Last active
December 22, 2015 22:29
-
-
Save joedougherty/6540522 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
import requests | |
from bs4 import BeautifulSoup | |
# Set the URL to download | |
endpoint = 'http://grants.nih.gov/searchGuide/Search_Guide_Results.cfm?Activity_Code=&Expdate_On_After=&OrderOn=ExpirationDate&OrderDirection=ASC&NoticesToo=0&OpeningDate_On_After=&Parent_FOA=All&PrimaryIC=Any&RelDate_On_After=&Status=1&SearchTerms=HIV&PAsToo=1&RFAsToo=1' | |
# Pull down the HTML from that URL | |
r = requests.get(endpoint) | |
page = r.content | |
# Make this parseable | |
parsed_page = BeautifulSoup(page) | |
# Now that you have this parsed_page object, you can call | |
# the methods from BeautifulSoup on it. | |
# Docs: http://www.crummy.com/software/BeautifulSoup/bs4/doc/ | |
# | |
# Taking a quick look at the markup, we can see the target table is | |
# 1.) a <table> element (precisely as expected) and 2.) has a class | |
# of "searchtable." | |
# | |
# All we need to do it use the 'find' method to extract the table | |
# with this class. | |
# | |
# Take a look at the docs to see how this works. | |
extracted_table = parsed_page.find("table", {"class" : "searchtable"}) | |
# This will help convert any special characters into something non-ugly | |
extracted_table = extracted_table.prettify('latin-1') | |
print(extracted_table) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment