Created
March 9, 2018 00:52
-
-
Save KameronKales/a314df91bc942445c2c296f9bd49bb34 to your computer and use it in GitHub Desktop.
Python For Sourcers Web-scraping Data
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 | |
import csv | |
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 | |
with open('filename.csv', 'wb') as myfile: | |
wr = csv.writer(myfile, quoting=csv.QUOTE_ALL) | |
wr.writerow(leads) | |
wr.writerow(rates) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment