Created
March 2, 2018 23:49
-
-
Save KameronKales/2d1f0a1f0dca667433d175a8c4b64edc to your computer and use it in GitHub Desktop.
re-try!
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
import requests | |
from bs4 import BeautifulSoup | |
leads = [] | |
rates = [] | |
for i in range(3): | |
url = "https://www.greatschools.org/virginia/manassas/prince-william-county-public-schools/schools/?page={}".format(i) | |
r = requests.get(url, headers={'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.95 Safari/537.36'}) | |
soup = BeautifulSoup(r.text, 'lxml') | |
print url | |
for sub_heading in soup.find_all("a", {"class":"open-sans_sb mbs font-size-medium rs-schoolName"}): | |
lead = sub_heading.text | |
leads.append(lead) | |
for sub_headings in soup.find_all("span", {"class":"gs-rating"}): | |
rate = sub_headings.text | |
rates.append(rate) | |
print leads, rates |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment