How can we naviagte to a web page, scrape data, move to the next page, and do it again?

Question

I made two attempts to get my code to navigate to a web page, import data from a table into a data frame, then move to the next page and do the same thing again. Below is some sample code that I tested. Now I am stuck; not sure how to proceed.

# first attempt
import requests
from bs4 import BeautifulSoup
import pandas as pd
from selenium import webdriver
from time import sleep

lst = []
url = "https://www.nasdaq.com/market-activity/stocks/screener"

for numb in (1, 10):
    url = "https://www.nasdaq.com/market-activity/stocks/screener"
    r = requests.get(url)
    html = r.text
    soup = BeautifulSoup(html, "html.parser")
    table = soup.find_all('table')
    df = pd.DataFrame(table)
    lst.append(df)
    
    def get_cpf():
        driver = webdriver.Chrome("C:/Utility/chromedriver.exe")
        driver.get(url)
        driver.find_element_by_class('pagination__page" data-page="'' +  numb + ''').click()
        sleep(10)
        text=driver.find_element_by_id('texto_cpf').text
        print(text)
    get_cpf()
    get_cpf.click
    

### second attempt
#import BeautifulSoup
from bs4 import BeautifulSoup
import pandas as pd
import requests
from selenium import webdriver
from time import sleep

lst = []

for numb in (1, 10):
    r=requests.get('https://www.nasdaq.com/market-activity/stocks/screener')
    data = r.text
    soup = BeautifulSoup(data, "html.parser")
    table = soup.find( "table", {"class":"nasdaq-screener__table"} )
    
    for row in table.findAll("tr"):
        for cell in row("td"):
            data = cell.get_text().strip()
            df = pd.DataFrame(data)
            lst.append(df)
            
    def get_cpf():
        driver = webdriver.Chrome("C:/Utility/chromedriver.exe")
        driver.get(url)
        driver.find_element_by_class('pagination__page" data-page="'' +  numb + ''').click()
        sleep(10)
        text=driver.find_element_by_id('texto_cpf').text
        print(text)
    get_cpf()
    get_cpf.click


### third attempt
from bs4 import BeautifulSoup
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 import webdriver
import time
import requests
import pandas as pd

lst = []

url="https://www.nasdaq.com/market-activity/stocks/screener"
driver = webdriver.Chrome("C:/Utility/chromedriver.exe")
wait = WebDriverWait(driver, 10)
driver.get(url)
wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"#_evh-ric-c"))).click()
for pages in range(1,9):
    try:
        print(pages)
        r = requests.get(url)
        html = r.text
        soup = BeautifulSoup(html, "html.parser")
        table = soup.find_all('table')
        df = pd.DataFrame(table)
        lst.append(df)
        wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"button.pagination__next"))).click()
        time.sleep(1)
    except:
        break

Here is a screen shot of the HTML behind the table that I am trying to scrape.

So, on the first page, I want to scrape everything from:

AAPL    Apple Inc. Common Stock $127.79 6.53    5.385%  2,215,538,678,600

To:

ASML    ASML Holding N.V. New York Registry Shares  $583.55 16.46   2.903%  243,056,764,541

Then, move to page 2, do the same, move to page 3, do the same, etc., etc., etc. I'm not sure if this is doable using only BeautifulSoup. Or maybe I need Selenium, for the button click event. I'm open to doing what is easiest here. Thanks!

Answer 1

Not going to deal with the API since Nuran just going to go with what the user asked

Here's an example of going through the first 10 pages. First we remove the notification. Then wait for the next button to be interactable and click it.

wait = WebDriverWait(driver, 10)
driver.get("https://www.nasdaq.com/market-activity/stocks/screener")
wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"#_evh-ric-c"))).click()
#Currently you start on the 1st page and say we want to click 9 times for the 10th page
for pages in range(1,10):
    try:
        print(pages)
        #Get your data from this page
        wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"button.pagination__next"))).click()
        #This is just here to slow everything so it may be removeable. 
        time.sleep(5)
    except:
        break

Import

from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait 
from selenium.webdriver.support import expected_conditions as EC

You can do something like this

html=driver.page_source
soup=BeautifulSoup(html,'html.parser')
div=soup.select_one("table.nasdaq-screener__table")
table=pd.read_html(str(div))
print(table[0])

Answer 2

Attention Please, you don't need to use selenium for such task as it's going to slow down your process at all.

In real world scenarios, we only use selenium to bypass browser detection, Then we pass cookies to whatever HTTP module for continue the operation.

Regarding your task, I noticed there's an API which actually feed the HTML source.

Here's a quick call for it.

import pandas as pd
import requests


def main(url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:86.0) Gecko/20100101 Firefox/86.0"
    }

    params = {
        'tableonly': 'true',
        'limit': 1000
    }
    r = requests.get(
        'https://api.nasdaq.com/api/screener/stocks', params=params, headers=headers)
    goal = pd.DataFrame(r.json()['data']['table']['rows'])
    print(goal)

    goal.to_csv('data.csv', index=False)


if __name__ == "__main__":
    main('https://api.nasdaq.com/api/screener/stocks')

Note that each page contain 25 ticker. Within my code, I've fetched 1000/ 25 = 40 Pages.

You don't need to loop over the pages here. as you can just interact with increasing the limit!

But in case if you would like to use for loop, so you have to loop over the following

And keep up the offset.

https://api.nasdaq.com/api/screener/stocks?tableonly=true&limit=25&offset=0