charities_scraper.py

from requests import get
from requests.exceptions import RequestException
from contextlib import closing
from bs4 import BeautifulSoup
import re

def simple_get(url):
    """
    Attempts to get the content at `url` by making an HTTP GET request.
    If the content-type of response is some kind of HTML/XML, return the
    text content, otherwise return None.
    """
    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):
    """
    Returns True if the response seems to be HTML, False otherwise.
    """
    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):
    """
    It is always a good idea to log errors.
    This function just prints them, but you can
    make it do anything.
    """
    print(e)

# Get the descriptions of various charitable organizations
raw_html = simple_get('https://www.uschamberfoundation.org/corporate-citizenship-center/descriptions-nonprofits-working-disasters')
html = BeautifulSoup(raw_html, 'html.parser')
for i, p in enumerate(html.select('tr')):
    print(i, p.text)
# Get the links of various charitable organizations
html_page = simple_get("https://www.uschamberfoundation.org/corporate-citizenship-center/descriptions-nonprofits-working-disasters")
soup = BeautifulSoup(html_page)
links = []

for link in soup.findAll('a', attrs={'href': re.compile("^http://")}):
    links.append(link.get('href'))

print(links[4:53])