Skip to content

Instantly share code, notes, and snippets.

@pteacher
Created December 4, 2019 02:57
Show Gist options
  • Save pteacher/7d7a69a669f9eda52915456e52283135 to your computer and use it in GitHub Desktop.
Save pteacher/7d7a69a669f9eda52915456e52283135 to your computer and use it in GitHub Desktop.
Attempt to get codepen.io projects via links [FAILED]
import os
import re
import requests
from fake_useragent import UserAgent
def createFolder(directory):
try:
if not os.path.exists(directory):
os.makedirs(directory)
except OSError:
print ('Error: Creating directory. ' + directory)
def all_files(path):
files = os.listdir(path)
for file in files:
if os.path.isfile(file):
#print file.split('_')[0]
f=open(file,'r')
for x in f:
s = re.findall(r'(https?://codepen.io/[A-Za-z/]+)', x)
if s != []:
print(s[0])
url = s[0]
headers = {'User-agent': ua.random}
r = ses.get(url + ".html", headers=headers)
print r.content
open(file.split('_')[0] + '.html', 'wb').write(r.content)
ua = UserAgent()
ses = requests.Session()
all_files('.')
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment