Created
November 21, 2017 19:48
-
-
Save lindsaycarbonell/9a328c951d33d74467ed3e1ab44095f6 to your computer and use it in GitHub Desktop.
Race/Gender NCDPI Scraper
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 | |
import http.cookiejar, urllib.request | |
import pandas as pd | |
import webbrowser | |
from bs4 import BeautifulSoup | |
url = "http://apps.schools.nc.gov/ords/f?p=1:220:1214343525970901::NO::P220_SELECTLEA:920" | |
response = requests.get(url) | |
html = response.content | |
soup = BeautifulSoup(html, "html.parser") | |
link_param = soup.find("div", attrs={'class':'t17CVS'}).a['href']; | |
link_to_click = "http://apps.schools.nc.gov/ords/" + link_param; | |
cj = http.cookiejar.CookieJar() | |
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj)) | |
f = open("file.xls", "wb") | |
res = opener.open(link_to_click) | |
f.write(res.read()) | |
f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment