Here is my code :
import os
import time
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
opt = Options()
opt.add_argument("--disable-infobars")
opt.add_argument("start-maximized")
# Pass the argument 1 to allow and 2 to block
opt.add_experimental_option("prefs", {
"profile.default_content_setting_values.media_stream_mic": 2,
"profile.default_content_setting_values.media_stream_camera": 2,
"profile.default_content_setting_values.geolocation": 2,
"profile.default_content_setting_values.notifications": 2
})
executable_path = r'C:\Users\SAMSUNG\Dropbox\CreationNumMaroc\chromedriver'
os.environ["webdriver.chrome.driver"] = executable_path
global driver
driver = webdriver.Chrome(r'C:\Users\SAMSUNG\Dropbox\CreationNumMaroc\chromedriver', options=opt)
# NavigationStart
time.sleep(3)
driver.get("https://yandex.com/")
time.sleep(4)
driver.find_element_by_xpath("//input[#class='input__control input__input mini-suggest__input']").send_keys("fkljdslkjdfdks")
time.sleep(2)
html_source = driver.page_source
if "fkljdslkjdfdks" in html_source:
print(html_source)
else:
print("nothing")
My script go to yandex.ru, write on search "fkljdslkjdfdks" .
and then :
I want to edit the word "fkljdslkjdfdks" from the source page .
You have not clicked on search button and that is the reason you may not find searched string in page source.
Click on search button :
driver.find_element_by_xpath("//span[text()='Search']/..").click()
Update 1 :
if you want to change the text then you would have to find the locator of that element. here is the sample code :
element = driver.find_element_by_id("fkljdslkjdfdks id locator")
driver.execute_script("arguments[0].innerText = 'your new string value';", element)
Related
I'm quite new to python and have written a script using selenium to scrape a website. I've tried everything but can't get the loop to cycle through pages. It currently just repeats the data on the first page 5 times. I want to scrape all the pages for 'BR1' any help would be great, currently the script below only scrapes the first page 5 times.
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
with open('rightmove.csv', 'w') as file:
file.write('PropertyCardcontent \n')
PATH = ("/usr/local/bin/chromedriver")
driver = webdriver.Chrome(PATH)
driver.get("https://www.rightmove.co.uk/house-prices.html")
print(driver.title)
elem = driver.find_element(By.NAME, 'searchLocation') # Find the search box
elem.send_keys('BR1' + Keys.RETURN)
try:
content = WebDriverWait(driver, 15).until(
EC.presence_of_element_located((By.ID,'content'))
)
finally:
time.sleep(3)
for p in range(5):
sold = content.find_elements(By.CLASS_NAME, 'sold-prices-content-wrapper ')
for solds in sold:
address = solds.find_elements(By.CLASS_NAME, 'sold-prices-content ')
for addresses in address:
result = addresses.find_elements(By.CLASS_NAME, 'results ')
for results in result:
card = results.find_elements(By.CLASS_NAME,'propertyCard')
for propertyCard in card:
header = propertyCard.find_elements(By.CLASS_NAME,'propertyCard-content')
for propertyCardcontent in header:
road = propertyCardcontent.find_elements(By.CLASS_NAME,'title')
for propertyCardcontent in header:
road = propertyCardcontent.find_elements(By.CLASS_NAME,'subTitle')
for subtitle in road:
bed = subtitle.find_elements(By.CLASS_NAME, 'propertyType')
with open('rightmove.csv', 'a') as file:
for i in range(len(result)):
file.write(header[i].text + '\n')
button = driver.find_element(By.XPATH, '//*[#id="content"]/div[2]/div[2]/div[4]/div[27]/div[3]/div')
button.click()
file.close()
time.sleep(3)
driver.quit()
Since the website link has page number on it, I recommend you put the base url as "https://www.rightmove.co.uk/house-prices/br1.html?page=1", and loop through the pages while changing the last index of the url with methods like format string.
One other thing, you don't need to implement all those for loops, you can simply assign each variable to its specific value since everything you need is inside an html block which is easy to navigate on it.
Update:
I'm sorry for being late, had unexpected stuff(...).
I've made some changes as I use Brave, so make sure you select your browser, Chrome I believe, the chromedriver(ver:102) stays the same (or depending your Chrome version).
I've also got the Price and Date and stored them in a tuple.
Every record is stored in a list[Title, propertyType, tupleof(Price_Date)]
At the end, it creates a csv and stores everything inside with a ";" as delimter.
You can if you prefer split the price and date for later use, up to you.
Note: This looping method only applies to websites in which the number of page is included within the URL. In this case, both the key and number of page is included in the URL.
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
import time
import random
import itertools
options = Options()
options.binary_location = r'C:\Program Files\BraveSoftware\Brave-Browser\Application\brave.exe'
driver = webdriver.Chrome(options = options, service = Service("chromedriver.exe"))
key_word = "BR1".lower()
base_url = f"https://www.rightmove.co.uk/house-prices/{key_word}.html?page=1"
driver.get(base_url)
#Number of pages
pages = driver.find_element(By.XPATH, '//span[#class="pagination-label"][2]').text
pages = int(pages.strip('of'))
WebDriverWait(driver, 15).until(
EC.presence_of_element_located((By.CLASS_NAME, 'results '))
)
data = []
pc = 0
for p in range(1,pages+1):
driver.get(f"https://www.rightmove.co.uk/house-prices/{key_word}.html?page={p}")
WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.XPATH, '//div//div[#class="propertyCard"]'))
)
propertyCards = driver.find_elements(By.XPATH, '//div//div[#class="propertyCard"]')
for propertyCard in propertyCards:
title = propertyCard.find_element(By.CLASS_NAME, 'title').text
propertyType = propertyCard.find_element(By.CLASS_NAME, 'propertyType').text
price_list = propertyCard.find_elements(By.CLASS_NAME, 'price')
date_list = propertyCard.find_elements(By.CLASS_NAME, 'date-sold')
data.append([title,propertyType])
for p, d in itertools.zip_longest(price_list, date_list , fillvalue = None):
try:
price = p.text
date = d.text
data[pc].append((price, date))
except Exception as e:
print(e)
pc+=1
time.sleep(random.randint(1,4))
print(data)
with open('rightmove.csv', 'w') as file:
header = "Title;propertyType;Price_Date\n"
file.write(header)
for record in data:
file.write("{};{};{}\n".format(record[0],record[1],record[2:]))
driver.quit()
You don't have to go down to dom elem by elem, you can just use xpath or class_name (if it's unique, otherwise it's better xpath or css-selector) and get the item you are looking for.
Anyway follow this:
import time
import selenium.webdriver as webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
driver = webdriver.Chrome("/usr/local/bin/chromedriver")
driver.get("https://www.rightmove.co.uk/house-prices.html")
# send query
query = "BR1"
search_bar = driver.find_element(By.XPATH, '//input[#class="searchBox ac_input"]')
search_bar.send_keys(query)
search_bar.send_keys(Keys.ENTER)
# wait to result been loaded
WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.CLASS_NAME, 'propertyCard'))
)
#get amount of pages
pages = driver.find_element(By.XPATH, '//span[#class="pagination-label"][2]').text
pages = int(pages.replace('of ', ''))
data = []
i = 1
while i <= pages:
WebDriverWait(driver, 10).until(
EC.element_to_be_clickable((By.XPATH, '//div[contains(text(), "Next")]'))
).click()
# wait page load result
WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.XPATH, '//div//div[#class="propertyCard"]'))
)
propertyCards = driver.find_elements(By.XPATH, '//div//div[#class="propertyCard"]')
# loop over result and store data
for propertyCard in propertyCards:
title = propertyCard.find_element(By.CLASS_NAME, 'title').text
propertyType = propertyCard.find_element(By.CLASS_NAME, 'propertyType').text
data.append((title, propertyType))
time.sleep(1)
i += 1
print("you reach the last page")
#get number of results
printf(data)
driver.close()
I use a list of tuple cause in your example you want store 2 item, if you want store more data you can use a dict and then convert into csv with Dictwriter directly. Enjoy.
I'm working on scraping the memes and all their comments from 9gag.
I used this code below but I am only getting few extra comments.
actions = ActionChains(driver)
link = driver.find_element(By.XPATH, "//button[#class='comment-list__load-more']")
actions.move_to_element(link).click(on_element=link).perform()
I would also like to access the subcomments under a comment by simulating click on view more replies.
From the html I found this XPATH element = driver.find_element(By.XPATH, "//div[#class='vue-recycle-scroller ready page-mode direction-vertical']")holds the comments section but I'm not sure how to iterate through each comment in this element and simulate these clicks.
This code should work directly provided the necessary libraries are present in case you wanna test it.
Please help me with these following tasks:
Getting all the comments from view all comments
Iterating through each comment section and clicking on view more replies to get all the subcomments
My Code
import time
from selenium.webdriver.common.by import By
from selenium.common.exceptions import NoSuchElementException
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
import undetected_chromedriver as uc
if __name__ == '__main__':
options = Options()
# options.headless = True
options.add_argument("start-maximized") # ensure window is full-screen
driver = uc.Chrome(service=Service(ChromeDriverManager().install()), options=options)
driver.get("https://9gag.com/gag/a5EAv9O")
prev_h = 0
for i in range(10):
height = driver.execute_script("""
function getActualHeight() {
return Math.max(
Math.max(document.body.scrollHeight, document.documentElement.scrollHeight),
Math.max(document.body.offsetHeight, document.documentElement.offsetHeight),
Math.max(document.body.clientHeight, document.documentElement.clientHeight)
);
}
return getActualHeight();
""")
driver.execute_script(f"window.scrollTo({prev_h},{prev_h + 200})")
time.sleep(1)
prev_h += 200
if prev_h >= height:
break
time.sleep(5)
title = driver.title[:-7]
try:
upvotes_count = \
driver.find_element(By.XPATH, "//meta[#property='og:description']").get_attribute("content").split(' ')[0]
comments_count = \
driver.find_element(By.XPATH, "//meta[#property='og:description']").get_attribute("content").split(' ')[3]
upvotes_count = int(upvotes_count) if len(upvotes_count) <= 3 else int("".join(upvotes_count.split(',')))
comments_count = int(comments_count) if len(comments_count) <= 3 else int("".join(comments_count.split(',')))
date_posted = driver.find_element(By.XPATH, "//p[#class='message']")
date_posted = date_posted.text.split("·")[1].strip()
# actions = ActionChains(driver)
# link = driver.find_element(By.XPATH, "//button[#class='comment-list__load-more']")
# actions.move_to_element(link).click(on_element=link).perform()
element = driver.find_element(By.XPATH,
"//div[#class='vue-recycle-scroller ready page-mode direction-vertical']")
print(element.text)
driver.quit()
except NoSuchElementException or Exception as err:
print(err)
Output
Edit:
I managed to make the code work better. It scrolls through the page until it sees all the comments. It also clicks on view more replies if there are subcomments.
But it's only able to read comments from middle to end. Maybe as the page is scrolled down, the initial comments are hidden dynamically. I do not know how to overcome this. And clicking on view more replies stops after some clicks and is throwing the error
selenium.common.exceptions.MoveTargetOutOfBoundsException: Message: move target out of bounds
Here's the updated code
import driver as driver
from selenium.webdriver.remote.webelement import WebElement
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains
import time
from selenium.webdriver.common.by import By
from selenium.common.exceptions import NoSuchElementException, ElementClickInterceptedException
from selenium.webdriver.support.wait import WebDriverWait
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
import undetected_chromedriver as uc
def scroll_page(scrl_hgt):
prev_h = 0
for i in range(10):
height = driver.execute_script("""
function getActualHeight() {
return Math.max(
Math.max(document.body.scrollHeight, document.documentElement.scrollHeight),
Math.max(document.body.offsetHeight, document.documentElement.offsetHeight),
Math.max(document.body.clientHeight, document.documentElement.clientHeight)
);
}
return getActualHeight();
""")
driver.execute_script(f"window.scrollTo({prev_h},{prev_h + scrl_hgt})")
time.sleep(1)
prev_h += scrl_hgt
if prev_h >= height:
break
if __name__ == '__main__':
options = Options()
# options.headless = True
driver = uc.Chrome(service=Service(ChromeDriverManager().install()), options=options)
driver.maximize_window()
driver.get("https://9gag.com/gag/a5EAv9O")
time.sleep(5)
# click on I accept cookies
actions = ActionChains(driver)
consent_button = driver.find_element(By.XPATH, '//*[#id="qc-cmp2-ui"]/div[2]/div/button[2]')
actions.move_to_element(consent_button).click().perform()
scroll_page(150)
time.sleep(2)
# click on fresh comments sectin
fresh_comments = driver.find_element(By.XPATH, '//*[#id="page"]/div[1]/section[2]/section/header/div/button[2]')
actions.move_to_element(fresh_comments).click(on_element=fresh_comments).perform()
time.sleep(5)
# getting meta data
title = driver.title[:-7]
upvotes_count = driver.find_element(By.XPATH, "//meta[#property='og:description']").get_attribute("content").split(' ')[0]
comments_count = driver.find_element(By.XPATH, "//meta[#property='og:description']").get_attribute("content").split(' ')[3]
upvotes_count = int(upvotes_count) if len(upvotes_count) <= 3 else int("".join(upvotes_count.split(',')))
comments_count = int(comments_count) if len(comments_count) <= 3 else int("".join(comments_count.split(',')))
date_posted = driver.find_element(By.XPATH, "//p[#class='message']")
date_posted = date_posted.text.split("·")[1].strip()
time.sleep(3)
# click on lood more comments button to load all the comments
load_more_comments = driver.find_element(By.XPATH, "//button[#class='comment-list__load-more']")
actions.move_to_element(load_more_comments).click(on_element=load_more_comments).perform()
scroll_page(500)
print([my_elem.text for my_elem in driver.find_elements(By.CSS_SELECTOR, "div.comment-list-item__text")])
comments = driver.find_elements(By.CSS_SELECTOR, "div.vue-recycle-scroller__item-view")
for item in comments:
html = item.get_attribute("innerHTML")
if "comment-list-item__text" in html:
print(item.find_element(By.CSS_SELECTOR, "div.comment-list-item__text").text)
elif "comment-list-item__deleted-text" in html:
print(item.find_element(By.CSS_SELECTOR, "div.comment-list-item__deleted-text").text)
# get sub comments
if "comment-list-item__replies" in html:
#item.find_element(By.CSS_SELECTOR, "div.comment-list-item__replies").click()
sub_comments = item.find_element(By.CSS_SELECTOR, "div.comment-list-item__replies")
actions.move_to_element(sub_comments).click(on_element=sub_comments).perform()
time.sleep(2)
driver.quit()
PS: My goal is to get every single comments and all their sub comments (whether they are text, image, gif, etc) in the order they appear and save them somewhere so that I should be able to recreate the comments section again.
To extract and print the comment texts you need to induce WebDriverWait for visibility_of_all_elements_located() and you can use the following Locator Strategies:
driver.get("https://9gag.com/gag/a5EAv9O")
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.CSS_SELECTOR, "button.comment-list__load-more"))).click()
print([my_elem.text for my_elem in driver.find_elements(By.CSS_SELECTOR, "div.comment-list-item__text")])
Console Output:
['Man, the battle of the cults is getting interesting now.', 'rent free in your head', 'Sorry saving all my money up for the Joe Biden Depends Multipack and the Karmella knee pads.', "It's basically a cult now.", "I'll take one. I'm not even American", '', 'that eagle looks familiar.', "Who doesn't want a trump card?"]
Note : You have to add the following imports :
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
What I'm trying to do is making nike product auto buyer the problem is after selecting size it doesn't let me click through selenium I even tried to click manually but nothing pops up this is my code where I try to click (not full code):
from selenium import webdriver
from selenium.common.exceptions import JavascriptException
from selenium.webdriver import ChromeOptions
import re
from bs4 import BeautifulSoup
import requests
import json
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
import os
user = os.environ['USERNAME']
snkrsurl = "https://www.nike.com/t/air-zoom-pegasus-38-womens-running-shoe-wide-gg8GBK/CW7358-500" #input("Please input your SNKRS url \n")
size = float(input("Please input size \n"))
options = ChromeOptions()
options.add_experimental_option('excludeSwitches',['enable-logging'])
options.add_experimental_option("useAutomationExtension", False)
options.add_experimental_option("detach",True)
options.add_argument("--disable-notifications")
chrome = webdriver.Chrome(options=options)
if "https://" in snkrsurl:
pass
elif "http://" in snkrsurl:
pass
else:
snkrsurl = "http://"+snkrsurl
chrome.get(snkrsurl)
with requests.Session() as session:
soup = BeautifulSoup(session.get(snkrsurl).text, features="lxml")
script = soup.find("script", string=re.compile('INITIAL_REDUX_STATE')).string
redux = json.loads(script[script.find('{'):-1])
products = redux["Threads"]["products"]
wait = WebDriverWait(chrome, 15)
def step1(i,v):
for key, product in products.items():
if float(product["skus"][i]["nikeSize"]) == v:
print("Found")
if v.is_integer():
wait.until(EC.element_to_be_clickable((By.XPATH, '//*[#id="gen-nav-footer"]/nav/button'))).click()
wait.until(EC.element_to_be_clickable((By.XPATH, "//*[text()='{}']".format(int(v))))).click()
chrome.execute_script("window.scroll(0,609)")
wait.until(EC.element_to_be_clickable((By.XPATH, '//*[text()="Add to Bag"]'))).click()
break
else:
wait.until(EC.element_to_be_clickable((By.XPATH, '//*[#id="gen-nav-footer"]/nav/button'))).click()
wait.until(EC.element_to_be_clickable((By.XPATH, "//*[text()='{}']".format(v)))).click()
e = chrome.find_element_by_css_selector("#floating-atc-wrapper > div > button.ncss-btn-primary-dark.btn-lg.add-to-cart-btn")
chrome.execute_script("arguments[0].scrollIntoView(true);")
e.click()
break
else:
pass
for i,v in products.items():
global length
length = len(v['skus'])
break
for i in range(length):
length -=1
step1(length,size)
I use window.scroll to go to that element because if I don't it throws error saying element is not interactable and yes checkout is being only clickable from real chrome.
Thanks
i try to scrape the contact data from companies from this website:
https://de.statista.com/companydb/suche?idCountry=276&idBranch=0&revenueFrom=-1000000000000000000&revenueTo=1000000000000000000&employeesFrom=0&employeesTo=100000000&sortMethod=revenueDesc&p=4
I can do this with the following Code:
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
import pandas as pd
import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
company_list= [] #create empty list
driver = webdriver.Chrome('/Users/rieder/Anaconda3/chromedriver_win32/chromedriver.exe') #define driver
driver.get('https://de.statista.com/companydb/suche?idCountry=276&idBranch=0&revenueFrom=-1000000000000000000&revenueTo=1000000000000000000&employeesFrom=0&employeesTo=100000000&sortMethod=revenueDesc&p=1') # open Website
driver.find_element_by_id("cookiesNotificationConfirm").click(); #accept cookies
driver.find_element_by_xpath("//*[#id='content']/section[3]/div/div/form/div/div[2]/div[2]/table/tr[2]/td[1]/a").click(); #click on the first company namelink
contact_data = WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.XPATH, "/html/body/div[3]/div[4]/section[6]/div/div[2]/div[2]/div/div"))) #get the contactdata from the company you chose before
for cn in contact_data:
company_list.append(cn.text) # this stores the text in the list
driver.back() #navigate to previous site
time.sleep(5) #wait for the pop-up window to appear
driver.find_element_by_xpath("/html/body/div[15]/div[3]/div[3]/div[1]/button[1]").click(), #deny the websites popup
time.sleep(5) #wait for the popup to vanish
driver.find_element_by_xpath("//*[#id='content']/section[3]/div/div/form/div/div[2]/div[2]/table/tr[3]/td[1]/a").click(); #click on the next company namelink
contact_data2 = WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.XPATH, "/html/body/div[3]/div[4]/section[6]/div/div[2]/div[2]/div/div"))) #get the contactdata from the company you chose before
for cn in contact_data2:
company_list.append(cn.text) # this stores the text in the list
print(company_list) #show the list
My Output is this:
['GUTex GmbH\nGerhard-Unland-Str. 1\n26683\nSaterland\nDeutschland', 'Robert Bosch GmbH\nRobert-Bosch-Platz 1\n70839\nGerlingen\nDeutschland']
Problem:
I want, that my code does this to the whole list on page 1 and then goes on on the next page and do it again. This shall go on until I have for example 100 adresses in the list. I would do this with a "while loop" but my xpaths for finding the adress are too specified, so it would always loop the same companies.
Thanks a lot inbefore
Try below code for one page data extract. Update the code for iterating over the next page records.
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
company_list= [] #create empty list
driver = webdriver.Chrome() #define driver
driver.get('https://de.statista.com/companydb/suche?idCountry=276&idBranch=0&revenueFrom=-1000000000000000000&revenueTo=1000000000000000000&employeesFrom=0&employeesTo=100000000&sortMethod=revenueDesc&p=1') # open Website
if len(driver.find_elements_by_id("cookiesNotificationConfirm")) > 0:
driver.find_element_by_id("cookiesNotificationConfirm").click(); # accept cookies
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH, '//table[#class="zebraTable zebraTable--companies"]//td[1]')))
elementsSize = len(driver.find_elements_by_xpath('//table[#class="zebraTable zebraTable--companies"]//td[1]'))
# To iterate over the company list and click on the company name then capture the address on navigated page
# come back to previous page and repeat the same.
for i in range(elementsSize):
WebDriverWait(driver, 20).until(
EC.element_to_be_clickable((By.XPATH, '//table[#class="zebraTable zebraTable--companies"]//td[1]')))
elements = driver.find_elements_by_xpath('//table[#class="zebraTable zebraTable--companies"]//td[1]/a')
company_name = elements[i].text
elements[i].click() # click on the first company namelink
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH,
'//*[#id="contactInformation"]//div[#class="companyContactBox"]'))) # get the contactdata from the company you chose before
contact_data = driver.execute_script("return document.getElementsByClassName('companyContactBox')[0].innerText")
# print(contact_data)
company_list.append(company_name + " : " + contact_data)
driver.back() # navigate to previous site
print(company_list)
Thanks to Dilip Meghwals comment above i could finish my Code:
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
import pandas as pd
import time
company_list= [] #create empty list
count = 25
chrome_options = webdriver.ChromeOptions()
prefs = {"profile.default_content_setting_values.notifications" : 2}
chrome_options.add_experimental_option("prefs",prefs)
driver = webdriver.Chrome('/Users/rieder/Anaconda3/chromedriver_win32/chromedriver.exe', chrome_options=chrome_options) #define driver
driver.get('https://de.statista.com/companydb/suche?idCountry=276&idBranch=0&revenueFrom=-1000000000000000000&revenueTo=1000000000000000000&employeesFrom=0&employeesTo=100000000&sortMethod=revenueDesc&p=1') # open Website
if len(driver.find_elements_by_id("cookiesNotificationConfirm")) > 0:
driver.find_element_by_id("cookiesNotificationConfirm").click(); # accept cookies
while len(company_list) < 1000:
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH, '//table[#class="zebraTable zebraTable--companies"]//td[1]')))
elementsSize = len(driver.find_elements_by_xpath('//table[#class="zebraTable zebraTable--companies"]//td[1]'))
