I want to scrape all tweets from twitter using Selenium. So, for this I want to go at bottom of the page.I tried a lot but it shows "Back to top " as shown in image.
How can I go at the bottom of the page/disappear "Back to top" using Selenium or How can I scrape all the tweets, if applying any other approach?
import pandas as pd
import selenium
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
driver=webdriver.Firefox(executable_path="/home/piyush/geckodriver")
url="https://twitter.com/narendramodi"
driver.get(url)
time.sleep(6)
lastHeight = driver.execute_script("return document.body.scrollHeight")
while True:
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
time.sleep(6)
newHeight = driver.execute_script("return document.body.scrollHeight")
if newHeight == lastHeight:
break
lastHeight = newHeight
soup=BeautifulSoup(driver.page_source.encode("utf-8"),"html.parser")
tweet=[p.text for p in soup.find_all("p",class_="tweet-text")]
Here is image of inspect element of "Back-to-top"
Here is the output image
Just briefly looking at twitter, it appears that the content is generated on scrolling, meaning you need to scrape and parse the data as you scroll rather than after.
I would suggest moving
soup = BeautifulSoup(driver.page_source.encode("utf-8"),"html.parser")
tweet = [p.text for p in soup.find_all("p",class_="tweet-text")]
into your while loop after the scroll:
while True:
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
###
soup = BeautifulSoup(driver.page_source.encode("utf-8"),"html.parser")
tweet = [p.text for p in soup.find_all("p",class_="tweet-text")]
###
time.sleep(6)
newHeight = driver.execute_script("return document.body.scrollHeight")
if newHeight == lastHeight:
break
lastHeight = newHeight
If this doesn't work you are probably being fingerprinted and labeled as a bot by Twitter.
Related
I am not getting all links there are 403 links in these page I am getting only 68 links I also used the scroll down method they move to end of page but not give all links is any thing I am doing wrong kindly guide us these is page link https://www.ocado.com/search?entry=frozen
from selenium import webdriver
import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support.select import Select
from selenium.webdriver.support import expected_conditions as EC
import pandas as pd
url='https://www.ocado.com/search?entry=frozen'
PATH="C:\Program Files (x86)\chromedriver.exe"
driver =webdriver.Chrome(PATH)
driver.get(url)
SCROLL_PAUSE_TIME = 50
last_height = driver.execute_script("return document.body.scrollHeight")
while True:
# Scroll down to bottom
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
# Wait to load page
time.sleep(SCROLL_PAUSE_TIME)
# Calculate new scroll height and compare with last scroll height
new_height = driver.execute_script("return document.body.scrollHeight")
if new_height == last_height:
break
last_height = new_height
t=driver.find_elements(By.XPATH, "//div[#class='fop-contentWrapper']")
for l in t:
links= l.find_element(By.XPATH, ".//a[starts-with(#href, '/products')]").get_attribute("href")
print(links)
With this should be enough:
# Needed libs
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
import time
# We create the driver
driver = webdriver.Chrome()
# We maximize the window, because if not the page will be different
driver.maximize_window()
# We navigate to the url
url='https://www.ocado.com/search?entry=frozen'
driver.get(url)
# We click on acceptbutton cookies pop up
WebDriverWait(driver, 20).until(EC.presence_of_element_located((By.XPATH, "//button[#id='onetrust-accept-btn-handler']"))).click()
# We take the show_more_button, which is at the bottom
show_more_button = driver.find_element(By.XPATH, "//button[text()='Show more']")
# We take latest product which contain the info we want, that product will be more or less in the middle of the page because it is the latest one which is loaded
last_element_with_link = WebDriverWait(driver, 20).until(EC.presence_of_element_located((By.XPATH, "//div[#class='fop-contentWrapper']/a[last()]")))
# If the location of the show_more_button - last_element_with_link location is bigger than 500 px means we did not arrive till the end of list
while show_more_button.location['y'] - last_element_with_link.location['y'] > 500:
# We get the location of the new last_element_with_link because we should have more elements
last_element_with_link = WebDriverWait(driver, 20).until(EC.presence_of_element_located((By.XPATH, "//div[#class='fop-contentWrapper']/a[last()]")))
# We do till we arrive to the position of this new last_element_with_link
print(f"Scroll to px: {last_element_with_link.location['y']}")
driver.execute_script(f"window.scrollTo(0, {last_element_with_link.location['y']})")
# small sleep to give time to the page
time.sleep(0.1)
# Here we now we are at the botton, so we can take the links
list_of_elements = WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.XPATH, "//div[#class='fop-contentWrapper']/a")))
print(len(list_of_elements))
# For each element we print the url
for element in list_of_elements:
print(element.get_attribute('href'))
Actually there are 403 products per page
I would like to scroll until the end of a page like : https://fr.finance.yahoo.com/quote/GM/history?period1=1290038400&period2=1612742400&interval=1d&filter=history&frequency=1d&includeAdjustedClose=true
The fact is using this :
# # Get scroll height after first time page load
last_height = driver.execute_script("return document.body.scrollHeight")
while True:
# Scroll down to bottom
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
# Wait to load page
time.sleep(2)()
# Calculate new scroll height and compare with last scroll height
new_height = driver.execute_script("return document.body.scrollHeight")
if new_height == last_height:
break
last_height = new_height
does not work. yes it should work for pages with infinite loads but doesn't work for yahoo finance, which has a finite number of loads but the condition should break when it reachs the end. So I'm quite confuse at the moment.
We could also use :
while driver.find_element_by_tag_name('tfoot'):
# Scroll down three times to load the table
for i in range(0, 3):
driver.execute_script("window.scrollBy(0, 5000)")
time.sleep(2)
but it sometimes blocks at a certain loads.
What would be the best way to do this ?
Requires pip install undetected-chromedriver, but will get the job done.
It's just my webdriver of choice, you can also do the exact same with normal selenium.
from time import sleep as s
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
import undetected_chromedriver as uc
options = uc.ChromeOptions()
options.headless = False
driver = uc.Chrome(options=options)
driver.get('https://fr.finance.yahoo.com/quote/GM/history?period1=1290038400&period2=1612742400&interval=1d&filter=history&frequency=1d&includeAdjustedClose=true')
WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.CSS_SELECTOR, '#consent-page > div > div > div > div.wizard-body > div.actions.couple > form > button'))).click() #clicks the cookie warning or whatever
last_scroll_pos=0
while True:
WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.CSS_SELECTOR, 'body'))).send_keys(Keys.DOWN)
s(.01)
current_scroll_pos=str(driver.execute_script('return window.pageYOffset;'))
if current_scroll_pos == last_scroll_pos:
print('scrolling is finished')
break
last_scroll_pos=current_scroll_pos
I'm trying to scrape a website (https://harleytherapy.com/therapists?page=1) that looks like it's been generated by Javascript and the element I'm trying to scrape (the lu with id="downshift-7-menu") doesn't appear on the "Page source" but only after I click on "Inspect element".
I tried to find a solution here and so far this the code I was able to come up with (a combination of Selenium + Beautiful soup)
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
import time
url = "https://harleytherapy.com/therapists?page=1"
options = webdriver.ChromeOptions()
options.add_argument('headless')
capa = DesiredCapabilities.CHROME
capa["pageLoadStrategy"] = "none"
driver = webdriver.Chrome(chrome_options=options, desired_capabilities=capa)
driver.set_window_size(1440,900)
driver.get(url)
time.sleep(15)
plain_text = driver.page_source
soup = BeautifulSoup(plain_text, 'html')
therapist_menu_id = "downshift-7-menu"
print(soup.find(id=therapist_menu_id))
I thought that allowing Selenium to wait for 15 seconds would make sure that all elements are loaded but I still can't find any element with id downshift-7-menu in the soup. Do you guys know what's wrong with my code?
The element with ID downshift-7-menu is loaded only after opening the THERAPIST dropdown menu, you can do it by scrolling it into view to load it and then clicking on it. You should also consider replacing sleep with explicit wait
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
wait = WebDriverWait(driver, 15)
# scroll the dropdown into view to load it
side_menu = wait.until(EC.visibility_of_element_located((By.CLASS_NAME, 'inner-a377b5')))
last_height = driver.execute_script("return arguments[0].scrollHeight", side_menu)
while True:
driver.execute_script("arguments[0].scrollTo(0, arguments[0].scrollHeight);", side_menu)
new_height = driver.execute_script("return arguments[0].scrollHeight", side_menu)
if new_height == last_height:
break
last_height = new_height
# open the menu
wait.until(EC.visibility_of_element_located((By.ID, 'downshift-7-input'))).click()
# wait for the option to load
therapist_menu_id = 'downshift-7-menu'
wait.until(EC.presence_of_element_located((By.ID, therapist_menu_id)))
print(soup.find(id=therapist_menu_id))
I am trying to scrape the connection names with selenium Python. But it only scrolls to one page and loads result of one page. Is there any way that I can get the full page of results with selenium? I am attaching the code for reference.
import time
import requests
from bs4 import BeautifulSoup as bt
import pandas as pd
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.chrome.options import Options
from parsel import Selector
import urllib3
options=webdriver.ChromeOptions()
prefs={"profile.default_content_setting_values.notifications":2}
options.add_experimental_option("prefs",prefs)
options.add_argument("start-maximized")
options.add_argument("--disable-notifications")
from webdriver_manager.chrome import ChromeDriverManager
email=input("Please enter your linkedin email id: ")
password=input("Please enter your linkedin password: ")
driver=webdriver.Chrome(options=options,executable_path="D:\chromedriver.exe")
driver.get("http://www.linkedin.com/login/")
time.sleep(4)
ele=driver.find_element_by_name("session_key")
#print(ele.is_displayed())
pwd=driver.find_element_by_name("session_password")
ele.send_keys(str(email))
pwd.send_keys(str(password))
driver.find_element_by_xpath("/html/body/div/main/div[2]/form/div[3]/button").click()
time.sleep(3)
#logging in
driver.get("https://www.linkedin.com/mynetwork/")
driver.get("https://www.linkedin.com/mynetwork/invite-connect/connections/")
def scroll(driver, timeout):
scroll_pause_time = timeout
last_height = driver.execute_script("return document.body.scrollHeight")
while True:
# Scroll down to bottom
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
# Wait to load page
time.sleep(scroll_pause_time)
# Calculate new scroll height and compare with last scroll height
new_height = driver.execute_script("return document.body.scrollHeight")
if new_height == last_height:
# If heights are the same it will exit the function
break
last_height = new_height
scroll(driver, 2)
My code is good for the most part
I currently get all the titles from a youtube page + do a scroll.
How would I get the number of views?
Would CSS or xPath work?
import time
from selenium import webdriver
from bs4 import BeautifulSoup
import requests
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from webdriver_manager.chrome import ChromeDriverManager
options = Options()
driver = webdriver.Chrome(ChromeDriverManager().install())
url='https://www.youtube.com/user/OakDice/videos'
driver.get(url)
last_height = driver.execute_script("return document.documentElement.scrollHeight")
SCROLL_PAUSE_TIME = 2
while True:
# Scroll down to bottom
time.sleep(2)
driver.execute_script("window.scrollTo(0, arguments[0]);", last_height)
# Wait to load page
time.sleep(SCROLL_PAUSE_TIME)
# Calculate new scroll height and compare with last scroll height
new_height = driver.execute_script("return document.documentElement.scrollHeight")
if new_height == last_height:
break
last_height = new_height
content=driver.page_source.encode('utf-8').strip()
soup=BeautifulSoup(content,'lxml')
titles = soup.findAll('a', id='video-title')
for title in titles:
print(title.text)
It would probably be more robust to use the YouTube API to get JSON data about the videos. You can get a list of all public videos uploaded by a given user (see for instance YouTube API to fetch all videos on a channel), and then you use the videos API to get the statistics for each video in the playlist and get the view count from statistics.viewCount.
I would loop through all the videos (parent tag ytd-grid-video-renderer)
and then pluck out the titles & counts from there.
Something like:
allvideos = driver.find_element_by_tag_name('driytd-grid-video-renderer')
for video in allvideos:
title = video.find_element_by_id('video-title')
count = video.find_element_by_xpath('//*[#id='metadata-line']/span')
print (title, count)
I don't have a beautiful soup solution for you, as selenium will do most of the work for you.
And a word of caution on using driver.page_source, it doesn't really return a full snapshot of the DOM, so it probably isn't doing what you think it's doing.