ازگر کا استعمال کرتے ہوئے آئی ایم ڈی بی ڈیٹا کو کھرچنے کا طریقہ

pip install requests lxml

import requests

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',  # Do Not Track header
    'pragma': 'no-cache',
    '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',
}

response = requests.get('https://www.imdb.com/chart/top/', headers=headers)

proxies = {
    "http": "http://your_proxy_server",
    "https": "https://your_proxy_server"
}

response = requests.get('https://www.imdb.com/chart/top/', headers=headers, proxies=proxies)

from lxml.html import fromstring
import json

# Parse the HTML response
parser = fromstring(response.text)

# Extract the JSON-LD data (structured data) from the script tag
raw_data = parser.xpath('//script[@type="application/ld+json"]/text()')[0]
json_data = json.loads(raw_data)

# Now we have structured movie data in JSON format

movies_details = json_data.get('itemListElement')

# Loop through the movie data
movies_data = []
for movie in movies_details:
    movie_type = movie['item']['@type']
    url = movie['item']['url']
    name = movie['item']['name']
    description = movie['item']['description']
    image = movie['item']['image']
    bestRating = movie['item']['aggregateRating']['bestRating']
    worstRating = movie['item']['aggregateRating']['worstRating']
    ratingValue = movie['item']['aggregateRating']['ratingValue']
    ratingCount = movie['item']['aggregateRating']['ratingCount']
    contentRating = movie['item'].get('contentRating')
    genre = movie['item']['genre']
    duration = movie['item']['duration']
    
    # Append each movie's data to the list
    movies_data.append({
        'movie_type': movie_type,
        'url': url,
        'name': name,
        'description': description,
        'image': image,
        'bestRating': bestRating,
        'worstRating': worstRating,
        'ratingValue': ratingValue,
        'ratingCount': ratingCount,
        'contentRating': contentRating,
        'genre': genre,
        'duration': duration
    })

import pandas as pd

# Convert the list of movies to a pandas DataFrame
df = pd.DataFrame(movies_data)

# Save the data to a CSV file
df.to_csv('imdb_top_250_movies.csv', index=False)

print("IMDB Top 250 movies data saved to imdb_top_250_movies.csv")

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

# Define headers for the 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',
    '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',
}

# Optionally, set up proxies
proxies = {
    "http": "http://your_proxy_server",
    "https": "https://your_proxy_server"
}

# Send the request to the IMDB Top 250 page
response = requests.get('https://www.imdb.com/chart/top/', headers=headers, proxies=proxies)

# Parse the HTML response
parser = fromstring(response.text)

# Extract the JSON-LD data
raw_data = parser.xpath('//script[@type="application/ld+json"]/text()')[0]
json_data = json.loads(raw_data)

# Extract movie details
movies_details = json_data.get('itemListElement')

movies_data = []
for movie in movies_details:
    movie_type = movie['item']['@type']
    url = movie['item']['url']
    name = movie['item']['name']
    description = movie['item']['description']
    image = movie['item']['image']
    bestRating = movie['item']['aggregateRating']['bestRating']
    worstRating = movie['item']['aggregateRating']['worstRating']
    ratingValue = movie['item']['aggregateRating']['ratingValue']
    ratingCount = movie['item']['aggregateRating']['ratingCount']
    contentRating = movie['item'].get('contentRating')
    genre = movie['item']['genre']
    duration = movie['item']['duration']
    
    movies_data.append({
        'movie_type': movie_type,
        'url': url,
        'name': name,
        'description': description,
        'image': image,
        'bestRating': bestRating,
        'worstRating': worstRating,
        'ratingValue': ratingValue,
        'ratingCount': ratingCount,
        'contentRating': contentRating,
        'genre': genre,
        'duration': duration
    })

# Save the data to a CSV file
df = pd.DataFrame(movies_data)
df.to_csv('imdb_top_250_movies.csv', index=False)
print("IMDB Top 250 movies data saved to imdb_top_250_movies.csv")