نیا سپریوس میڈیم-آرٹیکلز-استعمال کرنے والے پوٹخون

pip install requests
pip install lxml 
pip install pandas

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': '"Google Chrome";v="129", "Not=A?Brand";v="8", "Chromium";v="129"',
    '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',
    'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36',
}

proxies = {
    'http': 'IP:PORT',
    'https': 'IP:PORT'
}

response = requests.get(
 'https://medium.com/techtofreedom/9-python-built-in-decorators-that-optimize-your-code-significantly-bc3f661e9017',
    headers=headers,
    proxies=proxies
)

import requests

# Headers to simulate a real browser request
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': '"Google Chrome";v="129", "Not=A?Brand";v="8", "Chromium";v="129"',
    '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',
    'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36',
}

url = 'https://medium.com/techtofreedom/9-python-built-in-decorators-that-optimize-your-code-significantly-bc3f661e9017'
response = requests.get(url, headers=headers)

from lxml.html import fromstring

parser = fromstring(response.text)

# Extract data
title = parser.xpath('//h1[@data-testid="storyTitle"]/text()')[0]
author = parser.xpath('//a[@data-testid="authorName"]/text()')[0]
publication_name = parser.xpath('//a[@data-testid="publicationName"]/p/text()')[0]
publication_date = parser.xpath('//span[@data-testid="storyPublishDate"]/text()')[0]
content = '\n '.join(parser.xpath('//div[@class="ci bh ga gb gc gd"]/p/text()'))
auth_followers = parser.xpath('//span[@class="pw-follower-count bf b bg z bk"]/a/text()')[0]
sub_title = parser.xpath('//h2[@id="1de6"]/text()')[0]

# Save data in a dictionary
article_data = {
    'Title': title,
    'Author': author,
    'Publication': publication_name,
    'Date': publication_date,
    'Followers': auth_followers,
    'Subtitle': sub_title,
    'Content': content,
}

print(article_data)

import pandas as pd

# Convert dictionary to DataFrame and save as CSV
df = pd.DataFrame([article_data])
df.to_csv('medium_article_data.csv', index=False)
print("Data saved to medium_article_data.csv")

import requests
from lxml.html import fromstring
import pandas as pd

# Headers to mimic a browser
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': '"Google Chrome";v="129", "Not=A?Brand";v="8", "Chromium";v="129"',
    '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',
    'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36',
}


proxies = {
    'http': 'IP:PORT',
    'https': 'IP:PORT'
}

# Requesting the page
url = 'https://medium.com/techtofreedom/9-python-built-in-decorators-that-optimize-your-code-significantly-bc3f661e9017'
response = requests.get(url, headers=headers, proxies=proxies)

# Parsing the page
parser = fromstring(response.text)

# Extract data
title = parser.xpath('//h1[@data-testid="storyTitle"]/text()')[0]
author = parser.xpath('//a[@data-testid="authorName"]/text()')[0]
publication_name = parser.xpath('//a[@data-testid="publicationName"]/p/text()')[0]
publication_date = parser.xpath('//span[@data-testid="storyPublishDate"]/text()')[0]
content = '\n '.join(parser.xpath('//div[@class="ci bh ga gb gc gd"]/p/text()'))
auth_followers = parser.xpath('//span[@class="pw-follower-count bf b bg z bk"]/a/text()')[0]
sub_title = parser.xpath('//h2[@id="1de6"]/text()')[0]

# Saving data
article_data = {
    'Title': title,
    'Author': author,
    'Publication': publication_name,
    'Date': publication_date,
    'Followers': auth_followers,
    'Subtitle': sub_title,
    'Content': content,
}

# Save to CSV
df = pd.DataFrame([article_data])
df.to_csv('medium_article_data.csv', index=False)
print("Data saved to medium_article_data.csv")