ازگر کے ساتھ گوگل نیوز کو کھرچنے کے لئے مرحلہ وار گائیڈ

pip install requests 
pip install lxml

URL = "https://news.google.com/topics/CAAqKggKIiRDQkFTRlFvSUwyMHZNRGRqTVhZU0JXVnVMVWRDR2dKSlRpZ0FQAQ?hl=en-US&gl=US&ceid=US%3Aen"

import requests

url = "https://news.google.com/topics/CAAqKggKIiRDQkFTRlFvSUwyMHZNRGRqTVhZU0JXVnVMVWRDR2dKSlRpZ0FQAQ?hl=en-US&gl=US&ceid=US%3Aen"
response = requests.get(url)

if response.status_code == 200:
    page_content = response.content
else:
    print(f"Failed to retrieve the page. Status code: {response.status_code}")

from lxml import html

# Parse the HTML content
parser = html.fromstring(page_content)

main_news_elements = parser.xpath('//c-wiz[@jsrenderer="ARwRbe"]')

news_data = []

for element in main_news_elements[:10]:
    title = element.xpath('.//c-wiz/div/article/a/text()')[0]
    link = "https://news.google.com" + element.xpath('.//c-wiz/div/article/a/@href')[0][1:]

    
    # Ensure data exists before appending to the list
    if title and link:
        news_data.append({
        "main_title": title,
        "main_link": link,
    })

related_articles = []
related_news_elements = element.xpath('.//c-wiz/div/div/article')

for related_element in related_news_elements:
    related_title = related_element.xpath('.//a/text()')[0]
    related_link = "https://news.google.com" + related_element.xpath('.//a/@href')[0][1:]
    related_articles.append({"title": related_title, "link": related_link})

news_data.append({
    "main_title": title,
    "main_link": link,
    "related_articles": related_articles
})

import json

with open('google_news_data.json', 'w') as f:
    json.dump(news_data, f, indent=4)

proxies = {
    "http": "http://your_proxy_ip:port",
    "https": "https://your_proxy_ip:port",
}

response = requests.get(url, proxies=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',
    'cache-control': 'no-cache',
    'dnt': '1',
    'pragma': 'no-cache',
    'priority': 'u=0, i',
    'sec-ch-ua': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
    'sec-ch-ua-arch': '"x86"',
    'sec-ch-ua-bitness': '"64"',
    'sec-ch-ua-full-version-list': '"Not)A;Brand";v="99.0.0.0", "Google Chrome";v="127.0.6533.72", "Chromium";v="127.0.6533.72"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-model': '""',
    'sec-ch-ua-platform': '"Linux"',
    'sec-ch-ua-platform-version': '"6.5.0"',
    'sec-ch-ua-wow64': '?0',
    'sec-fetch-dest': 'document',
    'sec-fetch-mode': 'navigate',
    'sec-fetch-site': 'none',
    'sec-fetch-user': '?1',
    'upgrade-insecure-requests': '1',
    'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
}

response = requests.get(url, headers=headers)

import requests
import urllib3
from lxml import html
import json

urllib3.disable_warnings()

# URL and headers
url = "https://news.google.com/topics/CAAqKggKIiRDQkFTRlFvSUwyMHZNRGRqTVhZU0JXVnVMVWRDR2dKSlRpZ0FQAQ?hl=en-US&gl=US&ceid=US%3Aen"
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',
   'cache-control': 'no-cache',
   'dnt': '1',
   'pragma': 'no-cache',
   'priority': 'u=0, i',
   'sec-ch-ua': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
   'sec-ch-ua-arch': '"x86"',
   'sec-ch-ua-bitness': '"64"',
   'sec-ch-ua-full-version-list': '"Not)A;Brand";v="99.0.0.0", "Google Chrome";v="127.0.6533.72", "Chromium";v="127.0.6533.72"',
   'sec-ch-ua-mobile': '?0',
   'sec-ch-ua-model': '""',
   'sec-ch-ua-platform': '"Linux"',
   'sec-ch-ua-platform-version': '"6.5.0"',
   'sec-ch-ua-wow64': '?0',
   'sec-fetch-dest': 'document',
   'sec-fetch-mode': 'navigate',
   'sec-fetch-site': 'none',
   'sec-fetch-user': '?1',
   'upgrade-insecure-requests': '1',
   'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
}

# Proxies configuration (replace with your proxy details)
proxy = 'ip:port'
proxies = {
   "http": f"http://{proxy}",
   "https": f"https://{proxy}",
}

# Fetch the page content with the specified headers and proxies
response = requests.get(url, headers=headers, proxies=proxies, verify=False)

# Check if the request was successful
if response.status_code == 200:
   page_content = response.content
else:
   print(f"Failed to retrieve the page. Status code: {response.status_code}")
   exit()

# Parse the HTML content using lxml
parser = html.fromstring(page_content)

# Extract the main news and related articles
main_news_elements = parser.xpath('//*[@id="i10-panel"]/c-wiz/c-wiz')

# Initialize a list to store the extracted news data
news_data = []

# Loop through each main news element
for element in main_news_elements[:10]:
   # Extract the main news title and link
   title = element.xpath('.//c-wiz/div/article/a/text()')
   link = element.xpath('.//c-wiz/div/article/a/@href')

   # Initialize a list to store related articles for this main news
   related_articles = []

   # Extract related news elements within the same block
   related_news_elements = element.xpath('.//c-wiz/div/div/article')

   # Loop through each related news element and extract the title and link
   for related_element in related_news_elements:
       related_title = related_element.xpath('.//a/text()')[0]
       related_link = "https://news.google.com" + related_element.xpath('.//a/@href')[0][1:]
       related_articles.append({"title": related_title, "link": related_link})

   # Append the main news and its related articles to the news_data list
   if title is not None:
       news_data.append({
           "main_title": title,
           "main_link": f'https://news.google.com{link}',
           "related_articles": related_articles
       })
   else:
       continue


# Save the extracted data to a JSON file
with open("google_news_data.json", "w") as json_file:
   json.dump(news_data, json_file, indent=4)

print('Data extraction complete. Saved to google_news_data.json')