I wrote a python script to check for an internet connection using socket (Checking network connection), then scrape html from yahoo finance using selenium.
Very frequently (but not always), it gives a ReadTimeoutError (see below)
I can get it to work by checking for an internet connection using http.client instead (see below), but I still want to know why socket interferes with selenium.
def internet(host="8.8.8.8", port=443, timeout=1):
try:
socket.setdefaulttimeout(timeout)
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.connect((host, port))
s.shutdown(socket.SHUT_RDWR)
s.close()
return True
except OSError:
s.close()
return False
# Wait for internet to be available
i = 1
while internet() is False:
time.sleep(1)
if i == 300: # quit if no connection for 5 min (300 seconds)
print('\nIt has been 5 minutes. Aborting attempt.\n')
sys.exit(0)
i += 1
# Get html from yahoo page
symb = 'AAPL'
url = 'http://finance.yahoo.com/quote/{}/history'.format(symb)
chop = webdriver.ChromeOptions()
chop.add_argument('--user-agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:68.0) Gecko/20100101 Firefox/68.0"')
driver = webdriver.Chrome('/Users/fake_user/Dropbox/Python/chromedriver', chrome_options=chop)
driver.get(url)
html_source = driver.page_source
driver.quit()
It throws this error:
urllib3.exceptions.ReadTimeoutError: HTTPConnectionPool(host='127.0.0.1', port=58956): Read timed out. (read timeout=<object object at 0x103af7140>)
I can change the internet function as a workaround, but I can't figure out why socket interferes with selenium:
import http.client as httplib
def internet():
conn = httplib.HTTPConnection("www.google.com", timeout=5)
try:
conn.request("HEAD", "/")
conn.close()
return True
except:
conn.close()
return False