لنکڈ ان ڈیٹا کو ازگر کے ساتھ کھرچنے کے لئے رہنمائی کریں

pip install requests
pip install lxml

import requests
from lxml import html
import csv
import random

url = 'https link'

user_agents = [
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
    'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
]

proxies = {
    'http': random.choice(proxies),
    'https': random.choice(proxies)
}

headers = {
    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
    'accept-language': 'en-IN,en;q=0.9',
    'dnt': '1',
    'sec-ch-ua': '"Not/A)Brand";v="8", "Chromium";v="126", "Google Chrome";v="126"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Linux"',
    'sec-fetch-dest': 'document',
    'sec-fetch-mode': 'navigate',
    'sec-fetch-site': 'none',
    'sec-fetch-user': '?1',
    'upgrade-insecure-requests': '1',
}

job_details = []

# Set random User-Agent and proxy with IP authorization method
headers['user-agent'] = random.choice(user_agents)
proxies = {
    'http': IP:PORT,
    'https': IP:PORT
}

# Send an HTTP GET request to the URL
response = requests.get(url=url, headers=headers, proxies=proxies)
parser = html.fromstring(response.content)

# Extract job details from the HTML content
for job in parser.xpath('//ul[@class="jobs-search__results-list"]/li'):
    title = ''.join(job.xpath('.//div/a/span/text()')).strip()
    company = ''.join(job.xpath('.//div/div[2]/h4/a/text()')).strip()
    location = ''.join(job.xpath('.//div/div[2]/div/span/text()')).strip()
    job_url = job.xpath('.//div/a/@href')[0]
    
    job_detail = {
        'title': title,
        'company': company,
        'location': location,
        'job_url': job_url
    }
    job_details.append(job_detail)

with open('linkedin_jobs.csv', 'w', newline='', encoding='utf-8') as csvfile:
    fieldnames = ['title', 'company', 'location', 'job_url']
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
    writer.writeheader()
    for job_detail in job_details:
        writer.writerow(job_detail)

from selenium.webdriver.chrome.options import Options
from seleniumwire import webdriver as wiredriver
from selenium.webdriver.common.by import By
import csv

# Specify the proxy server address with username and password
proxy_address = ""
proxy_username = ""
proxy_password = ""

# Set up Chrome options with the proxy and authentication
chrome_options = Options()
chrome_options.add_argument(f'--proxy-server={proxy_address}')
chrome_options.add_argument(f'--proxy-auth={proxy_username}:{proxy_password}')

# Create a WebDriver instance with selenium-wire
driver = wiredriver.Chrome(options=chrome_options)

url = 'https link'

# Perform your Selenium automation with the enhanced capabilities of selenium-wire
driver.get(url)

job_details = []

all_elements = driver.find_elements(By.XPATH,
                                   '//*[@id="main-content"]/section/ul/li')

for i in all_elements:
   title = i.find_element(By.XPATH,
                          './/div/div/h3').text
   company = i.find_element(By.XPATH, './/div/div[2]/h4/a').text
   location = i.find_element(By.XPATH, './/div/div[2]/div/span').text
   job_url = i.find_element(By.XPATH,
                            './/div/a').get_attribute('href')

   job_detail = {
       'title': title,
       'company': company,
       'location': location,
       'job_url': job_url
   }
   job_details.append(job_detail)

with open('linkedin_jobs.csv', 'w', newline='', encoding='utf-8') as csvfile:
   fieldnames = ['title', 'company', 'location', 'job_url']
   writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
   writer.writeheader()
   for job_detail in job_details:
       writer.writerow(job_detail)

driver.quit()