def monthyearnavigate(monthyear):
compare = r.read(
'//*[@aria-roledescription="datepicker"]/div/div[1]/div[2]/div/div/div')
while(monthyear != compare):
r.click('//*[contains(@aria-label,"Next")]')
compare = r.read(
'//*[@aria-roledescription="datepicker"]/div/div[1]/div[2]/div/div/div')
def get_stay_url():
url= [None] * 10 #catching top 10 in case of airbnb plus
if (r.exist('//*[@id="FMP-target"]/div/div/div/div/div[1]/div/div/div/div[2]/a') == True):
url[0]=URL+r.read('//*[@id="FMP-target"]/div/div/div/div/div[1]/div/div/div/div[2]/a/@href')
for i in range(2,11) : url[i-1]=URL+r.read(f'//*[@id="FMP-target"]/div/div/div/div/div[{i}]/div/div/div/div[1]/a/@href')
else:
url[0]=URL+r.read('//div[@itemprop="itemList"]/div[2]/div/div/div/div[2]/div/div/div/div/div[1]/div/div/div/div[2]/a/@href')
for i in range(2,11) : url[i-1]=URL+r.read(f'//div[@itemprop="itemList"]/div[2]/div/div/div/div[2]/div/div/div/div/div[{i}]/div/div/div/div[1]/a/@href')
#print(url)
return(url)
def get_rpa(timeout=10):
r.init()
r.url('https://www.google.com')
r.type('//*[@name="q"]', 'decentralization[enter]')
print(r.read('result-stats'))
r.snap('page', 'results.png')
r.close()
def change_password(username, new_password):
#//*[@id="content-main"]/div[9]/table/tbody/tr/th/a
element = '//tr[@class="model-user"]/th/a'
r.click(element)
#//Element[@attribute1="abc" and @attribute2="xyz" and text()="Data"]
#user_elem = f'//td[@class="field-name" and text()="{username}"]' #/preceding-sibling::th[@class="field-id"]/a'
user_elem = f'//td[text()="{username}"]/preceding-sibling::th[@class="field-id"]/a'
r.click(user_elem)
pwd_form_elem = '//a[@href="../password/"]'
r.click(pwd_form_elem)
pwd1_elem = '//input[@id="id_password1"]'
r.click(pwd1_elem)
r.type(pwd1_elem, new_password)
pwd2_elem = '//input[@id="id_password2"]'
r.click(pwd2_elem)
r.type(pwd2_elem, new_password)
submit_elem = '//input[@type="submit"]'
r.click(submit_elem)
success_elem = '//ul[@class="messagelist"]/li[@class="success"]'
txt = r.read(success_elem)
print('CLICK')
return txt
def download_stay_picinfo(): #Downloads picture locally as jpg img, MIGHT be useful if we are doing local image classification....but I rather gcloud classify with url if needed
print('Extracting Top 5 Stay Information..')
url=[]
url=get_stay_url()
print('Downloading Pics uploaded by host..')
i=0
k=0
while (i<5):
r.url(url[i+k])
r.click('//*[@id="FMP-target"]')
j=0
while (1):
j=j+1
print(f'Downloading Homestay {i+1} Photo {j}')
r.wait(0.4)
#r.snap('//div[@data-testid="photo-viewer-slideshow-desktop"]/div/div/div/div/div/img',f"data/{i+1}/{j}.jpg") #fastest but not perfect
if (r.exist('//div[@data-testid="photo-viewer-slideshow-desktop"]/div/div/div/div/div/img/@src') == True):
dl_link=r.read('//div[@data-testid="photo-viewer-slideshow-desktop"]/div/div/div/div/div/img/@src')
r.download(dl_link,f'data/{i+1}/{j}.jpg')
print(f'Homestay {i+1} Photo {j} downloaded!')
else:
i=i-1 #Detects Whales (Airbnb Plus spoils the format alot)
k=k+1 #Compensating Constant k
print("WHALE detected, adding one more loop..")
if (r.exist('/html/body/div[9]/div/div/div/div/div[3]/div/div[2]/button') == False or j >= 15): break #Max 15 photos
r.click('/html/body/div[9]/div/div/div/div/div[3]/div/div[2]/button')
i=i+1
r.click('/html/body/div[9]/div/div/div/section/div/div[1]/div/button')
print('Done.')
def today_dollar():
r.init()
r.url('https://www.melhorcambio.com/dolar-hoje')
sleep(4)
dolar = r.read('//*[@id="comercial"]')
sleep(2)
print(f'{dolar} | {datetime.today()}')
r.close()
return dolar
def dollar_cannadian():
r.init()
r.url('https://www.melhorcambio.com/dolar-hoje')
sleep(4)
r.click('//*[@id="dock"]/ul/li[2]/a')
sleep(4)
dolar_c = r.read('//*[@id="comercial"]')
sleep(2)
print(f'{dolar_c} | {datetime.today()}')
r.close()
return dolar_c
def do_web_auto(search_data):
r.init()
r.url('https://www.google.com')
r.click('.gLFyf.gsfi')
r.type('.gLFyf.gsfi', f'{search_data}[enter]')
#r.type("//*[@name='q']', 'decentralization[enter]")
#print(r.read('result-stats'))
r.snap('page', 'results.png')
res = r.read('result-stats')
r.close()
return res
def gestionar_uuii(uuii, codigoPostal, cto):
r.url(uuii)
r.timeout(120)
if r.read('//*[@id="btnNew"]'):
r.click('//*[@id="btnNew"]')
r.timeout(120)
if r.read('//*[@id="btnFormEditSave"]'):
r.select('//*[@name="planta"]', 'BA')
r.type('//*[@name="cp"]', codigoPostal)
r.click('//*[@id="btnFormEditSave"]')
if r.read('//*[@class="tableCell"]'):
r.click('//*[@class="tableCell"]')
r.click('//*[@id="btnRD"]')
if r.read('//*[@id="btnFormRDSave"]'):
r.timeout(120)
r.select('//*[@name="rd"]', cto)
r.wait(5)
if r.read('//*[@id="ctoAddress_ctoName"]'):
r.click('//*[@id="btnFormRDSave"]')
if r.url('xxxx.do?dispatchMethod=rdSave'):
print('Gestionada')
def extract_stay_info_as_data(
): #Generates URL/text in dict instead, shorten time for upload/download, more unified
data = {
"0": {
"name": "",
"description": "",
"inventory": "",
"price": "",
"rating": "",
"picurl": [None] * 10,
"pictext": [None] * 10,
"url": "",
"coordinates": ""
},
"1": {
"name": "",
"description": "",
"inventory": "",
"price": "",
"rating": "",
"picurl": [None] * 10,
"pictext": [None] * 10,
"url": "",
"coordinates": ""
},
"2": {
"name": "",
"description": "",
"inventory": "",
"price": "",
"rating": "",
"picurl": [None] * 10,
"pictext": [None] * 10,
"url": "",
"coordinates": ""
},
"3": {
"name": "",
"description": "",
"inventory": "",
"price": "",
"rating": "",
"picurl": [None] * 10,
"pictext": [None] * 10,
"url": "",
"coordinates": ""
},
"4": {
"name": "",
"description": "",
"inventory": "",
"price": "",
"rating": "",
"picurl": [None] * 10,
"pictext": [None] * 10,
"url": "",
"coordinates": ""
}
}
print('Extracting Top 5 Stay Picture Information (10 Image Max)..')
url = []
url = get_stay_url()
i = 0
k = 0
while (i < 5):
data[str(i)]["url"] = url[i + k]
r.url(url[i + k])
print(f'Extracting Text Data - Homestay {i+1}')
if (r.exist('//*[@itemprop="name"]/span/h1/span') == True):
data[str(i)]["coordinates"] = r.read(
'//*[@data-veloute="map/GoogleMap"]/div/div/div/div[2]/a/@href'
).split("=", 1)[1].split("&", 1)[0]
data[str(i)]["name"] = r.read('//*[@itemprop="name"]/span/h1/span')
data[str(i)]["description"] = r.read(
'//*[@href="#neighborhood"]/div')
#data[str(i)]["description"]=data[str(i)]["description"].replace("\xa0"," ")
data[str(i)]["inventory"] = r.read(
'//*[@id="room"]/div[2]/div/div[2]/div/div/div[3]/div/div/div[1]/div/div/div[1]/div'
) + " " + r.read(
'//*[@id="room"]/div[2]/div/div[2]/div/div/div[3]/div/div/div[1]/div/div/div[2]/div'
) + " " + r.read(
'//*[@id="room"]/div[2]/div/div[2]/div/div/div[3]/div/div/div[1]/div/div/div[3]/div'
) + " " + r.read(
'//*[@id="room"]/div[2]/div/div[2]/div/div/div[3]/div/div/div[1]/div/div/div[4]/div'
)
if (r.present('//*[@id="book_it_form"]/div[4]/div[2]') == True):
data[str(i)]["price"] = r.read(
'//*[@id="book_it_form"]/div[4]/div[2]').split("Total",
1)[1]
else:
data[str(i)]["price"] = r.read(
'//*[@id="book_it_form"]/div[2]').split("Total",
1)[1] #Total Price
if r.present('//*[@data-heading-focus="review header"]/div'):
data[str(i)]["rating"] = r.read(
'//*[@data-heading-focus="review header"]/div/div/@aria-label'
) + " (" + r.read(
'//*[@data-heading-focus="review header"]/div/span') + ")"
else:
data[str(i)]["rating"] = "No Reviews Yet"
r.click('//*[@data-veloute="hero-view-photos-button"]')
j = 0
while (1):
j = j + 1
print(f'Extracting Picture Data - Homestay {i+1} Photo {j}')
r.wait(0.4)
#r.snap('//div[@data-testid="photo-viewer-slideshow-desktop"]/div/div/div/div/div/img',f"data/{i+1}/{j}.jpg") #fastest but not perfect
if (r.exist('//img[@data-veloute="slideshow-image"]/@src') ==
True):
data[str(i)]["picurl"][j - 1] = r.read(
'//img[@data-veloute="slideshow-image"]/@src')
if (r.present(
'//*[@data-veloute="slideshow-modal"]/div/div/div[2]/div[2]/div[2]/div[2]/div'
) == True):
data[str(i)]["pictext"][j - 1] = r.read(
'//*[@data-veloute="slideshow-modal"]/div/div/div[2]/div[2]/div[2]/div[2]/div'
)
#r.download(dl_link,f'data/{i+1}/{j}.jpg')
print(f'Homestay {i+1} Photo {j} extracted!')
if (r.exist('//button[@aria-label="Next"]') == False
or j >= 10):
break
r.click('//button[@aria-label="Next"]')
else:
i = i - 1 #Detects Whales (Airbnb Plus spoils the format alot)
k = k + 1 #Compensating Constant k
print("WHALE detected, adding one more loop..")
i = i + 1
#r.click('/html/body/div[9]/div/div/div/section/div/div[1]/div/button')
print('Done.')
return data
# input the values to the rpachallenge website through web automation
# this makes use of xpath (using chrome, inspect the element > right-click on highlighted element >
# copy > copy xpath)
bot.init()
bot.url('http://www.rpachallenge.com')
# start the clock
bot.click('/html/body/app-root/div[2]/app-rpa1/div/div[1]/div[6]/button')
# loop through the records and input onto website
for r in range(2, sheet.max_row + 1):
# first name
bot.type('//*[@ng-reflect-name="labelFirstName"]', sheet.cell(row=r, column=1).value)
# last name
bot.type('//*[@ng-reflect-name="labelLastName"]', sheet.cell(row=r, column=2).value)
# company name
bot.type('//*[@ng-reflect-name="labelCompanyName"]', sheet.cell(row=r, column=3).value)
# role in company
bot.type('//*[@ng-reflect-name="labelRole"]', sheet.cell(row=r, column=4).value)
# address
bot.type('//*[@ng-reflect-name="labelAddress"]', sheet.cell(row=r, column=5).value)
# email
bot.type('//*[@ng-reflect-name="labelEmail"]', sheet.cell(row=r, column=6).value)
# phone number
bot.type('//*[@ng-reflect-name="labelPhone"]', str(sheet.cell(row=r, column=7).value))
# click submit
bot.click('/html/body/app-root/div[2]/app-rpa1/div/div[2]/form/input')
# get result
print('RPA Challenge result: ' + bot.read('/html/body/app-root/div[2]/app-rpa1/div/div[2]/div[2]'))
# take screenshot
bot.snap('page', 'rpa-challenge-result.png')
# close the browser
bot.close()
import rpa as r
# use init() to start TagUI, it auto downloads TagUI on first run
# default init(visual_automation = False, chrome_browser = True)
r.init()
# use url('your_url') to go to web page, url() returns current URL
r.url('https://ca.yahoo.com')
# use type() to enter text into an UI element or x, y location
# '[enter]' = enter key, '[clear]' = clear field
r.type('search-box', 'github')
# use read() to fetch and return text from UI element
search_text = r.read('search-box')
print(search_text)
# use click() to click on an UI element or x, y location
# rclick() = right-click, dclick() = double-click
r.click('search-button')
r.wait(6.6)
# use snap() to save screenshot of page or UI element
# page = web page, page.png = computer screen
r.snap('page', 'results.png')
r.snap('logo', 'logo.png')
r.wait(4.4)
r.click('GitHub')
r.wait(10)
#,'Lavender','Lim_Chu_Kang','Little_India','Macpherson','Mandai','Marine_Parade','Mount_Sophia','Mountbatten','Newton','Novena','Orchard'
#,'Outram','Pasir_Panjang','Pasir_Ris','Paya_Lebar','Potong_Pasir','Pulau_Ubin','Punggol','Queenstown','Raffles_Place','Redhill','River_Valley'
#,'Robertson_Quay','Seletar','Sembawang','Sengkang','Sentosa','Serangoon','Serangoon_Gardens','Siglap','Simei','Sixth_Avenue','Somerset','Tampines'
#,'Tanglin','Tanglin_Halt','Tanjong_Pagar','Tanjong_Rhu','Telok_Blangah',]
size = len(area_list)
for a in range(size):
URL = f'https://www.yelp.com/search?find_desc=Restaurants&find_loc=Singapore&l=p%3ASG-SG%3ASingapore%3A%3A{area_list[a]}'
r.url(URL)
time.sleep(10)
URL_list = []
maxpage = int(
r.read(
'//*[@id="wrap"]/div[3]/div[2]/div/div[1]/div[1]/div[2]/div[2]/div[1]/div[2]/span'
).replace("1 of ", ""))
for j in range(0, maxpage):
if j != 0:
if r.present(
f'(//*[@id="wrap"]/div[3]/div[2]/div/div[1]/div[1]/div[2]/div[2]/div[1]/div[1]/div/div/span/a/span)[2]'
):
r.click(
f'(//*[@id="wrap"]/div[3]/div[2]/div/div[1]/div[1]/div[2]/div[2]/div[1]/div[1]/div/div/span/a/span)[2]'
)
else:
r.click(
f'(//*[@id="wrap"]/div[3]/div[2]/div/div[1]/div[1]/div[2]/div[2]/div[1]/div[1]/div/div/span/a/span)[1]'
)
import rpa as r
r.init()
r.url('https://cn.bing.com/')
r.type('//*[@name="q"]', 'decentralization[enter]')
print(r.read('result-stats'))
r.snap('page', 'results.png')
r.close()
from time import sleep
from datetime import datetime
# Email modules
import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
from email.mime.base import MIMEBase
from email import encoders
r.init()
r.url('https://www.melhorcambio.com/dolar-hoje')
sleep(4)
window = auto.getActiveWindow()
window.maximize()
dolar = r.read('//*[@id="comercial"]')
sleep(2)
r.snap('page', 'img3.png')
sleep(2)
# window.close() fecha todas as janelas do
# navegador. Já o r.close() fecha apenas a
# janela do bot.
r.close()
print(dolar)
# Session of email
text_email = f'Dolar hoje: {dolar}\nDay: {str(datetime.today())}'
# email sender, password and destiny
fromadr = '*****@*****.**'
pwd = '###########'
import rpa as r
import pandas as pd
import time
import pickle
#Get URLs
r.init()
URL = f'https://www.tripadvisor.com.sg/Restaurants-g294265-Singapore.html'
r.url(URL)
time.sleep(10)
maxpage = int(r.read('//*[@id="EATERY_LIST_CONTENTS"]/div[2]/div/div/a[6]/@data-page-number'))
for j in range (0,maxpage):
URL_list = []
if j!=0:
if r.present(f'(//*[@id="EATERY_LIST_CONTENTS"]/div[2]/div/a)[2]'):
r.click(f'(//*[@id="EATERY_LIST_CONTENTS"]/div[2]/div/a)[2]')
else:
r.click(f'(//*[@id="EATERY_LIST_CONTENTS"]/div[2]/div/a)[1]')
time.sleep(10)
for i in range (1,100):
if r.exist(f'(//*[@id="component_2"]/div/div[*]/span/div[1]/div[2]/div[1]/div/span/a/@href)[{i}]') == False: break
URL_list.append("https://www.tripadvisor.com.sg" + r.read(f'(//*[@id="component_2"]/div/div[*]/span/div[1]/div[2]/div[1]/div/span/a/@href)[{i}]'))
#print(URL_list)
with open(f'url_list_{j}.txt', 'wb') as filehandle: pickle.dump(URL_list, filehandle)
usep_pred_arr = usep_lr.predict(np.array([[demand_predicted]]))
usep_pred = usep_pred_arr[0][0]
return demand_predicted, usep_pred
print(get_period_nbr())
period_nbr = get_period_nbr()
today = datetime.today()
#os.chdir("D:")
r.init()
r.url('https://www.emcsg.com/marketdata/priceinformation')
r.wait(5)
print(
r.read(
'//table[@class="ptable realtimePriceTable"]//tr[@class="current"]'))
data_list = r.read(
'//table[@class="ptable realtimePriceTable"]//tr[@class="current"]'
).splitlines()
data_list[0] = today.strftime('%d/%m/%Y')
data_list[1] = get_period_nbr()
data_list[2] = float(data_list[2])
data_list[3] = float(data_list[3])
data_list[4] = float(data_list[4])
data_list[6] = float(data_list[6])
if data_list[6] == 0:
data_list.append(0)
else:
data_list.append(1)
data_list = [data_list]
df_current = DataFrame(data_list,
r.wait(1)
r.click('pnlFiltreBtn')
r.wait(3)
total_items = r.count('div.col-sm-12')
print("Toplam İhale Sayısı =",total_items)
r.wait(3)
for x in range(0, total_items):
print(x+1,". İhale")
worksheet.write(x+1, 0, x+1)
ihale_adi = r.read('//*[@id="sonuclar"]/div[' + str(x+1) + ']/div/div/div/div[2]/div/div/p[1]')
print(ihale_adi)
worksheet.write(x+1, 1, ihale_adi)
idare_adi = r.read('//*[@id="sonuclar"]/div[' + str(x+1) + ']/div/div/div/div[3]/div/div/p')
print(idare_adi)
worksheet.write(x+1, 2, idare_adi)
ihale_detayi = r.read('//*[@id="sonuclar"]/div[' + str(x+1) + ']/div/div/div/div[2]/div/div/p[2]')
print(ihale_detayi)
worksheet.write(x+1, 3, ihale_detayi)
workbook.close()
r.close()
# to use in Jupyter notebook, Python script or interactive shell
import rpa as r
# use init() to start TagUI, it auto downloads TagUI on first run
# default init(visual_automation = False, chrome_browser = True)
r.init()
# use url('your_url') to go to web page, url() returns current URL
r.url('https://ca.yahoo.com')
# use type() to enter text into an UI element or x, y location
# '[enter]' = enter key, '[clear]' = clear field
r.type('search-input', 'github')
# use read() to fetch and return text from UI element
search_text = r.read('search-input')
print(search_text)
# use click() to click on an UI element or x, y location
# rclick() = right-click, dclick() = double-click
r.click('search-button')
# use wait() to wait for a number of seconds
# default wait() is 5 seconds
r.wait(6.6)
# use snap() to save screenshot of page or UI element
# page = web page, page.png = computer screen
r.snap('page', 'results.png')
r.snap('logo', 'logo.png')
import rpa
import pyautogui
rpa.init(visual_automation=False, chrome_browser=True)
rpa.url('https://www.melhorcambio.com/dolar-hoje')
rpa.wait(5.0)
janela = pyautogui.getActiveWindow()
janela.maximize()
rpa.type('//*[@id="original"]', '10')
pyautogui.sleep(2)
dolar_comercial = rpa.read('//*[@id="comercial"]')
pyautogui.sleep(2)
print(dolar_comercial)
janela.close()
def urlSnap():
r.init(visual_automation=True)
r.url('https://www.google.com')
r.type("q", "CEG[enter]")
print(r.read('result-stats'))
r.snap('page', 'results.png')
def sigaaRPA(self):
r.init()
r.timeout(30)
while(self.state > 0):
if self.terminateBot:
r.close()
break
elif self.state == 1:
# use url('your_url') to go to web page, url() returns current URL
r.url('https://sigaa.upb.edu.co/ssomanager/c/SSB')
self.state = self.state + 1
elif self.state == 2:
# use type() to use the keyboard to write something
if r.exist(X.username) & r.present(X.username):
r.type(X.username, '000290164')
r.type(X.password, 'Tandres1997_')
self.state = self.state + 1
else:
print("Couldn\'t find Username and Password Components")
self.state = 1
elif self.state == 3:
# use click() to click on an UI element or x, y location
self.state = click(X.login, self.state)
elif self.state == 4:
## hace click en Estudiantes
self.state = click(X.estudiantes, self.state)
elif self.state == 5:
## Hace click en Seguimiento a la formación
self.state = click(X.seguimieto, self.state)
elif self.state == 6:
## hace click en Calificaciones parciales
self.state = click(X.calif, self.state)
elif self.state == 7:
## Selecciona el semestre del cual quiere mirar las notas
r.select(X.semester, self.semester)
self.state = self.state + 1
elif self.state == 8:
## se hace click en enviar
r.click(X.enviar)
self.state = self.state + 1
elif self.state == 9:
tablexpath = ''
r.wait(2)
numCursos = r.count('//*[@class="datadisplaytable"][2]/tbody/tr/td/a')
for i in range(2,numCursos+2):
tablexpath = '//*[@class="datadisplaytable"][2]/tbody/tr['+ str(i) +']/td/a'
if r.exist(tablexpath):
r.click(tablexpath)
r.wait(1)
pagetitle = r.read('//div[@id="pagetitle"]')
if pagetitle == 'Detalle de Calificación de Componente':
materia = r.read('//*[@class="datadisplaytable"][1]/tbody/tr[5]/td[2]')
print(materia)
r.snap('page', './notas/s'+self.semester+'/'+ materia +'.png')
# r.table('//table[@class="datadisplaytable"][2]', './csv/table'+str(i-1)+'.csv')
r.dom('history.back()')
# use wait() to wait for a number of seconds
# default wait() is 5 seconds
r.wait(5)
self.terminateBot = True
elif self.state == 10:
r.dom('history.back()')
print("Posicion: " + str(i))
#print(list[i])
r.url(list[i])
reps=0
err=False
while tempNum==atmNumber:
reps+=1
if reps>5:
break
# checkWhatsError = r.read('//*[@id="fallback_block"]/div/a')
# print('Error '+ checkWhatsError)
# if checkWhatsError == 'Descargar':
# print('Error found')
# err=True
# break
tempNum = r.read('//*[@id="main_block"]/div[1]/h1/p/span')
print(atmNumber + " ==? " + tempNum)
if n ==0:
break
r.wait(0.2)
#if err:
# continue
if reps >5:
print('Atasco capturar este error')
numErroneosURL.append(list[i])
numErroneos.append(atmNumber)
cantidadNoEnviados +=1
continue
atmNumber = tempNum
r.click('//*[@id="action-button"]')
r.wait(0.3)
import rpa as r
r.init(visual_automation=True, chrome_browser=False)
print(r.read('pdf_window.png'))
print(r.read('image_preview.png'))
r.hover('anchor_element.png')
print(r.read(r.mouse_x(), r.mouse_y(), r.mouse_x() + 400, r.mouse_y() + 200))
r.close()
links = int(purchase_history_number)
row = 1
for link in range(1, links + 1):
t.sleep(1)
total_items = int(
r.count('section.o_c-card-history')) + 1 # total of items per page
item = 1
t.sleep(1)
while item < total_items:
# key_full = key_name1 + str(item) + key_name2
# this f" is for new python 3.6 text format; it allows for changable variables inside the string by using {}
key_full = f"/html/body/div[1]/div[2]/section/div[1]/section[2]/div/div/section[{str(item)}]" \
f"/div[2]/div/div[1]/div[2]"
price_full = price_part1 + str(item) + price_part2
var = r.read(key_full)
t.sleep(1)
r.timeout(5)
if not r.exist(price_full):
var2 = '0.00'
else:
var2 = r.read(price_full)
t.sleep(1)
sheet.cell(row=row, column=1).value = var
sheet.cell(row=row, column=2).value = var2
# you can add records to a list, then use append as well
# sheet.append(list)
print(var)
row += 1
item += 1
minus_link = int(purchase_history_number) - link
import rpa as r
import pyautogui as p
import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
import pandas as pd
r.init()
r.url('https://www.melhorcambio.com/dolar-hoje')
p.sleep(4)
dollar_value = r.read('//*[@id="comercial"]')
r.close()
#texto do email
texto_email = 'A cotação do dolar hoje ' + str(
pd.Timestamp('today')) + ' é ' + dollar_value
# email remetente, senha, destinatário
de = '*****@*****.**'
senha = '*********'
para = '*****@*****.**'
# Setup the MIME
message = MIMEMultipart()
message['From'] = de
message['To'] = para
message['Subject'] = 'Cotação do dolar' #Título do e-mail
def extract_stay_info_as_data(
): #Generates URL/text in dict instead, shorten time for upload/download, more unified
data = {
"0": {
"name": "",
"description": "",
"inventory": "",
"price": "",
"rating": "",
"picurl": [None] * 10,
"pictext": [None] * 10,
"url": ""
},
"1": {
"name": "",
"description": "",
"inventory": "",
"price": "",
"rating": "",
"picurl": [None] * 10,
"pictext": [None] * 10,
"url": ""
},
"2": {
"name": "",
"description": "",
"inventory": "",
"price": "",
"rating": "",
"picurl": [None] * 10,
"pictext": [None] * 10,
"url": ""
},
"3": {
"name": "",
"description": "",
"inventory": "",
"price": "",
"rating": "",
"picurl": [None] * 10,
"pictext": [None] * 10,
"url": ""
},
"4": {
"name": "",
"description": "",
"inventory": "",
"price": "",
"rating": "",
"picurl": [None] * 10,
"pictext": [None] * 10,
"url": ""
}
}
print('Extracting Top 5 Stay Picture Information (10 Image Max)..')
url = []
url = get_stay_url()
i = 0
k = 0
while (i < 5):
data[str(i)]["url"] = url[i + k]
r.url(url[i + k])
print(f'Extracting Text Data - Homestay {i+1}')
if (r.exist(
'//*[@data-plugin-in-point-id="TITLE_DEFAULT"]/div/div/section/div/div/h1'
) == True):
data[str(i)]["name"] = r.read(
'//*[@data-plugin-in-point-id="TITLE_DEFAULT"]/div/div/section/div/div/h1'
)
data[str(i)]["description"] = r.read(
'//*[@data-plugin-in-point-id="OVERVIEW_DEFAULT"]/div/div/div/section/div/div/div/div/div'
)
data[str(i)]["description"] = data[str(i)]["description"].replace(
"\xa0", " ")
data[str(i)]["inventory"] = r.read(
'//*[@data-plugin-in-point-id="OVERVIEW_DEFAULT"]/div/div/div/section/div/div/div/div/div[2]'
)
data[str(i)]["price"] = r.read(
'//*[@data-plugin-in-point-id="BOOK_IT_SIDEBAR"]/div/div[2]/div/ul[2]/li/span[2]'
) #Total Price
if r.present(
'//*[@data-plugin-in-point-id="REVIEWS_DEFAULT"]/div/div/section/div/div/div/h2/span[2]/span'
):
data[str(i)]["rating"] = r.read(
'//*[@data-plugin-in-point-id="REVIEWS_DEFAULT"]/div/div/section/div/div/div/h2/span[2]/span'
)
else:
data[str(i)]["rating"] = "No Reviews Yet"
r.click('//*[@id="FMP-target"]')
j = 0
while (1):
j = j + 1
print(f'Extracting Picture Data - Homestay {i+1} Photo {j}')
r.wait(0.4)
#r.snap('//div[@data-testid="photo-viewer-slideshow-desktop"]/div/div/div/div/div/img',f"data/{i+1}/{j}.jpg") #fastest but not perfect
if (r.exist(
'//div[@data-testid="photo-viewer-slideshow-desktop"]/div/div/div/div/div/img/@src'
) == True):
data[str(i)]["picurl"][j - 1] = r.read(
'//div[@data-testid="photo-viewer-slideshow-desktop"]/div/div/div/div/div/img/@src'
)
if (r.present(
'//div[@data-testid="photo-viewer-slideshow-desktop"]/div/div/div/div[2]/div/span/div/span'
) == True):
data[str(i)]["pictext"][j - 1] = r.read(
'//div[@data-testid="photo-viewer-slideshow-desktop"]/div/div/div/div[2]/div/span/div/span'
)
#r.download(dl_link,f'data/{i+1}/{j}.jpg')
print(f'Homestay {i+1} Photo {j} extracted!')
if (r.exist('//*[@aria-label="Next"]') == False or j >= 10):
break
r.click('//*[@aria-label="Next"]')
else:
i = i - 1 #Detects Whales (Airbnb Plus spoils the format alot)
k = k + 1 #Compensating Constant k
print("WHALE detected, adding one more loop..")
i = i + 1
#r.click('/html/body/div[9]/div/div/div/section/div/div[1]/div/button')
print('Done.')
return data
import rpa as r
import pandas as pd
import time
#Read all restaurant names in csv
yelp = pd.read_csv("yelpindex.csv")
yelp["URL"].head
r.init()
#Fill up table with URLs
for i in (0, len(yelp["URL"])):
r.url(yelp["URL"][i])
if r.present("//*[@id='rso']/div[1]/div/div[1]/a/@href"):
name = r.read("//*[@id='rso']/div[1]/div/div[1]/a/@href")
else:
name = r.read("//*[@id='rso']/div[2]/div/div[1]/a/@href")
print(name)
yelp["URL"][i] = name
time.sleep(5)
yelp.to_csv("yelpindex_updated.csv")
yelp2TA = pd.read_csv("yelpindex_updated.csv")
yelp2TA.reset_index(drop=True)
yelp2TA["URL"].head
#Get Reviews
author_loc = ""
reviews_df = pd.DataFrame()
#if y == 9: init = 33
# to use in Jupyter notebook, Python script or interactive shell
import rpa as r
# use init() to start TagUI, it auto downloads TagUI on first run
# default init(visual_automation = False, chrome_browser = True)
r.init()
# use url('your_url') to go to web page, url() returns current URL
r.url('https://ca.yahoo.com')
# use type() to enter text into an UI element or x, y location
# '[enter]' = enter key, '[clear]' = clear field
r.type('ybar-sbq', 'github')
# use read() to fetch and return text from UI element
search_text = r.read('ybar-sbq')
print(search_text)
# use click() to click on an UI element or x, y location
# rclick() = right-click, dclick() = double-click
r.click('ybar-search')
# use wait() to wait for a number of seconds
# default wait() is 5 seconds
r.wait(6.6)
# use snap() to save screenshot of page or UI element
# page = web page, page.png = computer screen
r.snap('page', 'results.png')
r.snap('logo', 'logo.png')
# r.wait(3)
# r.keyboard('https://1839.trust.codes/xCJEHBoK[enter]')
# r.wait(2)
r.init(visual_automation = True)
r.url('https://www.foodsafety.govt.nz/registers-lists/exporters/index.htm?setup_file=exporters-ssi.setup.cgi&rows_to_return=20000&submit_search=Search')
time.sleep(10)
tr = '//form[@ACTION="/registers-lists/exporters/index.htm"]//tr'
show_email_button = '//a[@class="obf-show-email"]'
count = r.count(tr)
print(count)
for i in range(count):
button = f"{tr}[{i+1}]{show_email_button}"
r.click(button)
print(f"clicked {button}")
print('clicked all')
time.sleep(99999999)
result = r.read('page')
r.close()
target_file = '/Users/teemo/Downloads/www.foodsafety.govt.nz_registered_list.txt'
with open(target_file, "w") as f:
f.write(result)
