Last active
October 30, 2018 11:23
-
-
Save Saichethan/66d90a82b28cabc443aefdb0894ee8f3 to your computer and use it in GitHub Desktop.
Python Script to get Meta Data
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from bs4 import BeautifulSoup | |
import requests | |
def main(): | |
#r = requests.get('any url') | |
#r = requests.get('https://Saichethan.github.io') | |
u = input("Enter URL :\n") | |
r = requests.get(u) | |
soup = BeautifulSoup(r.content, "html") | |
meta = soup.find_all('meta') | |
for tag in meta: | |
print("\n") | |
print(tag) | |
print("\n") | |
title = soup.title.string | |
print('TITLE :', title) | |
print("\n") | |
for tag in meta: | |
if 'property' in tag.attrs.keys() and tag.attrs['property'].strip().lower() in ['og:type', 'og:url', 'og:image', 'og:site_name', 'og:title']: | |
print('Open Graph Protocol PROPERTY : ',tag.attrs['content'].lower()) | |
print("\n") | |
print('Open Graph Protocol CONTENT : ',tag.attrs['content']) | |
print("\n") | |
if 'name' in tag.attrs.keys(): | |
print('NAME : ',tag.attrs['name'].lower()) | |
print("\n") | |
print('CONTENT : ',tag.attrs['content']) | |
print("\n") | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment