Last active
October 30, 2019 08:53
-
-
Save amenayach/81330c577047b0b19689568a435063bd to your computer and use it in GitHub Desktop.
Simple python script that retrieves Lebanon files site latest news (use Jupyter for best view)
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 requests import get | |
from requests.exceptions import RequestException | |
from contextlib import closing | |
from bs4 import BeautifulSoup | |
#Best used via Jupyter | |
def download_text(url): | |
try: | |
with closing(get(url, stream=True)) as resp: | |
if is_good_response(resp): | |
return resp.content | |
else: | |
return None | |
except RequestException as e: | |
log_error('Error during requests to {0} : {1}'.format(url, str(e))) | |
return None | |
def is_good_response(resp): | |
content_type = resp.headers['Content-Type'].lower() | |
return (resp.status_code == 200 | |
and content_type is not None | |
and content_type.find('html') > -1) | |
def log_error(e): | |
print(e) | |
def get_lb(): | |
url = 'http://www.lebanonfiles.com/category/2' | |
response = download_text(url) | |
if response is not None: | |
html = BeautifulSoup(response, 'html.parser') | |
for p in html.select('.content-detail-section > p'): | |
print(p.text.strip()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment