Last active
December 4, 2018 18:06
-
-
Save grantglidewell/8f6e8fb41847d7b468325abcb674de37 to your computer and use it in GitHub Desktop.
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 urllib2 import urlopen | |
import time | |
def scrape(url, term) : | |
# Make the http request for the resource | |
response = urlopen(url) | |
# Read the response body to a variable | |
html = response.read() | |
# Create a unique token for filename | |
ts = time.time() | |
# Generate a string for the filename | |
filename = "scrape" + str(ts) + ".html" | |
# Write html as a file to disk | |
f = open(filename, "w") | |
f.write(html) | |
# Open the file | |
s = open(filename, "r") | |
# Read the file and check if the search term is present | |
if term in s.read(): | |
# Return a message to the user that the search term was found | |
return "Found " + term + " in " + url | |
# Return a message to the user that the search term was not found | |
return term + " was not found in " + url | |
print scrape('URL', 'SearchTerm') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment