[0]
except:
i = '--'
lists.append(i)
strs = line.split('||')
sheet.write(count, 0, strs[0])
sheet.write(count, 1, strs[1])
sheet.write(count, 2, strs[2])
sheet.write(count, 3, strs[3])
sheet.write(count, 4, strs[4])
sheet.write(count, 5, strs[5])
num = 6
for i in lists:
sheet.write(count, num, i)
num += 1
sheet.write(count, num, strs[-1])
count += 1
ex.save('data.xls')
def main():
data = xlrd.open_workbook('data/data.xlsx')
table = data.sheets()[0]
excel = xlwt3.Workbook()
sheet = excel.add_sheet('sheet')
for row in range(table.nrows):
print(row)
fromport = table.cell(row, 0).value
toport = table.cell(row, 1).value
commodityName = table.cell(row, 2).value
Load_Type = table.cell(row, 3).value
fromid = get_port(fromport)
toid = get_port(toport)
if fromid == False or toid == False:
sheet.write(row, 0, fromport)
sheet.write(row, 1, toport)
sheet.write(row, 2, commodityName)
sheet.write(row, 3, Load_Type)
sheet.write(row, 4, '')
excel.save('data/result.xls')
continue
try:
result = get_infor(
fromid, toid,
commodityName.replace('&',
'%26').replace(' ',
'+').replace(',', '%2C'))
except:
result = ''
sheet.write(row, 0, fromport)
sheet.write(row, 1, toport)
sheet.write(row, 2, commodityName)
sheet.write(row, 3, Load_Type)
sheet.write(row, 4, result)
excel.save('data/result.xls')
def main(username, passwd, page):
excel = xlwt3.Workbook()
count = 0
sheet = excel.add_sheet('sheet')
session = login(username, passwd)
for pagenum in range(int(page)):
ships = get_urls(session, pagenum + 1)
for ship in ships:
try:
ship = infor(session, ship)
except:
continue
if ship['img'] == False:
ship['phone'] = ''
continue
with open('temp.png', 'wb') as img:
img.write(ship['img'])
phonenum = img_ocr('temp.png')
ship['phone'] = phonenum
for ship in ships:
try:
sheet.write(count, 0, ship['title'])
sheet.write(count, 1, ship['weight'])
sheet.write(count, 2, ship['date'])
sheet.write(count, 3, ship['from'])
sheet.write(count, 4, ship['to'])
sheet.write(count, 5, ship['phone'])
count += 1
except:
continue
print(pagenum + 1, '---ok')
excel.save('data.xls')
def run(self):
try:
os.mkdir('data')
except:
print('..')
for key in self.urls:
try:
html=requests.get(self.urls[key],headers=self.headers).text
except:
continue
table=BeautifulSoup(html,'html.parser').find('table',attrs={'class':'today'}).find_all('tr')
self.f=xlwt3.Workbook()
self.sheet=self.f.add_sheet('sheet')
self.count=0
for item in table:
try:
infor=item.find_all('td')
self.sheet.write(self.count,0,infor[0].get_text())
num=1
for i in infor[2].find_all('em'):
self.sheet.write(self.count,num,i.get_text())
num+=1
self.count+=1
except:
continue
self.f.save('data/'+key+'.xls')
def main():
excel = xlwt3.Workbook()
sheet = excel.add_sheet('sheet')
count = 0
keys = [
'title', 'commentsNumber', 'asin', 'date', 'Rank', 'feature', 'Des'
]
browser = webdriver.Firefox()
browser.get('http://www.amazon.co.uk')
input('在浏览器中输入店铺链接，待加载完成后确认')
browser.implicitly_wait(10)
results = get_products(browser)
for url in results:
browser.get(url)
time.sleep(5)
try:
infor = inforParser(browser.page_source)
except:
continue
num = 0
for key in keys:
sheet.write(count, num, infor[key])
num += 1
print(count)
count += 1
excel.save('data.xls')
def __init__(self):
self.session = requests.session()
self.headers = {
'User-Agent':
'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:39.0) Gecko/20100101 Firefox/39.0',
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en-US,en;q=0.5',
'Accept-Encoding': 'gzip, deflate',
'Connection': 'keep-alive'
}
self.f = xlwt3.Workbook()
self.sheet = self.f.add_sheet('sheet')
self.lists = [
'id', 'Loan_Title', 'Loan_type', 'Loan_Status', 'Amount',
'Interest_Rate', 'Term', 'Next_Payment_Day', 'Term_Remain',
'Repayment_Type', 'Des', 'Guarantee_Type', 'Early_Repayment_Rate',
'Borrower_Id', 'Userid', 'Age', 'Education', 'Marital status',
'Working_City', 'Company_Scale', 'Position', 'Employment_Sector',
