As to say this code works but problem that i am facing that only one url it scrape the data afterward it through an error as show below in figure help me out from this . it print only one link after it through session not created error
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import pandas as pd
import time
url = ["https://www.skechers.com/women/shoes/ultra-flex---twilight-twinkle/149173.html",
"https://www.skechers.com/women/shoes/ultra-flex---statements/12841.html",
"https://www.skechers.com/women/shoes/ultra-flex/12843.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-hyper-burst---extreme-outlook/124580.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-hyper-burst---lunar-mars/124577.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-hyper-burst/124575.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-stability---coco-jazz/124603.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-stability---magnificent-glow/124602.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-joy/124191.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-joy---paradise/15601.html",
"https://www.skechers.com/women/shoes/skech-air-element-2.0---vivid-blush/149408.html",
"https://www.skechers.com/women/shoes/skech-air-element-2.0---kaleidoscope-splash/149134.html",
"https://www.skechers.com/women/shoes/skech-air-element-2.0/149062.html",
"https://www.skechers.com/women/shoes/skech-air-element-2.0---rising-gaze/149611.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-air---twirl/124073.html",
"https://www.skechers.com/women/shoes/gowalk-air---whirl/124074.html",
"https://www.skechers.com/women/shoes/skechers-arch-fit-refine---her-best/104092.html",
"https://www.skechers.com/women/shoes/skechers-arch-fit-refine/104090.html",
"https://www.skechers.com/women/shoes/glide-step---stepping-up/104086.html",
"https://www.skechers.com/women/shoes/relaxed-fit-empire-dlux---sharp-witted/149007.html",
"https://www.skechers.com/women/shoes/relaxed-fit-empire-dlux---paradise-sky/149274.html",
"https://www.skechers.com/women/shoes/skechers-gorun-smart/128230.html"]
for endpoint in url:
options = webdriver.ChromeOptions()
options.add_experimental_option("excludeSwitches", ['enable-automation'])
options.add_argument('--disable-blink-features=AutomationControlled')
options.add_argument(
"user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36")
options.add_argument("--remote-debugging-port=9222")
driver = webdriver.Chrome('F:/chromedriver.exe',options=options)
driver.get(endpoint)
time.sleep(5)
image= None
page_Source = driver.page_source
soup = BeautifulSoup(page_Source, 'html.parser')
content= soup.find_all('div',class_='c-product-description-features s-product-description-features row')
pid=soup.find('span',class_='product-id').text
links = soup.find_all('img', srcset=True)
for link in links:
img= link['srcset']
alt=link['alt']
print(pid ,img,alt)
Advertisement
Answer
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import time
url = ["https://www.skechers.com/women/shoes/ultra-flex/12843.html",
"https://www.skechers.com/women/shoes/ultra-flex---twilight-twinkle/149173.html",
"https://www.skechers.com/women/shoes/ultra-flex---statements/12841.html",
"https://www.skechers.com/women/shoes/ultra-flex/12843.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-hyper-burst---extreme-outlook/124580.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-hyper-burst---lunar-mars/124577.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-hyper-burst/124575.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-stability---coco-jazz/124603.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-stability---magnificent-glow/124602.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-joy/124191.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-joy---paradise/15601.html",
"https://www.skechers.com/women/shoes/skech-air-element-2.0---vivid-blush/149408.html",
"https://www.skechers.com/women/shoes/skech-air-element-2.0---kaleidoscope-splash/149134.html",
"https://www.skechers.com/women/shoes/skech-air-element-2.0/149062.html",
"https://www.skechers.com/women/shoes/skech-air-element-2.0---rising-gaze/149611.html",
"https://www.skechers.com/women/shoes/skechers-gowalk-air---twirl/124073.html",
"https://www.skechers.com/women/shoes/gowalk-air---whirl/124074.html",
"https://www.skechers.com/women/shoes/skechers-arch-fit-refine---her-best/104092.html",
"https://www.skechers.com/women/shoes/skechers-arch-fit-refine/104090.html",
"https://www.skechers.com/women/shoes/glide-step---stepping-up/104086.html",
"https://www.skechers.com/women/shoes/relaxed-fit-empire-dlux---sharp-witted/149007.html",
"https://www.skechers.com/women/shoes/relaxed-fit-empire-dlux---paradise-sky/149274.html",
"https://www.skechers.com/women/shoes/skechers-gorun-smart/128230.html"]
count=0
for endpoint in url:
print(count)
count+=1
options = webdriver.ChromeOptions()
options.add_experimental_option("excludeSwitches", ['enable-automation'])
options.add_argument('--disable-blink-features=AutomationControlled')
options.add_argument(
"user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36")
#options.add_argument("--remote-debugging-port=9222")
driver = webdriver.Chrome('./chromedriver.exe', options=options)
driver.get(endpoint)
ISSUE:
The issue is with the remote debugging port, you already used it with one instance ,
Solution:
remove that
