Created
May 11, 2016 16:29
-
-
Save aborilov/e30b0e4e6097c69150fcf2d99ba2916d 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
#!/usr/bin/env python2 | |
import os | |
import requests | |
from urlparse import urlparse | |
from bs4 import BeautifulSoup | |
urls = ['https://energyplus.net/weather-region/north_and_central_america_wmo_region_4/USA', | |
'https://energyplus.net/weather-region/north_and_central_america_wmo_region_4/CAN'] | |
dirname = 'weatherdata' | |
def parse_files(html): | |
soup = BeautifulSoup(html, 'html.parser') | |
divs = soup.find_all(class_="btn-group-vertical")[0] | |
for div in divs.contents[:-1]: | |
path = div.get('href') | |
filename = path.split('/')[-1] | |
response = requests.get(domain+path) | |
if response.ok: | |
with open(os.path.join(dirname, filename), 'wb') as f: | |
f.write(response.content) | |
print "{} saved".format(filename) | |
def parse_state(html): | |
soup = BeautifulSoup(html, 'html.parser') | |
divs = soup.find_all(class_="btn-group-vertical")[0] | |
for div in divs: | |
response = requests.get(domain+div.get('href')) | |
if response.ok: | |
parse_files(response.content) | |
for url in urls: | |
response = requests.get(url) | |
parsed_uri = urlparse(url) | |
domain = '{uri.scheme}://{uri.netloc}/'.format(uri=parsed_uri) | |
if response.ok: | |
html = response.content | |
soup = BeautifulSoup(html, 'html.parser') | |
divs = soup.find_all(class_="btn-group-vertical")[1] | |
for div in divs: | |
response = requests.get(domain+div.get('href')) | |
if response.ok: | |
parse_state(response.content) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment