def n_seguidores(self, username):
driver = self.driver
driver.get('https://www.instagram.com/'+ username +'/')
time.sleep(3)
user_botao = driver.find_elements_by_class_name('g47SY ')
print_us = user_botao.get_attribute('title')
print(print_us)
please help me to find numbers of following from html
.find_elements_* return a list, so you need access by index.
There are 3 numbers with the same class name in the page, and the numbers of following you mean is the third.
And to get the number you can use .text, not .get_attribute('title')
Try following code:
user_botao = driver.find_elements_by_class_name('g47SY ')
#second index
print_us = user_botao[2].text
print(print_us)
Related
I am trying to make a selenium python script to collect data from each job in an indeed job search. I can easily get the data from the first and second page. The problem I am running into is while looping through the pages, the script only clicks the next page and the previous page, in that order. Going from page 1 -> 2 -> 1 -> 2 -> ect. I know it is doing this because both the next and previous button have the same class name. So when I redeclare the webelement variable when the page uploads, it hits the previous button because that is the first location of the class in the stack. I tried making it always click the next button by using the xpath, but I still run into the same errors. I would inspect the next button element, and copy the full xpath. my code is below, I am using python 3.7.9 and pip version 21.2.4
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.common.exceptions import NoSuchElementException
import time
PATH = "C:\Program Files (x86)\chromedriver.exe"
driver = webdriver.Chrome(PATH)
HTTPS = "https://"
# hard coded data to test
siteDomain = "indeed.com"
jobSearch = "Software Developer"
locationSearch = "Richmond, VA"
listOfJobs = []
def if_exists_by_id(id):
try:
driver.find_element_by_id(id)
except NoSuchElementException:
return False
return True
def if_exists_by_class_name(class_name):
try:
driver.find_element_by_class_name(class_name)
except NoSuchElementException:
return False
return True
def if_exists_by_xpath(xpath):
try:
driver.find_element_by_xpath(xpath)
except NoSuchElementException:
return False
return True
def removeSpaces(strArray):
newjobCounter = 0
jobCounter = 0
for i, word in enumerate(strArray):
jobCounter += 1
if strArray[i].__contains__("\n"):
strArray[i] = strArray[i].replace("\n", " ")
if strArray[i].__contains__("new"):
newjobCounter += 1
print(strArray[i] + "\n")
if newjobCounter == 0:
print("Unfortunately, there are no new jobs for this search")
else:
print("With " + str(newjobCounter) + " out of " + str(jobCounter) + " new jobs!")
return strArray
try:
# Goes to Site
driver.get(HTTPS + siteDomain)
# obtains access to elements from website
searchJob = driver.find_element_by_name("q")
searchLocation = driver.find_element_by_name("l")
# clear text field
searchJob.send_keys(Keys.CONTROL, "a", Keys.BACK_SPACE)
searchLocation.send_keys(Keys.CONTROL, "a", Keys.BACK_SPACE)
# inputs values into website elements
searchJob.send_keys(jobSearch)
searchLocation.send_keys(locationSearch)
# presses button to search
searchLocation.send_keys(Keys.RETURN)
# Begin looping through pages
pageList = driver.find_element_by_class_name("pagination")
page = pageList.find_elements_by_tag_name("li")
numPages = 0
for i,x in enumerate(page):
time.sleep(1)
# checks for popup, if there is popup, exit out and sleep
if if_exists_by_id("popover-x"):
driver.find_element_by_id("popover-x").click()
time.sleep(1)
# increment page counter variabke
numPages += 1
# obtains data in class name value
jobCards = driver.find_elements_by_class_name("jobCard_mainContent")
# prints number of jobs returned
print(str(len(jobCards)) + " jobs in: " + locationSearch)
# inserts each job into list of jobs array
# commented out to make debugging easier
# for jobCard in jobCards:
# listOfJobs.append(jobCard.text)
# supposed to click the next page, but keeps alternating
# between next page and previous page
driver.find_element_by_class_name("np").click()
print("On page number: " + str(numPages))
# print(removeSpaces(listOfJobs))
except ValueError:
print(ValueError)
finally:
driver.quit()
Any help will be greatly appreciated, also if I am implementing bad coding practices in the structure of the script please let me know as I am trying to learn as much as possible! :)
I have tested your code.. the thing is there are 2 'np' class elements when we go to the 2nd page.. what you can do is for first time use find_element_by_class_name('np') and for all the other time use find_elements_by_class_name('np')[1] that will select the next button.. and you can use find_elements_by_class_name('np')[0] for the previous button if needed. Here is the code!
if i == 0:
driver.find_element_by_class_name("np").click()
else:
driver.find_elements_by_class_name("np")[1].click()
Just replace the line driver.find_element_by_class_name("np").click() with the code snippet above.. I have tested it and it worked like a charm.
Also i am not as experienced as the other devs here.. But i am glad if i could help you. (This is my first answer ever on stackoverflow)
As it print all details but problem is that print Master Juice repeatedly as below is highlighted in picture that is my link https://www.foodpanda.pk/restaurants/new?lat=24.9414896&lng=67.1676002&vertical=restaurants from where i scrape
from selenium import webdriver
driver = webdriver.Chrome('F:/chromedriver')
driver.get("https://www.foodpanda.pk/restaurants/new?lat=24.9414896&lng=67.1676002&vertical=restaurants")
# response = scrapy.Selector(text=driver.page_source)
list = driver.find_elements_by_css_selector("ul.vendor-list li")
length = len(driver.find_elements_by_css_selector("ul.vendor-list li"))
for i in range(length):
try:
name = driver.find_elements_by_css_selector(".headline .name")[i].text
time = driver.find_elements_by_css_selector(".badge-info")[i].text.strip()
rating = driver.find_elements_by_css_selector(".rating")[i].text
dealtag = driver.find_elements_by_css_selector(".multi-tag")[i].text
except:
pass
print(name,time,rating,dealtag)
It's because it prints every time even if there's an error, printing whatever was previously stored in your name, time, etc. variables. Try it when you move your print statement within your try: block
from selenium import webdriver
driver = webdriver.Chrome('F:/chromedriver')
driver.get("https://www.foodpanda.pk/restaurants/new?lat=24.9414896&lng=67.1676002&vertical=restaurants")
# response = scrapy.Selector(text=driver.page_source)
list = driver.find_elements_by_css_selector("ul.vendor-list li")
length = len(driver.find_elements_by_css_selector("ul.vendor-list li"))
for i in range(length):
try:
name = driver.find_elements_by_css_selector(".headline .name")[i].text
time = driver.find_elements_by_css_selector(".badge-info")[i].text.strip()
rating = driver.find_elements_by_css_selector(".rating")[i].text
dealtag = driver.find_elements_by_css_selector(".multi-tag")[i].text
print(name,time,rating,dealtag)
except:
pass
Have been trying to emulate examples posted earlier, yet got stuck.
I have a simple web form: Last name, name, email, password, confirm password.
Also a .csv with 4 columns that corresponds to the form
Last name Name Email Password
0 Brown Stan brown#stan.com 12345678
1 White Eagle white#eagle.com 123456789
2 Dante Aligr adant#mail.au 98765432
So, all I want is to feed the 3 entries to the form and click "Sent" after each entry.
I copycated a code from here that seemed passing but I keep getting this
File "C:\Users\untitled2.py", line 43, in <module>
last.send_keys(lname)
AttributeError: 'list' object has no attribute 'send_keys'
the code I tried
from selenium import webdriver
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.firefox.firefox_binary import FirefoxBinary
options = Options()
options.binary_location = FirefoxBinary(r"C:\Program Files\Mozilla Firefox\firefox.exe")
driver = webdriver.Firefox(executable_path=r'C:\WebDriver\bin\geckodriver.exe', firefox_options=options)
import time
import pandas as pd
reg = pd.read_csv('Form.csv', header=0, delimiter=';', sep=r'\s*;\s*')
print(reg)
lname = reg['Last name'].tolist()
name = reg['Name'].tolist()
mail = reg['Email'].tolist()
password = reg['Password'].tolist()
password_c = reg['Password'].tolist()
driver.get('url')
first = driver.find_elements_by_xpath("/html/body/div/div[3]/form/div[2]/div/div[2]/div[2]/div/div/div[2]/div/div[1]/div/div[1]/input")
last = driver.find_elements_by_xpath("/html/body/div/div[3]/form/div[2]/div/div[2]/div[1]/div/div/div[2]/div/div[1]/div/div[1]/input")
mail = driver.find_elements_by_xpath("/html/body/div/div[3]/form/div[2]/div/div[2]/div[3]/div/div/div[2]/div/div[1]/div/div[1]/input")
password = driver.find_elements_by_xpath("/html/body/div/div[3]/form/div[2]/div/div[2]/div[4]/div/div/div[2]/div/div[1]/div/div[1]/input")
password_confirm = driver.find_elements_by_xpath("/html/body/div/div[3]/form/div[2]/div/div[2]/div[4]/div/div/div[2]/div/div[1]/div/div[1]/input")
submit = driver.find_elements_by_xpath('/html/body/div/div[3]/form/div[2]/div/div[3]/div[1]/div/div/span/span')
for lname, name, mail, password, password_c in zip(lname, name, mail, password, password_c):
last.send_keys(lname)
time.sleep(1)
first.send_keys(name)
time.sleep(1)
mail.send_keys(mail)
time.sleep(1)
password.send_keys(password)
time.sleep(1)
password_confirm.send_keys(password_c)
time.sleep(1)
submit.click()
time.sleep(3)
Any nudge into the right direction will be highly appreciated since I have seen plenty of examples of using lists with send_keys()
Thanks!
The error message indicates that you are using send_keys() with plain python lists.
According to Selenium docs, find_elements_by_xpath does indeed return a list.
It's possible that you meant to use find_element_by_xpath (without the 's' after element)?
Anyhow,
the execution part should have look like this
for lnames in lname:
count = 0
for names in name:
count_name = 0
for mails in mail_:
count_mail = 0
for value in last:
value.send_keys(lname[count])
count +=1
for x in mail:
x.send_keys(mail_[count_mail])
count_mail +=1
for y in first:
y.send_keys(name[count_name])
count_name +=1
submit = driver.find_element_by_xpath('//*[#id="mG61Hd"]/div[2]/div/div[3]/div[1]/div/div/span/span')
submit.click()
I am trying to open up several URL's (because they contain data I want to append to a list). I have a logic saying "if amount in icl_dollar_amount_l" then run the rest of the code. However, I want the script to only run the rest of the code on that specific amount in the variable "amount".
Example:
selenium opens up X amount of links and sees ['144,827.95', '5,199,024.87', '130,710.67'] in icl_dollar_amount_l but i want it to skip '144,827.95', '5,199,024.87' and only get the information for '130,710.67' which is in the 'amount' variable already.
Actual results:
Its getting webscaping information for amount '144,827.95' only and not even going to '5,199,024.87', '130,710.67'. I only want it getting webscaping information for '130,710.67' because my amount variable has this as the only amount.
print(icl_dollar_amount_l)
['144,827.95', '5,199,024.87', '130,710.67']
print(amount)
'130,710.67'
file2.py
def scrapeBOAWebsite(url,fcg_subject_l, gp_subject_l):
from ICL_Awk_Checker import rps_amount_l2
icl_dollar_amount_l = []
amount_ack_missing_l = []
file_total_l = []
body_l = []
for link in url:
print(link)
browser = webdriver.Chrome(options=options,
executable_path=r'\\TEST\user$\TEST\Documents\driver\chromedriver.exe')
# if 'P2 Cust ID 908554 File' in fcg_subject:
browser.get(link)
username = browser.find_element_by_name("dialog:username").get_attribute('value')
submit = browser.find_element_by_xpath("//*[#id='dialog:continueButton']").click()
body = browser.find_element_by_xpath("//*[contains(text(), 'Total:')]").text
body_l.append(body)
icl_dollar_amount = re.findall('(?:[\£\$\€]{1}[,\d]+.?\d*)', body)[0].split('$', 1)[1]
icl_dollar_amount_l.append(icl_dollar_amount)
if not missing_amount:
logging.info("List is empty")
print("List is empty")
count = 0
for amount in missing_amount:
if amount in icl_dollar_amount_l:
body = body_l[count]
get_file_total = re.findall('(?:[\£\$\€]{1}[,\d]+.?\d*)', body)[0].split('$', 1)[1]
file_total_l.append(get_file_total)
return icl_dollar_amount_l, file_date_l, company_id_l, client_id_l, customer_name_l, file_name_l, file_total_l, \
item_count_l, file_status_l, amount_ack_missing_l
I don't know if I understand problem but this
if amount in icl_dollar_amount_l:
doesn't give information on which position is '130,710.67' in icl_dollar_amount_l and you need also
count = icl_dollar_amount_l.index(amount)
for amount in missing_amount:
if amount in icl_dollar_amount_l:
count = icl_dollar_amount_l.index(amount)
body = body_l[count]
But it will works if you expect only one amount on list icl_dollar_amount_l. For more elements you would have to use rather for-loop and check every element separatelly
for amount in missing_amount:
for count, item in enumerate(icl_dollar_amount_l)
if amount == item :
body = body_l[count]
But frankly I don't know why you don't check it in first loop for link in url: when you have direct access to icl_dollar_amount and body
This is my code:
from selenium import webdriver
import time
x = 0
#while x < 5:
browser = webdriver.Chrome('/Users/John Smith/Downloads/chromedriver.exe')
browser.get('https://kdp.amazon.com/en_US/')
x = 0
def Sign():
browser.find_element_by_id('signinButton-announce')
elem = browser.find_element_by_id('signinButton-announce')
elem.click()
email = browser.find_element_by_id('ap_email')
email.send_keys(' ')
password = browser.find_element_by_id('ap_password')
password.send_keys(' ')
SignIn = browser.find_element_by_id('signInSubmit')
SignIn.click()
def Sign1():
browser.find_element_by_id('signinButton-announce')
elem = browser.find_element_by_id('signinButton-announce')
elem.click()
email = browser.find_element_by_id('ap_email')
email.send_keys(' ')
password = browser.find_element_by_id('ap_password')
password.send_keys(' ')
SignIn = browser.find_element_by_id('signInSubmit')
SignIn.click()
browser.execute_script("window.open('https://kdp.amazon.com/en_US/', 'new window')")
Sign()
time.sleep(20)
browser.execute_script("window.open('https://kdp.amazon.com/en_US/', 'new window')")
if (browser.current_url == 'https://kdp.amazon.com/en_US/'):
Sign1()
x += 1
I tried to solve the problem by creating another tab, so if I put in the authentication code once, maybe it would stop asking for it after. I can't really find a way to solve this.. Is there a way?
I've heard of using a current chrome profile, however I could not find a way to actually use any commands on it. I've got the chrome file to work, but it would not go to the URL I needed it to go to.