# To iterate over the company list and click on the company name then capture the address on navigated page
# come back to previous page and repeat the same.
for i in range(elementsSize):
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH, '//table[#class="zebraTable zebraTable--companies"]//td[1]')))
elements = driver.find_elements_by_xpath('//table[#class="zebraTable zebraTable--companies"]//td[1]/a')
company_name = elements[i].text
elements[i].click() # click on the first company namelink
WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH,'//*[#id="contactInformation"]//div[#class="companyContactBox"]'))) # get the contactdata from the company you chose before
contact_data = driver.execute_script("return document.getElementsByClassName('companyContactBox')[0].innerText")
# print(contact_data)
company_list.append(contact_data)
driver.back() # navigate to previous site
time.sleep(5)
driver.find_element_by_xpath("//*[#id='content']/section[3]/div/div/form/div/div[2]/div[2]/div[2]/div/button[2]").click();
company_list = [w.replace('\n', ', ') for w in company_list]
print(company_list)
df_company_name = pd.DataFrame(company_list, columns =['Name'])
df_company_name.to_excel("company_name.xlsx")
I have written a script in python to extract and paste 400-500 lines of text from one browser to another. I am using send_keys() to put the text content into the text area. It is writing line by line (2 lines / second) which is resulting in a few minutes to complete the operation. Is there any other method in Selenium to write faster (like how we paste manually in 1 second)?
My code
<code>
import time
import re
import csv
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from selenium.common.exceptions import ElementNotVisibleException
from selenium.webdriver.common.keys import Keys
def init_driver(uname,pwd):
driver = webdriver.Chrome()
driver.wait = WebDriverWait(driver, 5)
driver.get("https://ops.stg1.xxxxxyyyxxxx.com/login.jsp")
box = driver.wait.until(EC.presence_of_element_located((By.NAME, "j_username")))
box.send_keys(uname)
box = driver.wait.until(EC.presence_of_element_located((By.NAME, "j_password")))
box.send_keys(pwd)
button = driver.wait.until(EC.element_to_be_clickable((By.NAME, "login")))
button.click()
return driver
def copy():
with open("Tag_input.txt") as f:
for line in f:
url = line.strip()
driver.get(url)
k=re.findall('\=(\d+)',url)
print(k[0])
a=k[0]
driver.wait = WebDriverWait(driver, 10)
time.sleep(10)
PC = driver.find_elements_by_xpath("//textarea[#name='messagingMap.PRIMARY_CONTENT.message']")
PC.send_keys(Keys.CONTROL, "a")
PC.send_keys(Keys.CONTROL, "c")
print("Copied Primary content !!")
for tag in PC:
varPC = tag.text
url1 = "http://jona.ca/blog/unclosed-tag-finder"
driver.get(url1)
driver.wait = WebDriverWait(driver, 10)
time.sleep(10)
text_area = driver.find_element_by_id("unclosed-tag-finder-input")
text_area.send_keys(Keys.CONTROL, "v")
button = driver.find_element_by_xpath("//input[#value='Submit']")
button.click()
result = driver.find_element_by_xpath("//pre[#id='unclosed-tag-finder-results']")
res_list = list(result)
print(res_list)
op = result.text
print(op)
writer = csv.writer(open('Tag_OP.csv','a+'))
z = zip(k,result)
print(z)
writer.writerows(k)
writer.writerows(result)
k = k.pop()
print("List cleared",k[0])
driver.wait = WebDriverWait(driver, 10)
time.sleep(10)
return driver
if __name__ == "__main__":
driver = init_driver("abdul.salam#xxxyyxxx.com","xxyyxx")
copy()
time.sleep(25)
driver.quit()
</code>
You might try using Ctrl+A to select the text, Ctrl+C to copy it, move to new browser Ctrl+A to select all text in your target field (so that you'll replace it), Ctrl+V to paste. I could imagine that it may be faster, but I haven't done any benchmarking myself.
This question popped right up when I did a search. It has more details, but, for instance, your paste would look like this:
driver.find_element_by_id("unclosed-tag-finder-input").sendKeys(Keys.chord(Keys.CONTROL,"v"));