Generating Link Preview

import urllib3
import sys
from bs4 import BeautifulSoup
from html import unescape, escape
from termcolor import colored
from urllib.parse import urlparse, urljoin, urlunparse
from datetime import datetime

def print_warning(*args, **kwargs):
    print(*[colored(s, 'red') for s in args], **kwargs)

def print_decision(*args, **kwargs):
    print(*[colored(s, 'green') for s in args], **kwargs)

hdr = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
       'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
       'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
       'Accept-Encoding': 'none',
       'Accept-Language': 'en-US,en;q=0.8',
       'Connection': 'keep-alive'}

urlInfo = urlparse(sys.argv[1])
if len(urlInfo.scheme) == 0 or len(urlInfo.netloc) == 0:
    raise RuntimeError('please use complete URL starting with http:// or https://')
urlBase = urlInfo.scheme + '://' + urlInfo.netloc

http = urllib3.PoolManager()
request = http.request('GET', sys.argv[1], headers=hdr)
content = request.data

soup = BeautifulSoup(content, 'html5lib')

result = {}

def resolve_title():
    global soup

    tag = soup.find('meta', attrs={'property' : 'og:title'})
    if tag is not None and 'content' in tag.attrs:
        print_decision('title acquired from meta \"og:title\"')
        return tag['content']

    tag = soup.find('title')
    if tag is not None:
        print_decision('title acquired from title tag')
        return tag.text

    print_warning('unable to extract title from page')
    return None


def resolve_image():
    global soup, urlBase

    tag = soup.find('meta', attrs={'property' : 'og:image'})
    if tag is not None and 'content' in tag.attrs:
        print_decision('image acquired from meta \"og:image\"')
        return urljoin(urlBase, tag['content'])

    tag = soup.find('link', attrs={'rel' : 'shortcut icon'})
    if tag is not None and 'href' in tag.attrs:
        print_decision('image acquired from shortcut icon')
        return urljoin(urlBase, tag['href'])

    tag = soup.find('img')
    if tag is not None and 'src' in tag.attrs:
        print_decision('image acquired from the first image in page')
        return urljoin(urlBase, tag['src'])

    print_warning('unable to resolve image for page')
    return None

def resolve_description():
    global soup

    tag = soup.find('meta', attrs={'property' : 'og:description'})
    if tag is not None and 'content' in tag.attrs:
        print_decision('description acquired from meta \"og:description\"')
        return tag['content']

    body = soup.find('body')
    if body is not None:
        tag = body.find('p')
        if tag is not None:
            print_decision('description acquired from first paragraph')
            return tag.text

    print_warning('unable to resolve description for page')
    return None


def resolve_domain():
    global soup, urlInfo

    tag = soup.find('meta', attrs={'property' : 'og:url'})
    if tag is not None and 'content' in tag.attrs:
        ogUrlInfo = urlparse(tag['content'])
        if len(ogUrlInfo.netloc) > 0:
            print_decision('domain name acquired from meta \"og:url\"')
            return ogUrlInfo.netloc

    print_decision('domain name acquired from input')
    return urlInfo.netloc

def show_result():
    global result

    for key, val in result.items():
        print(key + ': ' + val)

def build_link_preview():
    global result

    template = r'''
<div class="div-link-preview">
    <div class="div-link-preview-col div-link-preview-col-l">
        <img class="div-link-preview-img" src="{img_link:}">
    </div>
    <div class="div-link-preview-col div-link-preview-col-r">
        <div style="display: block; height: 100%; padding-left: 10px;">
            <div class="div-link-preview-title"><a href="{page_link:}">{page_title:}</a></div>
            <div class="div-link-preview-content">{page_description:}</div>
            <div class="div-link-preview-domain">
            <span style="font-size: 80%;">&#x1F4C5;</span>&nbsp;{proc_date:}
            <span style="font-size: 80%; margin-left: 20px;">&#x1F517;</span>&nbsp;{page_domain:}</div>
        </div>
    </div>
</div>
'''

    return template.format(
        img_link=result['image'],
        page_title=result['title'],
        page_link=result['link'],
        page_description=result['description'],
        page_domain=result['domain'],
        proc_date=result['access_date']
    )


result['title'] = resolve_title()
result['image'] = resolve_image()
result['description'] = resolve_description()
result['domain'] = resolve_domain()
result['link'] = sys.argv[1]
result['access_date'] =  datetime.now().strftime('%b %-d, %Y')

show_result()

print('')
print(build_link_preview())