'Emploment_Length', 'Homeowner', 'Mortgage', 'Car', 'Car_Loan',
'Total_Amount', 'Number_of_Succesful_Loan', 'Income_Range_Monthly',
'Number_of_Borrow', 'Number_of_Repaid', 'Outstanding',
'Overdue_amount', 'Severe_overdue', 'Credit_Score',
'Number_Arrears', 'Credit_Limit'
]
self.count = 1
num = 0
self.login()
self.text_f = open('text.txt', 'a')
self.failed_f = open('failed.txt', 'a')
def create_excel_book(self, bookname, list_sql):
wb = xlwt3.Workbook(style_compression=2)
for counter, sql in enumerate(list_sql):
self.add_sheet_excel(sql[1], wb, sql[0])
report_folder = os.getcwd() + '\\reports\\'
if not os.path.exists(report_folder):
os.makedirs(report_folder)
wb.save(report_folder + bookname +
'_{0}__{1}.xls'.format(self.date_start, self.date_end))
def test_create_mini_xls(self):
book = xlwt3.Workbook()
sheet = book.add_sheet('xlwt was here')
book.save('mini.xls')
self.assertTrue(
filecmp.cmp(from_tst_dir('mini.xls'),
from_tst_dir(os.path.join('output-0.7.2', 'mini.xls')),
shallow=False))
def __init__(self):
self.session=requests.session()
self.headers = {
'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:39.0) Gecko/20100101 Firefox/39.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en-US,en;q=0.5',
'Accept-Encoding': 'gzip, deflate',
'Connection': 'keep-alive'}
self.f=xlwt3.Workbook()
self.sheet=self.f.add_sheet('sheet')
self.count=0
def run():
name = '相机'
f = xlwt3.Workbook(encoding='utf-8')
sheet = f.add_sheet('sheet')
data = xlrd.open_workbook(name + '.xls')
table = data.sheets()[0]
for i in range(table.nrows):
line = table.cell(i, 0).value
line = fan_jian(line)
sheet.write(i, 0, line)
f.save(name + '_.xls')
def __init__(self):
self.f = xlwt3.Workbook(encoding='utf-8')
self.sheet = self.f.add_sheet('sheet', cell_overwrite_ok=True)
self.sheet1 = self.f.add_sheet('sheet1', cell_overwrite_ok=True)
self.count = 1
head = ['公司', '职位', '职位发布城市', '工作经验', '学历要求', '年龄要求', '薪水']
num = 0
for i in head:
self.sheet.write(0, num, i)
self.sheet1.write(0, num, i)
num += 1
self.f.save('data.xls')
def insert_value(path):
workbook_new = xlwt3.Workbook() #创建一个Excel对象
sheet_new = workbook_new.add_sheet('create_new_sheet',
cell_overwrite_ok=True)
sheet_new.write(0, 0, "name")
sheet_new.write(0, 1, "sex")
for i in range(1, 101):
name = create_value('abcdefg', 3)
sex = create_value('01', 1)
sheet_new.write(i, 0, name)
sheet_new.write(i, 1, sex)
workbook_new.save(path)
def write_txt_to_xls(txt_file):
with open(txt_file, 'rb') as f:
file_content = f.read().decode('utf-8')
file_json = json.loads(file_content)
xls_content = xlwt3.Workbook()
sheet = xls_content.add_sheet('numbers')
for i in range(len(file_json)):
data = file_json[i]
for j in range(len(data)):
sheet.write(i, j, data[j])
xls_content.save('numbers.xls')
def write_txt_to_xls(txt_file):
# Read form the txt file
txt_object = open(txt_file, 'r')
file_content = json.load(txt_object)
# Write to the xls file
xls_object = xlwt3.Workbook()
sheet = xls_object.add_sheet('city')
for i in range(len(file_content)):
sheet.write(i, 0, i + 1)
data = file_content[str(i + 1)]
sheet.write(i, 1, data)
xls_object.save('city.xls')
def writexls(file_name, table_name, data_list):
book = xlwt.Workbook()
sheet = book.add_sheet(table_name)
row = 0
for datarow in data_list:
col = 0
for data in datarow:
sheet.row(row).write(col, data)
col = col + 1
row = row + 1
book.save(file_name)
def write_txt_to_xls(txt_file):
# Read form the txt file
txt_object = open(txt_file, 'r')
file_content = json.load(txt_object)
# Write to the xls file
xls_object = xlwt3.Workbook()
sheet = xls_object.add_sheet('numbers')
for i in range(len(file_content)):
data = file_content[i]
for j in range(len(data)):
sheet.write(i, j, data[j])
xls_object.save('numbers.xls')
def save_fixed_original(self):
"""
Method that prepares fixed original table to be saved into new file
as xlwt table and then calls save_file to actually save the table.
"""
wb = xlwt.Workbook()
ws = wb.add_sheet('Page1')
for i in range(len(self.codes)):
ws.write(i, 0, self.codes[i])
ws.write(i, 1, self.est[i])
ws.write(i, 2, self.eng[i])
ws.write(i, 3, self.rus[i])
self.save_file(wb, original=True)
def write_txt_to_xls(txt_file):
with open(txt_file, 'rb') as f:
file_content = f.read().decode('utf-8')
file_json = json.loads(file_content)
xls_object = xlwt3.Workbook()
sheet = xls_object.add_sheet('student')
for i in range(len(file_json)):
sheet.write(i, 0, i + 1)
data = file_json[str(i + 1)]
for j in range(len(data)):
sheet.write(i, j + 1, data[j])
xls_object.save('student.xls')
def Excel():
excel = xlwt3.Workbook()
sheet = excel.add_sheet('sheet')
count = 0
for line in open('data.txt', 'r').readlines():
line = line.replace('，||', '||').replace('||', ' ||').replace('\n', '')
lists = line.split('||')
num = 0
for i in lists:
sheet.write(count, num, i)
num += 1
count += 1
excel.save('data.xls')
def main():
pageurls=['http://invest.ppdai.com/loan/list_safe_s0_ppage?Rate=0','http://invest.ppdai.com/loan/list_riskmiddle_s0_ppage?Rate=0','http://invest.ppdai.com/loan/list_riskhigh_s0_ppage?Rate=0']
labels=['新手收益区','中风险收益区','高风险收益区']
excel=xlwt3.Workbook()
for index in range(len(pageurls)):
sheet=excel.add_sheet(labels[index])
count=0
pageurl=pageurls[index]
for page in range(1,100):
try:
urls=geturls(pageurl.replace('page',str(page)))
except:
break
for url in urls:
try:
loan=loaninfor(url.split('|')[-1])
except:
continue
result=[]
result.append(url.split('|')[0])
lists=loan.split('|')
result.append(lists[1])
result.append(lists[3].replace('借入信用：',''))
result.append(lists[5].replace('借款金额：',''))
result.append(lists[6].replace('年利率：',''))
result.append(lists[7].replace('期限：',''))
result.append(lists[8].replace('进度条：',''))
history=eval(lists[-1])
if history==[]:
continue
sum=0
for index_hi in range(len(history)-1):
try:
sum+=calculate_time(history[index_hi].split('-')[1],history[index_hi+1].split('-')[1])
except:
continue
try:
diff=sum/(len(history)-1)
except:
continue
for item in history:
num=0
for i in result:
sheet.write(count,num,i)
num+=1
sheet.write(count,num,item.split('-')[0])
sheet.write(count,num+1,item.split('-')[1])
sheet.write(count,num+2,diff)
count+=1
excel.save('result.xls')
print(labels[index],'--',page,'--ok')
def main():
excel = xlwt3.Workbook()
sheet = excel.add_sheet('sheet')
queue = []
urls = ['http://news.fudan.edu.cn']
exists_urls = []
count = 0
try:
os.mkdir('fudan')
except:
print('Exists')
while len(urls):
url = urls.pop()
if url in exists_urls:
continue
exists_urls.append(url)
work = Infor(url)
queue.append(work)
if len(urls) > 0 and len(queue) < 20:
continue
for work in queue:
work.start()
for work in queue:
work.join()
while len(queue):
work = queue.pop()
if work.statue:
if work.title == '404 Not Found':
continue
sheet.write(count, 0, count)
sheet.write(count, 1, work.url)
sheet.write(count, 2, work.title)
sheet.write(count, 3, work.date)
sheet.write(count, 4, work.author)
sheet.write(count, 5, work.comefrom)
sheet.write(count, 6, work.body)
text = ''
for item in work.urls:
text += item + ';'
sheet.write(count, 7, text)
sheet.write(count, 8, work.keywords)
urls += work.urls
with open('fudan/' + str(count) + '.html', 'w') as f:
f.write(work.html)
del work
count += 1
excel.save('fudan.xls')
print(count)
if count > 1500:
break
def __init__(self):
self.f = xlwt3.Workbook(encoding='utf-8')
self.sheet = self.f.add_sheet('sheet', cell_overwrite_ok=True)
self.count = 1
head = [
'实地认证', '身份认证', '信用报告', '工作认证', '收入认证', '房产认证', '购车认证', '结婚认证',
'学历认证', '手机实名认证', '微博认证', '居住地证明'
]
self.sheet.write(0, 0, 'ID')
num = 1
for i in head:
self.sheet.write(0, num, i)
num += 1
self.f.save('data.xls')
