Created
July 1, 2014 23:25
-
-
Save manugarri/59b7a0e12bd5b4dafff0 to your computer and use it in GitHub Desktop.
Fuck Boe (requires python and requests library)
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 | |
def get_file(url): | |
response = requests.get(url) | |
filename = url.split('/')[-1] | |
print url | |
print('SAVING FILE {}'.format(filename)) | |
with open(filename, 'wb') as file: | |
file.write(response.content) | |
file.close() | |
def get_url(row): | |
try: | |
row = row.replace('Disallow: ','') | |
row = 'http://www.boe.es' + row | |
return row | |
except exception as e: | |
print e,' ', row | |
def get_url(row): | |
try: | |
row = row.replace('Disallow: ','') | |
row = 'http://www.boe.es' + row | |
return row | |
except exception as e: | |
print e,' ', row | |
def download_interesting_file(row): | |
if not 'pdf' in row: | |
return None | |
try: | |
url = get_url(row) | |
get_file(url) | |
except Exception as e: | |
print('ERROR', row) | |
print e | |
def fuck_boe(): | |
amazing_url = 'http://www.boe.es/robots.txt' | |
links = requests.get(amazing_url) | |
links = links.content.splitlines() | |
map(download_interesting_file, links[:100]) | |
if __name__ == '__main__': | |
fuck_boe() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment